Algorithms

Subterms

    More stories

    • 125 Shares159 Views

      in Energy

      Machine learning, harnessed to extreme computing, aids fusion energy development

      by

      MIT research scientists Pablo Rodriguez-Fernandez and Nathan Howard have just completed one of the most demanding calculations in fusion science — predicting the temperature and density profiles of a magnetically confined plasma via first-principles simulation of plasma turbulence. Solving this problem by brute force is beyond the capabilities of even the most advanced supercomputers. Instead, the researchers used an optimization methodology developed for machine learning to dramatically reduce the CPU time required while maintaining the accuracy of the solution.

      Fusion energyFusion offers the promise of unlimited, carbon-free energy through the same physical process that powers the sun and the stars. It requires heating the fuel to temperatures above 100 million degrees, well above the point where the electrons are stripped from their atoms, creating a form of matter called plasma. On Earth, researchers use strong magnetic fields to isolate and insulate the hot plasma from ordinary matter. The stronger the magnetic field, the better the quality of the insulation that it provides.

      Rodriguez-Fernandez and Howard have focused on predicting the performance expected in the SPARC device, a compact, high-magnetic-field fusion experiment, currently under construction by the MIT spin-out company Commonwealth Fusion Systems (CFS) and researchers from MIT’s Plasma Science and Fusion Center. While the calculation required an extraordinary amount of computer time, over 8 million CPU-hours, what was remarkable was not how much time was used, but how little, given the daunting computational challenge.

      The computational challenge of fusion energyTurbulence, which is the mechanism for most of the heat loss in a confined plasma, is one of the science’s grand challenges and the greatest problem remaining in classical physics. The equations that govern fusion plasmas are well known, but analytic solutions are not possible in the regimes of interest, where nonlinearities are important and solutions encompass an enormous range of spatial and temporal scales. Scientists resort to solving the equations by numerical simulation on computers. It is no accident that fusion researchers have been pioneers in computational physics for the last 50 years.

      One of the fundamental problems for researchers is reliably predicting plasma temperature and density given only the magnetic field configuration and the externally applied input power. In confinement devices like SPARC, the external power and the heat input from the fusion process are lost through turbulence in the plasma. The turbulence itself is driven by the difference in the extremely high temperature of the plasma core and the relatively cool temperatures of the plasma edge (merely a few million degrees). Predicting the performance of a self-heated fusion plasma therefore requires a calculation of the power balance between the fusion power input and the losses due to turbulence.

      These calculations generally start by assuming plasma temperature and density profiles at a particular location, then computing the heat transported locally by turbulence. However, a useful prediction requires a self-consistent calculation of the profiles across the entire plasma, which includes both the heat input and turbulent losses. Directly solving this problem is beyond the capabilities of any existing computer, so researchers have developed an approach that stitches the profiles together from a series of demanding but tractable local calculations. This method works, but since the heat and particle fluxes depend on multiple parameters, the calculations can be very slow to converge.

      However, techniques emerging from the field of machine learning are well suited to optimize just such a calculation. Starting with a set of computationally intensive local calculations run with the full-physics, first-principles CGYRO code (provided by a team from General Atomics led by Jeff Candy) Rodriguez-Fernandez and Howard fit a surrogate mathematical model, which was used to explore and optimize a search within the parameter space. The results of the optimization were compared to the exