In this episode, we talk about how a method leveraging ground data and satellite imagery can help prevent wetland losses. &nbsp;<iframe height="200px" width="100%" frameborder="no" scrolling="no" seamless="" src="https://player.simplecast.com/a470d96e-2d6f-42ab-9aff-e52672c3e85a?dark=false" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true"></iframe><hr>This podcast is sponsored by <a href="https://www2.mouser.com/" id="isPasted" rel="nofollow" target="_blank">Mouser Electronics</a>. &nbsp;&nbsp;<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1669714706413-Mouser-sponsor-1-a.jpg" style="width: 766px;" class="fr-fic fr-dib"><hr><h3 id="isPasted">EPISODE NOTES</h3>(2:42) -&nbsp;<a href="https://www.wevolver.com/article/satellites-help-scientists-track-dramatic-wetlands-loss-in-louisiana" target="_blank">Satellites Help Scientists Track Dramatic Wetlands Loss in Louisiana</a>This episode was brought to you by Mouser, our favorite place to get electronic components for any project. Click <a href="https://resources.mouser.com/space/communications-in-space-a-deep-subject" target="_blank">HERE</a> to learn more about the intricacies of deep space communication!<hr>As always, you can find these and other interesting &amp; impactful engineering articles on Wevolver.com.To learn more about this show, please visit our<a href="https://www.wevolver.com/profile/the.next.byte" target="_blank">&nbsp;shows page</a>. By following the page, you will get automatic updates by email when a new show is published. Be sure to give us a follow and review on<a href="https://podcasts.apple.com/nl/podcast/the-next-byte/id1548255861?l=en" rel="nofollow" target="_blank">&nbsp;Apple&nbsp;</a>podcasts,<a href="https://open.spotify.com/show/6lPPsRtegnivsRUEsQ09R7?si=IPMiah7xT_apJtPjqvXMlA" rel="nofollow" target="_blank">&nbsp;Spotify</a>, and most of your favorite podcast platforms!

The researchers mapped land change in coastal Louisiana from 1984 to 2020. Basins that failed to build new soil, such as Terrebonne and Barataria, experienced the most land loss – more than 180 square miles (466 square kilometers). Credit: Jensen et al. Journal of Geophysical Research: Biogeosciences

In this episode, we talk about how a method leveraging ground data and satellite imagery can help prevent wetland losses. 

Podcast: Fighting Wetland Loss From Outer Space

This article was discussed in our <a data-saferedirecturl="https://www.google.com/url?q=https://www.wevolver.com/profile/the.next.byte&source=gmail&ust=1669765825866000&usg=AOvVaw0adN1ijmCNIvr_GfjyI5jV" href="https://www.wevolver.com/profile/the.next.byte" id="isPasted" rel="noopener noreferrer" target="_blank">Next Byte podcast</a>.&nbsp;<iframe height="200px" width="100%" frameborder="no" scrolling="no" seamless="" src="https://player.simplecast.com/a470d96e-2d6f-42ab-9aff-e52672c3e85a?dark=false" class="fr-draggable" data-lf-form-tracking-inspected-kn9eq4roawkarlvp="true" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true" data-lf-vimeo-playback-inspected-kn9eq4roawkarlvp="true"></iframe>The full article will continue below.<hr>From Lake Pontchartrain to the Texas border, Louisiana has lost enough wetlands since the mid-1950s to cover the entire state of Rhode Island. Using a first-of-its kind model, NASA-funded researchers quantified those wetlands losses at nearly 21 square miles (54 square kilometers) per year since the early 1980s.In the <a href="https://doi.org/10.1029/2022JG006794" target="_blank">new study</a>, scientists used the NASA/USGS <a href="https://landsat.gsfc.nasa.gov/" target="_blank">Landsat</a> satellite record to track shoreline changes across Louisiana from 1984 to 2020. Some of those wetlands were submerged by rising seas; others were disrupted by oil and gas infrastructure and hurricanes. But the primary driver of losses was coastal and river engineering, which can have positive or negative effects depending on how it is implemented.Centimeter by centimeter, wetlands are built by the slow accumulation &ndash; accretion &ndash; of mineral sediment and organic material carried by rivers and streams. Accretion makes new soil and counters erosion, the sinking of land, and the rise of sea level.Human intervention and engineering often hold back or divert the flow of sediments that naturally accrete to build and replenish wetlands. For instance, reinforced levees and thousands of miles of canals and excavated banks have isolated many wetlands from the Mississippi River and the network of streams that course through its delta like veins and capillaries. In a few cases, engineering projects have added sediment to delta areas and built new land.<a data-caption="The researchers mapped land change in coastal Louisiana from 1984 to 2020. Basins that failed to build new soil, such as Terrebonne and Barataria, experienced the most land loss – more than 180 square miles (466 square kilometers). Credit: Jensen et al. Journal of Geophysical Research: Biogeosciences" data-fancybox="" data-src="https://d2pn8kiwq2w21t.cloudfront.net/original_images/e1-wetlands_land_loss_map.jpeg" href="https://d2pn8kiwq2w21t.cloudfront.net/original_images/e1-wetlands_land_loss_map.jpeg" target="_blank"></a><div data-v-47d42ddc=""><a data-caption='The researchers mapped land change in coastal Louisiana from 1984 to 2020. Basins that failed to build new soil, such as Terrebonne and Barataria, experienced the most land loss – more than 180 square miles (466 square kilometers). Credit: Jensen et al. Journal of Geophysical Research: Biogeosciences' data-fancybox="" data-src="https://d2pn8kiwq2w21t.cloudfront.net/original_images/e1-wetlands_land_loss_map.jpeg" href="https://d2pn8kiwq2w21t.cloudfront.net/original_images/e1-wetlands_land_loss_map.jpeg" target="_blank"><img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjY4MTM4NTc4OTIwLWUxLXdldGxhbmRzX2xhbmRfbG9zc19tYXAud2lkdGgtMTMyMC5qcGciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 766px;" class="fr-fic fr-dib">The researchers mapped land change in coastal Louisiana from 1984 to 2020. Basins that failed to build new soil, such as Terrebonne and Barataria, experienced the most land loss &ndash; more than 180 square miles (466 square kilometers). Credit: Jensen et al. Journal of Geophysical Research: Biogeosciences</a></div>By analyzing Landsat imagery with tools from cloud computing, the researchers developed a remote sensing model that focused on accretion or the lack of it. Basins that failed to build new soil, such as Terrebonne and Barataria, experienced the most land loss over the study period &ndash; more than 180 square miles (466 square kilometers). Other areas gained ground, including 33.6 square miles (87 square kilometers) of new land in the <a href="https://earthobservatory.nasa.gov/world-of-change/WaxLake" target="_blank">Atchafalaya Basin</a> and 43 square miles (112 square kilometers) in the area known as the &ldquo;Bird&rsquo;s Foot Delta&rdquo; at the mouth of the Mississippi River.&ldquo;The Louisiana coastal system is highly engineered,&rdquo; said Daniel Jensen, lead author and postdoctoral researcher at NASA&rsquo;s Jet Propulsion Laboratory in Southern California. &ldquo;But the fact that ground has been gained in some places indicates that, with enough restoration efforts to reintroduce fresh water supply and sediment, we could see some wetland recovery in the future.&rdquo;Understanding wetland dieback and recovery is critically important because the Mississippi River Delta, like many of the world&rsquo;s deltas, drives local and national economies through farming, fisheries, tourism, and shipping. &ldquo;For the 350 million people who live and farm on deltas around the world, coastal wetlands provide a key link in the food chain,&rdquo; said JPL&rsquo;s Marc Simard, principal investigator of NASA&rsquo;s <a href="https://deltax.jpl.nasa.gov/" target="_blank">Delta-X</a> mission and co-author of the paper.<a data-caption="A map of soil accretion in coastal Louisiana showing higher buildup in parts of Atchafalaya and the “Bird’s Foot Delta,” where the Mississippi River system deposits mineral-rich sediment during flood periods. Credit: Jensen et al. Journal of Geophysical Research: Biogeosciences" data-fancybox="" data-src="https://d2pn8kiwq2w21t.cloudfront.net/original_images/e2-Wetlands_accretion_map.jpeg" href="https://d2pn8kiwq2w21t.cloudfront.net/original_images/e2-Wetlands_accretion_map.jpeg" target="_blank"></a><div data-v-47d42ddc=""><a data-caption='A map of soil accretion in coastal Louisiana showing higher buildup in parts of Atchafalaya and the “Bird’s Foot Delta,” where the Mississippi River system deposits mineral-rich sediment during flood periods. Credit: Jensen et al. Journal of Geophysical Research: Biogeosciences' data-fancybox="" data-src="https://d2pn8kiwq2w21t.cloudfront.net/original_images/e2-Wetlands_accretion_map.jpeg" href="https://d2pn8kiwq2w21t.cloudfront.net/original_images/e2-Wetlands_accretion_map.jpeg" target="_blank"><img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjY4MTM4NjIxNjUzLWUyLVdldGxhbmRzX2FjY3JldGlvbl9tYXAud2lkdGgtMTMyMC5qcGciLCJlZGl0cyI6eyJyZXNpemUiOnsid2lkdGgiOjk1MCwiZml0IjoiY292ZXIifX19" style="width: 766px;" class="fr-fic fr-dib">A map of soil accretion in coastal Louisiana showing higher buildup in parts of Atchafalaya and the &ldquo;Bird&rsquo;s Foot Delta,&rdquo; where the Mississippi River system deposits mineral-rich sediment during flood periods. Credit: Jensen et al. Journal of Geophysical Research: Biogeosciences</a></div> In several airborne and field campaigns since 2016, the Delta-X research team has been studying the Mississippi River Delta, the seventh largest on Earth, using airborne sensing and field measurements of water, vegetation, and sediment changes in the face of rising sea level. The Landsat analysis builds on this airborne mission. Delta-X is part of NASA&rsquo;s Earth Venture Suborbital (EVS) program, managed at NASA&rsquo;s Langley Research Center in Hampton, Virginia.The new model by Jensen and colleagues is the first to directly estimate soil accretion rates in coastal wetlands using satellite data. Working with ground-based accretion records from Louisiana&rsquo;s Coastwide Reference Monitoring System, the scientists were able to estimate amounts of mineral sediment from water pixels in the Landsat imagery and organic material from the land pixels.The researchers said their approach could be applied beyond Louisiana because wetland loss and resiliency is a <a href="https://landsat.gsfc.nasa.gov/article/landsat-reveals-dramatic-loss-of-global-wetlands-over-past-two-decades/" target="_blank">global phenomenon</a>. From the <a href="https://landsat.gsfc.nasa.gov/article/where-the-wetlands-are/" target="_blank">Great Lakes</a> to the Nile Delta, the Amazon to Siberia, wetlands are found on every continent except Antarctica. And they are declining in most places. Wetlands were recently called some of the &ldquo;most vulnerable, most threatened, most valuable, and most diverse&rdquo; ecosystems on the planet, according to an international<a href="https://agupubs.onlinelibrary.wiley.com/doi/10.1002/9781119536789.ch5" target="_blank">&nbsp;analysis</a> co-authored by NASA researchers.

A satellite image of the Mississippi River Delta with land shown in bright green and water shown in dark blue. Credit: NASA Earth Observatory image by Michael Taylor and Adam Voiland, using Landsat data from the U.S. Geological Survey

New research uses NASA satellite observations and advanced computing to chronicle wetlands lost (and found) around the globe.

Satellites Help Scientists Track Dramatic Wetlands Loss in Louisiana

Representational image of soldiers participating in toxic industrial chemical protection and detection equipment training. Source: USArmy-Flickr

A student article showcasing an Android application called DOT-HAZMAT based on Machine Learning and Computer Vision that locates and categorizes HAZMAT placards in perilous rescue operations.


DOT-HAZMAT: An Android application for  detection of hazardous materials (HAZMAT)

Last year marked the beginning of the UN Decade on Ecosystem Restoration. This initiative is aimed at halting the degradation of ecosystems by 2030, preventing it going forward and, if possible, remedying the damage that has already been done. Delivering on these kinds of projects calls for accurate foundations, such as surveys and maps of the existing vegetation.In an interview, Ralph Dubayah, the Principal Investigator of NASA&rsquo;s Global Ecosystem Dynamics Investigation (GEDI) mission, explains: &ldquo;We simply do not know how tall trees are globally. [...] We need good global maps of where trees are. Because whenever we cut down trees, we release carbon into the atmosphere, and we don&rsquo;t know how much carbon we are releasing.&rdquo;Analysing and preparing precisely this kind of environmental data is what the <a href="https://prs.igp.ethz.ch/ecovision.html" target="_blank">EcoVision Lab</a> in the ETH Zurich Department of Civil, Environmental and Geomatic Engineering specialises in. Founded by ETH Zurich Professor Konrad Schindler and University of Zurich Professor Jan Dirk Wegner in 2017, this lab is where researchers are developing machine learning algorithms that enable automatic analysis of large-scale environmental data. One of those researchers is Nico Lang. In his doctoral thesis, he developed an approach &ndash; based on neural networks &ndash; for deriving vegetation height from optical satellite images. Using this approach, he was able to create the first vegetation height map that covers the entire Earth: the <a href="https://nlang.users.earthengine.app/view/global-canopy-height-2020" target="_blank">Global Canopy Height Mapcall_made</a>.The map&rsquo;s high resolution is another first: thanks to Lang&rsquo;s work, users can zoom in to as little as 10x10 metres of any piece of woodland on Earth and check the tree height. A forest survey of this kind could lead the way forward particularly in dealing with carbon emissions, as tree height is a key indicator of biomass and the amount of carbon stored. &ldquo;Around 95 percent of the biomass in forests is made up of wood, not leaves. Thus, biomass strongly correlates with height,&rdquo; explains Konrad Schindler, Professor of Photogrammetry and Remote Sensing.<h2>Trained with laser scanning data from space</h2>But how does a computer read tree height from a satellite image? &ldquo;Since we don&rsquo;t know which patterns the computer needs to look out for to estimate height, we let it learn the best image filters itself,&rdquo; Lang says. He shows his neural network millions of examples &ndash; courtesy of the images from the two <a href="https://sentinel.esa.int/web/sentinel/missions/sentinel-2" target="_blank">Copernicus Sentinel-2 satellitescall_made</a> operated by the European Space Agency (ESA). These satellites capture every location on Earth every five days with a resolution of 10x10 metres per pixel. They are the highest-quality images currently available to the public.&nbsp;<blockquote>&quot;The trick here is that we stack the image filters. This gives the algorithm contextual information, since every pixel, from the previous convolution layer, already includes information about its neighbours.&rdquo; &nbsp; &nbsp; &nbsp; &nbsp; &nbsp; <cite>Konrad Schindler</cite>&nbsp; &nbsp; &nbsp; &nbsp;&nbsp;</blockquote>The algorithm must also have access to the correct answer &ndash; that is, the tree height derived from space laser measurements from <a href="https://gedi.umd.edu/" target="_blank">NASA&rsquo;s GEDI missioncall_made</a>. &ldquo;The GEDI mission delivers globally distributed, sparse data on the vegetation height between the latitudes of 51 degrees north and south, so the computer sees many different vegetation types in the training process,&rdquo; Lang explains. With the input and answer, the algorithm can acquire the filters for textural and spectral patterns itself. Once the neural network has been trained, it can automatically estimate the vegetation height from the more than 250,000 images (some 160 terabytes of data) needed for the global map.In specialist jargon, Lang&rsquo;s neural network is known as a convolutional neural network (CNN). The &ldquo;convolution&rdquo; is a mathematical operation in which the algorithm slides a 3x3 pixel filter mask over the satellite image to obtain information on brightness patterns in the image. &ldquo;The trick here is that we stack the image filters. This gives the algorithm contextual information, since every pixel, from the previous convolution layer, already includes information about its neighbours,&rdquo; Schindler says. As a result, the EcoVision Lab was the first to successfully use satellite maps to also reliably estimate tree heights of up to 55 metres.Because their many layers make these neural networks &ldquo;deep&rdquo;, this method is also called &ldquo;deep learning&rdquo;. It heralded a major revolution in image processing around ten years ago. However, dealing with the sheer amount of data remains very challenging: calculating the global vegetation height map would take a single powerful computer three years. &ldquo;Fortunately, we have access to the ETH Zurich high-performance computing cluster, so we didn&rsquo;t have to wait three years for the map to be calculated,&rdquo; Lang says with a laugh.<h2>Transparency by estimating uncertainties</h2>Lang didn&rsquo;t prepare just one CNN for this task, but several. This is known as an ensemble. &ldquo;An important aspect for us was also letting users know the uncertainty of the estimate,&rdquo; he says. The neural networks &ndash; five altogether &ndash; were trained independently of each other, with each one returning its own estimate of tree height. &ldquo;If all the models agree, then the answer is clear based on the training data. If the models arrive at different answers, it means there is a higher uncertainty in the estimate,&rdquo; Lang explains. The models also incorporate uncertainties in the data itself: if a satellite image is hazy, for instance, the uncertainty is greater than when atmospheric conditions are good.<h2>Foundation for future ecological research</h2>Thanks to its high resolution, Lang&rsquo;s global map provides detailed insights: &ldquo;We have already discovered interesting patterns,&rdquo; Schindler says. &ldquo;In the Rocky Mountains, for example, forests are managed in fixed sections, and the rainforest also forms interesting structures that can&rsquo;t be coincidental.&rdquo; Now ecologists can interpret these captured patterns and data globally.<blockquote>&ldquo;Thanks to Sentinel-2, vegetation height can be recalculated every five days, making it possible to monitor&nbsp; rainforest deforestation.&rdquo; <cite>Nico Lang</cite>&nbsp; &nbsp; &nbsp; &nbsp;&nbsp;</blockquote>To allow this research to continue, the map and its source code will be made publicly accessible (see link). The first interested parties have already been in touch: Walter Jetz, a professor at Yale University, wants to use the Global Canopy Height Map for biodiversity modelling. However, the map could also be of interest to governments, administrative bodies and NGOs. &ldquo;Thanks to Sentinel-2, vegetation height can be recalculated every five days, making it possible to monitor rainforest deforestation,&rdquo; Lang says.In addition, he adds, it is now also possible to globally validate regional findings, such as the way tropical leaf canopies act as a climate buffer. Coupled with the <a href="https://highcarbonstock.org/" target="_blank">High Carbon Stock Approachcall_made</a>, which classifies forests according to their carbon storage and biodiversity value, the vegetation height map is an important foundation for maintaining and strengthening ecosystems. According to Lang&rsquo;s calculations, vegetation with a height of more than 30 metres is found on only 5 percent of the landmass, and only 34 percent of it is located in protected areas.With the GEDI mission set to end in 2023, Lang&rsquo;s newly developed approach offers the possibility to continue mapping vegetation height in future. However, getting the GEDI mission extended &ndash; something that is currently also being discussed in the <a href="https://www.theguardian.com/environment/2022/mar/20/nasa-urged-to-extend-life-of-key-climate-sensor-that-maps-worlds-forests-gedi-aoe" target="_blank">mediacall_made</a> internationally &ndash; is key to comparing its data with future satellite missions such as the <a href="https://earth.esa.int/eogateway/missions/biomass" target="_blank">ESA Biomass missioncall_made</a> and calibrating the model for changes.

Researchers at ETH Zurich have developed a world map that for the first time uses machine learning to derive vegetation heights from satellite images in high resolution. (Image: EcoVision Lab)

Using an artificial neural network, researchers at ETH Zurich have created the first high-​resolution global vegetation height map for 2020 from satellite images. 

Neural network can read tree heights from satellite images

Measurement of the significant wave height, period and direction of waves in open water, and analysis of these measurements over short or long stretches of time provide information which is crucial to many people and organizations. Most obviously, it helps skippers of vessels such as fishing boats as well as operators of civilian and military shipping fleets to monitor and predict the conditions in which they sail.But wave measurement has many other uses such as scientific research, to learn about ocean behavior, extreme weather events, global warming and more. Wave measurement is also used for weather forecasting, and in the construction of permanent infrastructure such as wind turbines or temporary installations such as fish farms.For decades wave measurement was a low-technology, expensive process which required the deployment of large, special-purpose buoys. The status quo was disrupted when <a href="https://www.seaviewsystems.com/" rel="noopener noreferrer" target="_blank">Seaview Systems</a>, based in Dexter, Michigan in the US, introduced a wholly new approach. Its SVS-603HR Wave Sensor is based on an <a href="https://www.xsens.com/mti-3" rel="noopener noreferrer" target="_blank">MTi-3 motion sensor</a> from Xsens, and runs a suite of sophisticated algorithms developed by the computer scientists at Seaview Systems.Much smaller, cheaper, and lower-power than the old technology – but just as accurate – the SVS-603HR can easily be installed on almost any type of new or existing buoy, or in an autonomous surface vehicle (ASV) or autonomous underwater vehicle (AUV).So what part does Xsens MEMS motion-sensor technology play in measuring waves?<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1648108998705-LimnoTech+Toledo+Crib+Wave+Buoy020+-+2.jpg" style="width: 300px;" class="fr-fic fr-dib">A typical deployment of a small buoy equipped with the SVS-603HR wave sensorPhoto credits: Ed Verhamme, LimnoTech and Great Lakes Outreach Media<h3>A new generation of technology for oceanography</h3>The modern era of wave measurement began in 1968 with the introduction of the Waverider® buoy manufactured by Datawell of The Netherlands. This type of wave measurement device relies on simple electro-mechanical technology to measure wave motion. The stability, accuracy and repeatability of its measurements depend on the special design of the buoy’s hull: the buoy is large and heavy for stability, and its shape is optimized for the single function of measuring wave motion.The uniform, optimized hull produces accurate wave measurements. But this dedicated buoy is expensive to buy, difficult to install, and consumes large amounts of power.What users really want is a system which is small and easy to deploy, and enables the use of low-cost, general-purpose buoys. In the past, the number of locations at which wave measurement could be performed was limited by the cost and inconvenience of the old technology. Wave measurement devices that are cheaper and easier to deploy can proliferate to give a much more granular picture of the behavior of oceans and lakes.This was the mission of Seaview Systems when it set out to reinvent the wave sensor. Its innovation was to deploy modern electronics technology to eliminate the drawbacks of the old electro-mechanical method. The MTi motion sensors from Xsens combine an array of miniature MEMS accelerometer, gyroscope and magnetometer chips with sensor fusion software to produce accurate measurements of motion in three dimensions, as well as the heading relative to magnetic North. These measurements are continually refreshed at an output data rate up to 400Hz.A motion sensor such as the MTi-3 Attitude and Heading Reference System (<a href="https://www.xsens.com/ahrs" rel="noopener noreferrer" target="_blank">AHRS</a>), the device chosen by Seaview Systems, measures just 12.1 x 12.1 x 2.55mm, and weighs only 0.6g. This meant that Seaview Systems was able to develop a robust wave measurement device in a marinized enclosure which is only 53.5 x 68 x 23mm. The SVS-603HR’s power consumption is typically just 150mW, which means that it only requires a small solar panel and battery to maintain uninterrupted operation.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1648109068080-SeaviewSystems-SVS-603HR.png" style="width: 300px;" class="fr-fic fr-dib">The SVS-603HR is housed in an anodized aluminum enclosure which has been pressure proven to 550psiThe other crucial innovation by Seaview Systems was to make its system compatible with almost any buoy of any type, as well as with new types of devices such as the ASV. It achieved this by developing sensor data-processing algorithms, a method which was only possible because the measurement output from the MTi-3 is so fast, detailed and accurate.The algorithms detect and cancel out the behavior of the craft which carries the sensor (the buoy or ASV), so that the sensor’s measurements represent only wave motion. Seaview Systems has built up a library of data on the behavior of more than 30 of the most widely used buoy hulls worldwide, giving users a ready-made solution for most deployments. For any new hull or ASV, the sensor automatically implements the most appropriate algorithm to match its behavior on the water.These algorithms allow the SVS-603HR sensor to be mounted on almost any type of new buoy, or retrofitted onto existing buoys. The small size of the wave sensor and its low power requirement means that it can be successfully used on small and light buoys which can be launched without the need for special equipment. As a result, the cost and difficulty of installing wave measurement equipment have plummeted, and buoys with Seaview Systems technology on board are proliferating across the world’s oceans and large inland waters such as the Great Lakes.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1648109247060-buoy+deployment+screen+grab1.jpg" style="width: 300px;" class="fr-fic fr-dib">Buoys equipped with an SVS-603HR wave sensor are small, light, and easy to launchTimothy Crandle, PhD, Principal of Seaview Systems, says that the Seaview Systems algorithms rely on stable, accurate readings of 3D motion and heading. He says, "Before developing the SVS-603HR we conducted detailed evaluations of the motion sensor modules on the market. We chose the MTi-3 because we were highly impressed by the quality of its measurements."He adds that the <a href="https://www.xsens.com/software-downloads" rel="noopener noreferrer" target="_blank">MT Software Suite</a> supplied with the MTi-3 by Xsens is a valuable complement to the sensor hardware, as it enables Seaview Systems to configure the device’s outputs, and easily perform system calibration.The SVS-603HR is now poised to unleash the untapped potential for ocean monitoring worldwide, enabling accurate, reliable and low-cost wave sensing and supporting the implementation of many more applications for this specialist branch of marine science.Information about Seaview Systems’ SVS-603HR wave sensor may be found <a href="https://www.seaviewsystems.com/products/data-buoy-instruments/svs-603-inertial-wave-sensor/" rel="noopener noreferrer" target="_blank">here</a>.

based on Xsens MTi-3

Ocean research benefits from new wave measurement sensor

In this episode, we talk about how a group at MIT has developed an easy-to-use handheld device to treat internal bleeding and a joint effort between MIT and Imperial College London which resulted in a marine mammal call sensor that can leverage machine learning models locally using power generated from the mammal calls. As always, you can find these and other interesting &amp; impactful engineering articles on Wevolver.com.&nbsp;<iframe height="200px" width="100%" frameborder="no" scrolling="no" seamless="" src="https://player.simplecast.com/85e3afbd-7cfe-4610-9f0b-a640df7c26c2?dark=false" class="fr-draggable" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true"></iframe><hr>This podcast is sponsored by <a href="https://www2.mouser.com/" id="isPasted" rel="nofollow" target="_blank">Mouser Electronics</a>. &nbsp;&nbsp;<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1647956698241-Mouser-sponsor-1-a.jpg" style="width: 766px;" class="fr-fic fr-dib"><hr><h3 id="isPasted">EPISODE NOTES</h3>(3:38) -&nbsp;<a href="https://www.wevolver.com/article/handheld-surgical-robot-can-help-stem-fatal-blood-loss/" target="_blank">Handheld Surgical Robot</a>(16:13) -&nbsp;<a href="https://www.wevolver.com/article/ultra-efficient-machine-learning-offers-on-device-inference-powered-solely-by-sound-under-the-sea/" target="_blank">Sound Powered Marine Call Identifier</a>Episode 62 was brought to you by Mouser Electronics, Farbod &amp; Daniel’s favorite electronics distributor. Click <a href="https://eu.mouser.com/empowering-innovation/artificial-intelligence/ai-saves-lives#talksaving" target="_blank">here&nbsp;</a>to read the article discussing the utilization of AI to save lives in rural regions of Africa.<hr>About the podcast:Every day, some of the most innovative universities, companies, and individual technology developers share their knowledge on Wevolver. To ensure we can also provide this knowledge for the growing group of podcast listeners, we started a collaboration with two young engineers, Daniel Scott Mitchell &amp; Farbod Moghaddam who discuss the most interesting content in this podcast series.&nbsp;To learn more about this show, please visit the <a href="https://www.wevolver.com/profile/the.next.byte" target="_blank">shows page</a>. By following the page, you will get automatic updates by email when a new show is published.Be sure to give us a follow and review on <a href="https://podcasts.apple.com/nl/podcast/the-next-byte/id1548255861?l=en" rel="nofollow" target="_blank">Apple</a> podcasts, <a href="https://open.spotify.com/show/6lPPsRtegnivsRUEsQ09R7?si=IPMiah7xT_apJtPjqvXMlA" rel="nofollow" target="_blank">Spotify</a>, and most of your favorite podcast platforms!

Matt Johnson (right) and Laura Brattain test a new medical device on an artificial model of human tissue and blood vessels. The device helps users to insert a needle and guidewire quickly and accurately into a vessel, a crucial first step to halting rapid blood loss. Photo: Nicole Fandel

In this episode, we talk about how a group at MIT has developed an easy-to-use handheld device to treat internal bleeding and a joint effort between MIT and Imperial College London which resulted in a marine mammal call sensor that can leverage machine learning models locally

Podcast: AI Powered Devices For Saving Lives & Studying Oceans

This article was discussed in our <a data-saferedirecturl="https://www.google.com/url?q=https://www.wevolver.com/profile/the.next.byte&source=gmail&ust=1647995729616000&usg=AOvVaw0aQXASXSRqe8X0H1Q367Vs" href="https://www.wevolver.com/profile/the.next.byte" id="isPasted" rel="noopener noreferrer" target="_blank">Next Byte podcast</a>.&nbsp;<iframe height="200px" width="100%" frameborder="no" scrolling="no" seamless="" src="https://player.simplecast.com/85e3afbd-7cfe-4610-9f0b-a640df7c26c2?dark=false" class="fr-draggable" data-lf-yt-playback-inspected-kn9eq4roawkarlvp="true"></iframe>The full article will continue below.<hr>Energy efficiency and machine learning don&rsquo;t always go hand-in-hand. While low-power sensor networks can make great use of deep-learning systems for processing data, they typically do so by transmitting said data to remote servers equipped with powerful processors and plenty of memory.On-device machine learning at the microprocessor scale &mdash; known as &ldquo;tinyML&rdquo; &mdash; looks to shift the work from data centers into the field, and a team of researchers at Imperial College London and the Massachusetts Institute of Technology (MIT) are hoping to go still further: The development and deployment of a machine learning system so efficient it can perform inference on energy-harvesting sensors deployed under the sea, operating entirely without batteries.<h1>Fundamental challenges</h1>The team, including first author Yuchen Zhao, aimed to deliver an answer to a simple question: Whether or not it is possible to design and build battery-free devices capable of machine learning and on-device inference, operable in underwater environments.Building on earlier works on battery-free sensing and energy-efficient machine learning systems, the team built a prototype: A device, built around an off-the-shelf microcontroller, which could harvest energy, capture sounds, process them through a lightweight deep neural network to identify particular marine species, and transmit the results back to a receiver unit &mdash; and all without needing a battery.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQ3MzgyMTIxMzUwLXVuZGVyd2F0ZXJtbDIuanBnIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 300px;" class="fr-fic fr-dib" alt="An overview diagram of an undersea sensor system which harvests sound energy and uses backscatter communication to transmit the results of on-board inference based on animal sounds captured by a hydrophone.">Despite having mere microwatts of power to play with, an energy-harvesting sensor system has been proven capable of on-device inference &mdash; even underwater.The idea of an ultra-low-power sensor, underwater or otherwise, which is powered by harvested energy and communicates via energy-efficient backscatter isn&rsquo;t new, but the team points out the majority of previous work has been focused on land rather than sea operation, and that most simply power their sensors but rely on battery- or mains-powered devices with more computational capabilities to process captured data.Performing computation on-device, meanwhile, would not only increase the flexibility of the deployed sensor systems but also work around significant issues with current approaches &mdash; including the low-bandwidth nature of underwater communications introducing large delays to the process, and the need to store captured data in-memory until a receiver is available.&ldquo;To overcome these challenges,&rdquo; the team writes, &ldquo;our node performs on-board inference. This results in a lower-power, time-and-resource efficient, and more scalable system design.&rdquo;<h1>Three-part hardware harmony</h1>The team&rsquo;s prototype boasts very modest specifications. At its heart is a Texas Instruments MSP430FR5994 microcontroller development board, connected to an omnidirectional hydrophone for capturing undersea sounds. The same sound energy as monitored by the sensor node also serves as its power source, being converted by a transducer into electrical energy.Despite the harvested energy being minimal at best, and the device lacking an integrated battery for energy accumulation over time, the prototype delivers on the team&rsquo;s goal: As energy is harvested, the microcontroller powers up, samples audio from the sensor, performs inference on-device, and then transmits the resulting classification via backscatter uplink.<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQ3MzgyMjg1ODY4LXVuZGVyd2F0ZXJtbDQuanBnIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 300px;" class="fr-fic fr-dib" alt="A picture of a Texas Instruments MSP430FR4994 microcontroller development board, next to a white and blue device described by its creators as an energy harvesting backscatter system for underwater use.">The team&#39;s prototype is based on a Texas Instruments MSP430 mcirocontroller, chosen for its low power demands, and a potted backscatter system designed two years earlier.Impressively, everything is handled in just 5.4mJ of power &mdash; with the inference stage taking three seconds to complete at a draw of 1.3mW. While by far the highest draw of the process, the researchers claim it represents a considerable saving over the typical approach of simply transmitting the raw data for later analysis &mdash; estimating that backscatter transmission of audio data would consume over 30 per cent more power than performing the inference on-device and simply transmitting the result, while cutting the time taken considerably.&ldquo;This result,&rdquo; the team notes, &ldquo;demonstrates that battery-free edge inference is feasible, and that it makes on-board inference both more efficient and faster, even with this preliminary inference model. We envision that the gains can be significantly improved as the research evolves.&rdquo;<h1>Training day</h1>The secret to the project&rsquo;s success is a highly-efficient machine learning model, trained off-device on a more powerful system using the Watkins Marine Mammal Sounds Database. The audio data was resampled to match the sample rate of the microcontroller&rsquo;s analog to digital converter (ADC) before being used to train high-level Keras models via TensorFlow.To generate smaller microcontroller-compatible models from these high-level Keras models, the team turned to Keras2C. &ldquo;This library generates smaller DNN models than TensorFlow Lite does,&rdquo; the researchers explain, &ldquo;and requires fewer third-party libraries when generating models.&rdquo;<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQ3MzgyMjk4Mjk0LXVuZGVyd2F0ZXJtbDMuanBnIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 300px;" class="fr-fic fr-dib" alt="A diagram showing the training and operation flow of the proposed underwater audio classification system, showing a centralised training system which occurs offline to produce a high-level model which is then processed for use on-device.">The team trained the model off-device, then processed it for use in the resource-constrained environment of the energy-harvesting microcontroller.In simulated testing, based on samples held-back from the Watkins dataset, performance of the resulting microcontroller-deployed on-device inference model showed promise: The team reports an 84 per cent success rate for offline single-mammal classification, though switching to eight-mammal classification dropped accuracy down to 76 per cent while increasing the model size beyond that which could be deployed on the prototype.Online accuracy, using data captured by the prototype&rsquo;s analog to digital converter based on recordings of four marine mammals, proved lower: 63 per cent, a drop the team attributes to the relatively low number of testing samples and a loss of data resolution during the sampling process.&ldquo;Nonetheless,&rdquo; the team notes, &ldquo;this result demonstrates that our prototype was successful in on-board classification of four marine animals with a reasonable accuracy at extremely low power, and this accuracy may be improved as the research evolves and with more comprehensive online evaluation.&rdquo;<img src="https://images.wevolver.com/eyJidWNrZXQiOiJ3ZXZvbHZlci1wcm9qZWN0LWltYWdlcyIsImtleSI6ImZyb2FsYS8xNjQ3MzgyMzA5NDcxLXVuZGVyd2F0ZXJtbDUuanBnIiwiZWRpdHMiOnsicmVzaXplIjp7IndpZHRoIjo5NTAsImZpdCI6ImNvdmVyIn19fQ==" style="width: 300px;" class="fr-fic fr-dib" alt="A boxplot and kernel density chart, showing the offline test accuracy of various machine learning models: The highest accuracy is seen with models of N-32 size.">The highest accuracy came from models with an input layer size of 32 (N-32), but this proved too large for deployment on the microcontroller even after processing.The researchers suggest a range of directions for future study, including on-device model personalization to boost accuracy, a model-optimized hardware/software co-design approach to boost performance and efficiency, and the investigation of methods to allow training, rather than just inference, to occur on-device.The team&rsquo;s work has been made available under open-access terms <a href="https://arxiv.org/abs/2202.08174" target="_blank">on Cornell&rsquo;s arXiv preprint server</a>. The researchers also made their underwater backscatter system available under the permissive Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International license upon its development two years ago, with code and design files <a href="https://github.com/saadafzal24/Underwater-Backscatter" target="_blank">available on GitHub</a>.<h1>Reference</h1>Yuchen Zhao, Sayed Saad Afzal, Waleed Akbar, Osvy Rodriguez, Fan Mo, David Boyle, Fadel Adib, and Hamed Haddadi: <cite>Towards Battery-Free Machine Learning and Inference in Underwater Environments</cite>. DOI <a href="https://doi.org/10.48550/arXiv.2202.08174" target="_blank">arXiv:2202.08174 [cs.LG]</a>.

While most machine learning takes place in high-power data centers, these researchers are trying to deploy the technology beneath the waves.

Designed to bring machine learning to the Earth's last great frontier, a prototype smart sensor platform users on-device inference to classify marine mammal calls — powering itself exclusively from the sounds it captures.

Ultra-efficient machine learning offers on-device inference powered solely by sound - under the sea

Autonomous Underwater Vehicles (AUVs) play a vital role in fields such as hydrocarbon drilling and extraction, marine surveying and aquatic environmental monitoring. An AUV can perform functions in which it is difficult for divers to accomplish, and can descend to depths which would put human operators in danger.Most AUV products on the market today are large, capable of carrying heavy payloads, and fitted with a large battery to enable them to stay underwater for long periods of time. This type of product suits customers such as oil companies, which can afford the substantial cost not only to buy a large AUV, but to transport it to where it is needed, to manoeuvre it into position, and to operate it.UK-based marine products supplier <a href="https://planet-ocean.co.uk/wp/" rel="noopener" target="_blank">Planet Ocean</a> spotted that this left a gap in the market for a smaller, more affordable AUV. This realization spurred the development of <a href="https://planet-ocean.co.uk/wp/?page_id=4509" rel="noopener" target="_blank">ecoSUB</a>, a range of small, low-cost AUVs which can be easily carried, launched, operated and retrieved from the water by a single person.Its goal was to democratize the use of AUVs: to bring them within reach of all research institutes, universities, commercial users, users in less developed countries, and of other users who have limited resources.&nbsp;It turned out that the design of this innovative AUV required a motion tracking sensor which was both compact and accurate.<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1619774171204-1619774171204.png" alt="Capture 2" width="1289" srcset="https://www.xsens.com/hs-fs/hubfs/Capture%202.png?width=645&amp;name=Capture%202.png 645w, https://www.xsens.com/hs-fs/hubfs/Capture%202.png?width=1289&amp;name=Capture%202.png 1289w, https://www.xsens.com/hs-fs/hubfs/Capture%202.png?width=1934&amp;name=Capture%202.png 1934w, https://www.xsens.com/hs-fs/hubfs/Capture%202.png?width=2578&amp;name=Capture%202.png 2578w, https://www.xsens.com/hs-fs/hubfs/Capture%202.png?width=3223&amp;name=Capture%202.png 3223w, https://www.xsens.com/hs-fs/hubfs/Capture%202.png?width=3867&amp;name=Capture%202.png 3867w" sizes="(max-width: 1289px) 100vw, 1289px" class="fr-fic fr-dii" style="width: 777px;">Xsens makes accurate underwater navigation possibleThe efficient operation of the ecoSUB AUV calls for accurate location data derived by the dead reckoning technique. On the surface of the water, geolocation is easy: satellite positioning signals determine position to a typical accuracy of ±5m.The satellites’ RF signals do not penetrate water, however, so the ecoSUB AUV determines its position by continuously tracking its motion relative to its launch point on the surface.&nbsp;For this motion tracking function, ecoSUB uses the <a href="https://www.xsens.com/inertial-sensor-modules" rel="noopener" target="_blank">Xsens MTi-3 AHRS</a> (Attitude and Heading Reference System), together with a discrete pressure sensor for depth measurement. The MTi-3 sensor provides the ecoSUB with highly accurate measurements of roll, pitch, heading and acceleration. The ecoSUB’s on-board computer continuously converts these measurements into position coordinates.<iframe src="https://www.youtube.com/embed/7EEqPm0ylWk?&amp;t=6s&amp;wmode=opaque&amp;rel=0" frameborder="0" allowfullscreen="" class="fr-draggable" style="width: 788px; height: 501px;"></iframe>The especially challenging requirements of designing a small and light AUV made the Xsens motion tracking sensor the ideal fit.&nbsp;‘The fundamental design objective for the ecoSUB was to make an AUV that was small and light enough for an average person to lift, while still having enough load-carrying capacity and range to perform useful tasks. Our design for the ecoSUB fits an “A” size sonar buoy tube – it is 1m long, and weighs just 4kg. To optimize the ecoSUB’s range and dynamic characteristics, we needed to apportion as much of the internal space as possible to the battery and the motor. So the motion sensor and the rest of the control electronics system have to be packed in a small space, in the presence of the strong magnetic fields generated by the motor system. And of course the accuracy of the AUV’s position data is absolutely crucial. When the AUV is being used for instance to detect an oil leak or to monitor variations in the oxygen content of sea water, users need to know exactly where in three dimensions it has taken its measurements.’Jeremy Sitbon, ecoSUB Chief Robotics EngineerXsens MTi-3 motion tracker: Small, light, reliableThe constraints applying to the design of the ecoSUB meant the motion sensor had to offer three essential characteristics:<ul><li>High accuracy in the sensor’s motion tracking data&nbsp;</li><li>Dependability, with high immunity to magnetic interference</li><li>Small size and weight</li></ul>The Xsens MTi-3 AHRS delivers on all three counts. The MTi-3 integrates multiple sensor functions including 3D accelerometer, gyroscope and magnetometer plus a processor.The accuracy of the sensor’s static measurements of roll and pitch is ±0.5°, and for yaw the value is ±2°. In use, the ecoSUB typically achieves positioning accuracy of ±5% of the distance travelled when using only the MTi-3 motion sensor and the pressure sensor measurements.The accuracy of the sensor’s measurements remains stable regardless of changes in the magnetic field around it. The ecoSUB designers have made full use of the sophisticated filtering capabilities built into the MTi-3 sensor: the sensor can be configured for operation in various types of operating environments, including for continuous strong magnetic interference. This is ideal for the ecoSUB, in which the propellers are coupled to the motor magnetically.All functionality is squeezed into a compact package which measures just 12.1 x 12.1 x 2.55mm and weighs less than 1g. Typical power consumption is less than 100mW, helping the ecoSUB’s battery to last longer and extend the vehicle’s range.Opening up the use of AUVs to whole new market segmentsAfter completing sea trials, the innovative ecoSUB AUV went into full commercial production in 2020. Jeremy Sitbon says that Planet Ocean is excited about the possibility of introducing a new generation of users to the utility of AUVs. The ecoSUB’s capabilities include acoustic (sonar) communication, enabling multiple ecoSUB AUVs to be used concurrently in ‘shoals’ to give a 3D picture of subsea conditions. The ecoSUB can act like a marine ‘truck’ – a carrier for almost any type of sensor or other payload, so the potential for its use is almost limitless.<blockquote>‘The success of the product comes down to our ability to pack a lot of functionality and performance into a very small space. Our decision to use the MTi-3 played a really important part in our ability to make this design successful. I’m very happy that we made the right choice!’</blockquote>Jeremy Sitbon, ecoSUB Chief Robotics Engineer&nbsp;Learn more about the <a href="https://www.xsens.com/mti-3" rel="noopener" target="_blank">Xsens MTi-3 AHRS</a>&nbsp;here.Choosing your productWant to know the right inertial measurement unit for your application? Try our recommendation tool and find out what MTi you need by answering just 3 questions.<a href="https://www.xsens.com/cs/c/?cta_guid=e67ae0db-e496-4b1b-aaae-0f33c66a97bb&signature=AAH58kERCATymf5UB4b7WHUo8PJHsSLMlQ&pageId=42748316968&placement_guid=0e0cf390-8244-48ac-aa9c-cc22448b3988&click=38fa5093-baba-426c-92e2-244e329bd831&hsutk=26cd9f0233255f079c3a3909dd662892&canon=https%3A%2F%2Fwww.xsens.com%2Fcases%2Fsmall-light-and-accurate-xsens-mti-3-sensor-helps-planet-ocean-open-up-new-markets-for-autonomous-underwater-vehicles&utm_referrer=https%3A%2F%2Fwww.xsens.com%2Fexplore%3Ffilter%3Dcases&portal_id=3446270&redirect_url=APefjpHFi12gvYuHqoWSZfHrIGqiyim6_ONHhAlUSf5P2fSu9LX3yPDWqIEBNMTq7zPbzoK-WfoIZg8Bfa15xkMpbz1GkbkzFFTzUwGCgcPUASxo3Mq8GkOyNHKblRAbv48KApkSyYPNJwvTLiTVMI_w5QhewNpuAjHGGtTfSn2xG8nR_UcoJBph_ito-8xtKFpTW9QoAoROG3GmG8mI-y8TDzizVxJguxXZRuSkE0Jr3QNx52alDInkfDxEm_QGTqfCxOEdsmfaCQUt-NiFKNTC_MtmiftGKw&__hstc=81749512.26cd9f0233255f079c3a3909dd662892.1612181589013.1619708666522.1619773674521.185&__hssc=81749512.8.1619773674521&__hsfp=1627031933&contentType=blog-post" target="_blank" title="Recommendation tool">Recommendation tool</a>&nbsp;

with Xsens MTi

Xsens AHRS Enables Planet Ocean To Open Up New Markets For Autonomous Underwater Vehicles

Engineers at Duke University have developed an electronics-free, entirely soft robot shaped like a dragonfly that can skim across water and react to environmental conditions such as pH, temperature or the presence of oil. The proof-of-principle demonstration could be the precursor to more advanced, autonomous, long-range environmental sentinels for monitoring a wide range of potential telltale signs of problems.The soft robot is described online March 25 in the journal Advanced Intelligent Systems.Soft robots are a growing trend in the industry due to their versatility. Soft parts can handle delicate objects such as biological tissues that metal or ceramic components would damage. Soft bodies can help robots float or squeeze into tight spaces where rigid frames would get stuck.The expanding field was on the mind of <a href="https://bme.duke.edu/faculty/shyni-varghese" target="_blank">Shyni Varghese</a>, professor of biomedical engineering, mechanical engineering and materials science, and orthopaedic surgery at Duke, when inspiration struck.“I got an email from Shyni from the airport saying she had an idea for a soft robot that uses a self-healing hydrogel that her group has invented in the past to react and move autonomously,” said Vardhman Kumar, a PhD student in Varghese’s laboratory and first author of the paper. “But that was the extent of the email, and I didn’t hear from her again for days. So the idea sort of sat in limbo for a little while until I had enough free time to pursue it, and Shyni said to go for it.”In 2012, Varghese and her laboratory created a self-healing hydrogel that reacts to changes in pH in a matter of seconds. Whether it be a crack in the hydrogel or two adjoining pieces “painted” with it, a change in acidity causes the hydrogel to form new bonds, which are completely reversible when the pH returns to its original levels.Varghese’s hastily written idea was to find a way to use this hydrogel on a soft robot that could travel across water and indicate places where the pH changes. Along with a few other innovations to signal changes in its surroundings, she figured her lab could design such a robot as a sort of autonomous environmental sensor.With the help of Ung Hyun Ko, a postdoctoral fellow also in Varghese’s laboratory, Kumar began designing a soft robot based on a fly. After several iterations, the pair settled on the shape of a dragonfly engineered with a network of interior microchannels that allow it to be controlled with air pressure.They created the body—about 2.25 inches long with a 1.4-inch wingspan—by pouring silicon into an aluminum mold and baking it. The team used soft lithography to create interior channels and connected with flexible silicon tubing.DraBot was born.<iframe src="https://www.youtube.com/embed/bTjZQMvagJ8?&amp;wmode=opaque&amp;rel=0" frameborder="0" allowfullscreen="" class="fr-draggable" style="width: 787px; height: 427px;"></iframe><main><section>“Getting DraBot to respond to air pressure controls over long distances using only self-actuators without any electronics was difficult,” said Ko. “That was definitely the most challenging part.”DraBot works by controlling the air pressure coming into its wings. Microchannels carry the air into the front wings, where it escapes through a series of holes pointed directly into the back wings. If both back wings are down, the airflow is blocked, and DraBot goes nowhere. But if both wings are up, DraBot goes forward.To add an element of control, the team also designed balloon actuators under each of the back wings close to DraBot’s body. When inflated, the balloons cause the wings to curl upward. By changing which wings are up or down, the researchers tell DraBot where to go.“We were happy when we were able to control DraBot, but it’s based on living things,” said Kumar. “And living things don’t just move around on their own, they react to their environment.”That’s where self-healing hydrogel comes in. By painting one set of wings with the hydrogel, the researchers were able to make DraBot responsive to changes in the surrounding water’s pH. If the water becomes acidic, one side’s front wing fuses with the back wing. Instead of traveling in a straight line as instructed, the imbalance causes the robot to spin in a circle. Once the pH returns to a normal level, the hydrogel “un-heals,” the fused wings separate, and DraBot once again becomes fully responsive to commands.To beef up its environmental awareness, the researchers also leveraged the sponges under the wings and doped the wings with temperature-responsive materials. When DraBot skims over water with oil floating on the surface, the sponges will soak it up and change color to the corresponding color of oil. And when the water becomes overly warm, DraBot’s wings change from red to yellow.The researchers believe these types of measurements could play an important part in an environmental robotic sensor in the future. Responsiveness to pH can detect freshwater acidification, which is a serious environmental problem affecting several geologically-sensitive regions. The ability to soak up oils makes such long-distance skimming robots an ideal candidate for early detection of oil spills. Changing colors due to temperatures could help spot signs of red tide and the bleaching of coral reefs, which leads to decline in the population of aquatic life.The team also sees many ways that they could improve on their proof-of-concept. Wireless cameras or solid-state sensors could enhance the capabilities of DraBot. And creating a form of onboard propellant would help similar bots break free of their tubing.“Instead of using air pressure to control the wings, I could envision using some sort of synthetic biology that generates energy,” said Varghese. “That’s a totally different field than I work in, so we’ll have to have a conversation with some potential collaborators to see what’s possible. But that’s part of the fun of working on an interdisciplinary project like this.”<hr>This work was mostly performed at Shared Materials and Instrumentation facility (SMIF) at Duke University, a core facility supported by the National Science Foundation (ECCS-1542015) as part of the National Nanotechnology Coordinated Infrastructure (NNCI).“Microengineered Materials with Self-healing Features for Soft Robotics.” V. Kumar, U. Ko, Y. Zhou, J. Hoque, G. Arya, and S. Varghese. Adv. Intel. Sys., 2021. DOI: 10.1002/aisy.202100005</section></main>

With the ability to sense changes in pH, temperature and oil, this completely soft robot dubbed 'DraBot' could be the prototype for future environmental sentinels

Electronics-free DraBot uses air pressure, microarchitectures and self-healing hydrogels to watch for changes in pH, temperature and oil

Soft Robotic Dragonfly Signals Environmental Disruptions

This article was discussed in our <a data-saferedirecturl="https://www.google.com/url?q=https://www.wevolver.com/profile/the.next.byte&source=gmail&ust=1640817319915000&usg=AOvVaw2nPRdRwJrXSYYeM9RCFu5x" href="https://www.wevolver.com/profile/the.next.byte" id="isPasted" rel="noopener noreferrer" target="_blank">Next Byte podcast</a>.&nbsp;<iframe height="200px" width="100%" frameborder="no" scrolling="no" seamless="" src="https://player.simplecast.com/6a1f8d34-3956-4645-9eb4-918c526c5f45?dark=false" class="fr-draggable"></iframe>The full article will continue below.<hr>Scientists from the<a href="https://distap.mit.edu/" target="_blank">&nbsp;</a><a href="https://distap.mit.edu/" target="_blank">Disruptive and Sustainable Technologies for Agricultural Precision (DiSTAP)</a> research group at the<a href="https://smart.mit.edu/" target="_blank">&nbsp;</a><a href="https://smart.mit.edu/" target="_blank">Singapore-MIT Alliance for Research and Technology (SMART)</a>, MIT’s research enterprise in Singapore, have engineered a novel type of plant nanobionic optical sensor that can detect and monitor, in real time, levels of the highly toxic heavy metal arsenic in the underground environment. This development provides significant advantages over conventional methods used to measure arsenic in the environment and will be important for both environmental monitoring and agricultural applications to safeguard food safety, as arsenic is a contaminant in many common agricultural products such as rice, vegetables, and tea leaves.This new approach is described in a paper titled <a href="https://onlinelibrary.wiley.com/doi/10.1002/adma.202005683" target="_blank">“Plant Nanobionic Sensors for Arsenic Detection,”</a> published recently in Advanced Materials. The paper was led by Tedrick Thomas Salim Lew, a recent graduate student of MIT, and co-authored by Michael Strano, co-lead principal investigator of DiSTAP and the Carbon P. Dubbs Professor at MIT, as well as Minkyung Park and Jianqiao Cui, both graduate students at MIT.Arsenic and its compounds are a serious threat to humans and ecosystems. Long-term exposure to arsenic in humans can cause a wide range of <a href="https://www.who.int/news-room/fact-sheets/detail/arsenic#:~:text=In%20addition%20to%20skin%20cancer,water%20is%20carcinogenic%20to%20humans." target="_blank">detrimental health effects</a>, including<a href="https://www.who.int/news-room/fact-sheets/detail/arsenic#:~:text=In%20addition%20to%20skin%20cancer,water%20is%20carcinogenic%20to%20humans." target="_blank">&nbsp;</a>cardiovascular disease such as heart attack, diabetes, birth defects, severe skin lesions, and numerous cancers including those of the skin, bladder, and lung. Elevated levels of soil arsenic as a result of anthropogenic activities such as mining and smelting are also harmful to plants, inhibiting growth and resulting in substantial crop losses.Food crops can absorb arsenic from the soil, leading to contamination of food and produce consumed by humans. Arsenic in underground environments can also contaminate groundwater and other underground water sources, the long-term consumption of which can cause severe health issues. As such, developing accurate, effective, and easy-to-deploy arsenic sensors is important to protect both the agriculture industry and wider environmental safety.The novel optical nanosensors exhibit changes in their fluorescence intensity upon detecting arsenic. Embedded in plant tissues, with no detrimental effects on the plant, these sensors provide a nondestructive way to monitor the internal dynamics of arsenic taken up by plants from the soil. This integration of optical nanosensors within living plants enables the conversion of plants into self-powered detectors of arsenic from their natural environment, marking a significant upgrade from the time- and equipment-intensive arsenic sampling methods of current conventional methods.“Our plant-based nanosensor is notable not only for being the first of its kind, but also for the significant advantages it confers over conventional methods of measuring arsenic levels in the below-ground environment, requiring less time, equipment, and manpower," says Lew. "We envision that this innovation will eventually see wide use in the agriculture industry and beyond. I am grateful to SMART DiSTAP and the Temasek Life Sciences Laboratory (TLL), both of which were instrumental in idea generation and scientific discussion as well as research funding for this work.”Besides detecting arsenic in rice and spinach, the team also used a species of fern, Pteris cretica, which can hyperaccumulate arsenic. This fern species can absorb and tolerate high levels of arsenic with no detrimental effect — engineering an ultrasensitive plant-based arsenic detector, capable of detecting very low concentrations of arsenic, as low as 0.2 parts per billion. In contrast, the regulatory limit for arsenic detectors is 10 parts per billion. Notably, the novel nanosensors can also be integrated into other species of plants. The researchers say this is the first successful demonstration of living plant-based sensors for arsenic and represents a groundbreaking advancement that could prove highly useful in both agricultural research (e.g., to monitor arsenic taken up by edible crops for food safety) and general environmental monitoring.Previously, conventional methods of measuring arsenic levels included regular field sampling, plant tissue digestion, extraction, and analysis using mass spectrometry. These methods are time-consuming, require extensive sample treatment, and often involve the use of bulky and expensive instrumentation. The new approach couples nanoparticle sensors with plants' natural ability to efficiently extract analytes via the roots and transport them. This allows for the detection of arsenic uptake in living plants in real time, with portable, inexpensive electronics such as a portable Raspberry Pi platform equipped with a charge-coupled device camera akin to a smartphone camera.Co-author, DiSTAP co-lead principal investigator, and MIT Professor Michael Strano adds, “This is a hugely exciting development, as, for the first time, we have developed a nanobionic sensor that can detect arsenic — a serious environmental contaminant and potential public health threat. With its myriad advantages over older methods of arsenic detection, this novel sensor could be a game-changer, as it is not only more time-efficient, but also more accurate and easier to deploy than older methods. It will also help plant scientists in organizations such as TLL to further produce crops that resist uptake of toxic elements. Inspired by TLL’s recent efforts to create rice crops which take up less arsenic, this work is a parallel effort to further support SMART DiSTAP's efforts in food security research, constantly innovating and developing new technological capabilities to improve Singapore’s food quality and safety.”The research is carried out by SMART and supported by the National Research Foundation (NRF) Singapore under its Campus for Research Excellence And Technological Enterprise (CREATE) program.Led by MIT's Strano and Singapore co-lead principal investigator Professor Chua Nam Hai, DiSTAP is one of the five Interdisciplinary Research Groups (IRGs) in SMART. The DiSTAP program addresses deep problems in food production in Singapore and the world by developing a suite of impactful and novel analytical genetic and biosynthetic technologies. The goal is to fundamentally change how plant biosynthetic pathways are discovered, monitored, engineered, and ultimately translated to meet the global demand for food and nutrients. Scientists from MIT, TTL, Nanyang Technological University, and National University of Singapore are collaboratively developing new tools for the continuous measurement of important plant metabolites and hormones for novel discovery, deeper understanding and control of plant biosynthetic pathways in ways not yet possible, especially in the context of green leafy vegetables; leveraging these new techniques to engineer plants with highly desirable properties for global food security, including high yield density production, drought and pathogen resistance and biosynthesis of high-value commercial products; developing tools for producing hydrophobic food components in industry-relevant microbes; developing novel microbial and enzymatic technologies to produce volatile organic compounds that can protect and/or promote growth of leafy vegetables; and applying these technologies to improve urban farming.<hr>SMART was founded by MIT in partnership with the NRF in 2007 and is the first entity in CREATE. SMART serves as an intellectual and innovation hub for cutting-edge research between MIT and Singapore, and currently comprises an Innovation Center and five IRGs: Antimicrobial Resistance, Critical Analytics for Manufacturing Personalized-Medicine, DiSTAP, Future Urban Mobility, and Low Energy Electronic Systems.

A novel type of plant nanobionic optical sensor can detect and monitor, in real-time, levels of arsenic in the underground environment. Credits:Image courtesy of Singapore-MIT Alliance for Research and Technology; Christine Daniloff, MIT

Nanoscale devices integrated into the leaves of living plants can detect the toxic heavy metal in real time.

SMART researchers engineer a plant-based sensor to monitor arsenic levels in soil

Exciting innovations in environmental conservation-related technology comes to rescue for some of the deforesting, equivalent of 27 soccer pitches every minute, going on in the world.Forests are essential to global biodiversity. They provide food and habitats for wildlife and indigenous populations and help reduce the impact of climate change. But across the world, forests are at risk of decimation by combining human-driven and natural threats.Innovative wireless conservation technologies are emerging to combat this concerning trend and encourage greater action against deforestation.<h2>The threat to the world's forests</h2>Increasing global demands for food, materials, and energy cause widespread deforestation and forest degradation. As the number of trees on our planet dwindles, potentially irreversible harm is done to terrestrial biodiversity. How precarious is this reality? In a landmark report, the Intergovernmental Science-Policy Platform on Biodiversity and Ecosystem Services (IPBES) published these figures: Approximately 2.9 million km2 of native forest cover was lost from 1990 to 2015 due to clearing and wood harvesting. Intact forests suffered a seven percent reduction from 2000 to 2013 in developed and developing countries.Today, things are not getting any better; the World Wildlife Fund (WWF) claims, on average, the world loses 75,700 km2 of forests annually — that's the equivalent of 27 soccer pitches every minute.Protected land zones represent a vital weapon in the global fight against deforestation. However, successfully enforcing borders, regulations, and restrictions is much easier said than done. Local authorities and conservationists everywhere need more support to identify and restrict human-driven threats to forests. Typically, illegal logging activity and natural events such as wildfires might otherwise go unchecked. Ultimately, meaningful change relies on closely monitoring the activities occurring within a tropical rainforest's designated protected areas.<h2>Wireless to the rescue</h2>Protected status alone cannot save forests across the globe. Thankfully, exciting innovations in environmental conservation-related technology have joined the battle. Utilizing short- and long-range wireless networks, sensor-based devices, like remote monitoring systems connected to Cloud platforms and smartphone apps, are at authorities' hands. Thus, they can constantly listen to all the sounds made in a forest, even if they're kilometers or continents away.<a href="https://www.codeofconscience.org/" rel="noopener" target="_blank">Code of Conscience</a> is a leading initiative supporting efforts to limit illegal deforestation. Launched in September 2019, the initiative aims to track the type of heavy-duty vehicles often used to rip through the forest in both legal and banned logging operations.Code of Conscience's solution autonomously restricts crews from entering protected zones (as determined by the UN World Database on Protected Areas). The open-source software uses publicly available mapping data with existing GPS tracking technology installed in construction vehicles. The GPS-based "geofence" capabilities interlock with the forest-clearing machinery's fuel pumps, enabling automatic shutdown if the equipment moves into a restricted area.Integrated cellular connectivity enables notifications and audits of the machinery's position during regular operation and provides a method for over-the-air map data updates. A small, low-cost chip has also been developed to equip older, non-GPS vehicle models with the same capability.<h2>Listening out for deforestation</h2>Code of Conscience has been piloted in the Amazon. Using Nordic Semiconductor's&nbsp;<a href="https://www.nordicsemi.com/Software-and-tools/Prototyping-platforms/Nordic-Thingy-91?utm_campaign=2021%20wevolver" rel="noopener noreferrer" target="_blank">Nordic Thingy:91</a> multi-sensor cellular IoT prototyping platform, they demonstrate forestry and agricultural vehicles tracking on land and water. The Nordic Thingy:91 offers cellular connectivity 'out-of-the-box.' OEM partners can easily integrate the technology into their machinery for future applications and remote installations.Another solution can highlight the dangers of deforestation to local communities by detecting loud sounds in forests. The unique device was developed by the young winner of the not-for-profit&nbsp;<a href="https://microbit.org/" rel="noopener" target="_blank">Micro:bit Educational Foundation</a>'s "do your:bit" BBC micro:bit challenge (North America), inspired by the UN Global Goals initiative.The system includes a Raspberry Pi computer with a connected camera and a microphone that communicates with the Micro:bit (a Nordic SoC-based pocket computer). It wirelessly relays an audio signal then automatically takes a photo and posts it to a public Twitter account. A local park ranger can then review the picture to determine the noise source and respond accordingly — whether it's the crack of lighting or something more sinister, for example, the buzz of a chainsaw.<h2>Light at the end of the canopy</h2>Could solutions providing remote access to actionable information and real-time alerts help individuals, organizations, and communities in their quest to save the forests and, in turn, the planet? With support from robust wireless networks, and if the world is willing to get on board, there certainly appears to be light at the end of the canopy.&nbsp;<hr>This article was first published on Nordic's&nbsp;<a href="https://blog.nordicsemi.com/getconnected" rel="nofollow" target="_blank"></a><a href="https://blog.nordicsemi.com/getconnected?utm_campaign=2021%20wevolver" rel="noopener noreferrer" target="_blank">Get Connected Blog</a>.

Exciting innovations in environmental conservation related technology comes to rescue for some of the deforesting, equivalent of 27 soccer pitches every minute, going on in the world.

Saving the forests with wireless tech

New results from NASA's Juno mission at <a href="https://www.nasa.gov/jupiter" target="_blank">Jupiter</a> suggest our solar system's largest planet is home to what's called "shallow lightning." An unexpected form of electrical discharge, shallow lightning originates from clouds containing an ammonia-water solution, whereas lightning on Earth originates from water clouds.Other new findings suggest the violent thunderstorms for which the gas giant is known may form slushy ammonia-rich hailstones Juno's science team calls "mushballs"; they theorize that mushballs essentially kidnap ammonia and water in the upper atmosphere and carry them into the depths of Jupiter's atmosphere.The shallow-lightning findings will be published Thursday, Aug. 6, in the journal Nature, while the mushballs research is currently available online in the Journal of Geophysical Research: Planets.Since NASA's Voyager mission first saw Jovian lightning flashes in 1979, it has been thought that the planet's lightning is similar to Earth's, occurring only in thunderstorms where water exists in all its phases - ice, liquid, and gas. At Jupiter this would place the storms around 28 to 40 miles (45 to 65 kilometers) below the visible clouds, with temperatures that hover around 32 degrees Fahrenheit (0 degrees Celsius, the temperature at which water freezes). Voyager, and all other missions to the gas giant prior to Juno, saw lightning as bright spots on Jupiter's cloud tops, suggesting that the flashes originated in deep water clouds. But lightning flashes observed on Jupiter's dark side by Juno's Stellar Reference Unit tell a different story."Juno's close flybys of the cloud tops allowed us to see something surprising - smaller, shallower flashes - originating at much higher altitudes in Jupiter's atmosphere than previously assumed possible," said Heidi Becker, Juno's Radiation Monitoring Investigation lead at NASA's Jet Propulsion Laboratory in Southern California and the lead author of the Nature paper.Becker and her team suggest that Jupiter's powerful thunderstorms fling water-ice crystals high up into the planet's atmosphere, over 16 miles (25 kilometers) above Jupiter's water clouds, where they encounter atmospheric ammonia vapor that melts the ice, forming a new ammonia-water solution. At such lofty altitude, temperatures are below minus 126 degrees Fahrenheit (minus 88 degrees Celsius) - too cold for pure liquid water to exist.<iframe src="https://www.youtube.com/embed/tq_6DClZ0Ns?&amp;wmode=opaque" frameborder="0" allowfullscreen="" class="fr-draggable" style="width: 788px; height: 445px;"></iframe>This animation takes the viewer on a simulated journey into Jupiter's exotic high-altitude electrical storms. Get an up-close view of Mission Juno's newly discovered "shallow lighting" flashes and dive into the violent atmospheric jet of the Nautilus cloud. Credit: NASA/JPL-Caltech/SwRI/MSSS/Kevin M. Gill&nbsp;"At these altitudes, the ammonia acts like an antifreeze, lowering the melting point of water ice and allowing the formation of a cloud with ammonia-water liquid," said Becker. "In this new state, falling droplets of ammonia-water liquid can collide with the upgoing water-ice crystals and electrify the clouds. This was a big surprise, as ammonia-water clouds do not exist on Earth."The shallow lightning factors into another puzzle about the inner workings of Jupiter's atmosphere: Juno's Microwave Radiometer instrument discovered that ammonia was depleted - which is to say, missing - from most of Jupiter's atmosphere. Even more puzzling was that the amount of ammonia changes as one moves within Jupiter's atmosphere."Previously, scientists realized there were small pockets of missing ammonia, but no one realized how deep these pockets went or that they covered most of Jupiter,"said Scott Bolton, Juno's principal investigator at the Southwest Research Institute in San Antonio. "We were struggling to explain the ammonia depletion with ammonia-water rain alone, but the rain couldn't go deep enough to match the observations. I realized a solid, like a hailstone, might go deeper and take up more ammonia. When Heidi discovered shallow lightning, we realized we had evidence that ammonia mixes with water high in the atmosphere, and thus the lightning was a key piece of the puzzle."<img src="https://s3-us-west-1.amazonaws.com/wevolver-project-images/froala%2F1597129735080-PIA24042-640.jpg">This graphic depicts the evolutionary process of "shallow lightning" and "mushballs" on Jupiter. Image Credit: NASA/JPL-Caltech/SwRI/CNRS&nbsp;<h2>Jovian Mushballs</h2>A second paper, released yesterday in the Journal of Geophysical Research: Planets,envisions the strange brew of 2/3 water and 1/3 ammonia gas that becomes the seed for Jovian hailstones, known as mushballs. Consisting of layers of water-ammonia slush and ice covered by a thicker water-ice crust, mushballs are generated in a similar manner as hail is on Earth - by growing larger as they move up and down through the atmosphere."Eventually, the mushballs get so big, even the updrafts can't hold them, and they fall deeper into the atmosphere, encountering even warmer temperatures, where they eventually evaporate completely," said Tristan Guillot, a Juno co-investigator from the Université Côte d'Azur in Nice, France, and lead author of the second paper. "Their action drags ammonia and water down to deep levels in the planet's atmosphere. That explains why we don't see much of it in these places with Juno's Microwave Radiometer.""Combining these two results was critical to solving the mystery of Jupiter's missing ammonia," said Bolton. "As it turned out, the ammonia isn't actually missing; it is just transported down while in disguise, having cloaked itself by mixing with water. The solution is very simple and elegant with this theory: When the water and ammonia are in a liquid state, they are invisible to us until they reach a depth where they evaporate - and that is quite deep."Understanding the meteorology of Jupiter enables us to develop theories of atmospheric dynamics for all the planets in our solar system as well as for the exoplanets being discovered outside our solar system. Comparing how violent storms and atmospheric physics work across the solar system allows planetary scientists to test theories under different conditions.<h2>More About the Mission</h2>The solar-powered Jupiter explorer launched&nbsp;<a href="https://www.jpl.nasa.gov/news/news.php?feature=3095" target="_blank">nine years ago today, on Aug. 5, 2011</a>. And last month marked the&nbsp;<a href="https://www.jpl.nasa.gov/news/news.php?feature=6558" target="_blank">fourth anniversary of its arrival at Jupiter</a>. Since entering the gas giant's orbit, Juno has performed 27 science flybys and logged over 300 million miles (483 million kilometers).JPL, a division of Caltech in Pasadena, California, manages the Juno mission for the principal investigator, Scott Bolton, of the Southwest Research Institute in San Antonio. Juno is part of NASA's New Frontiers Program, which is managed at NASA's Marshall Space Flight Center in Huntsville, Alabama, for the agency's Science Mission Directorate in Washington. Lockheed Martin Space in Denver built and operates the spacecraft.

This illustration uses data obtained by NASA's Juno mission to depict high-altitude electrical storms on Jupiter. Juno's sensitive Stellar Reference Unit camera detected unusual lightning flashes on Jupiter's dark side during the spacecraft's close flybys of the planet. Image Credit: NASA/JPL-Caltech/SwRI/MSSS/Gerald Eichstädt

environmental monitoring

Latest Posts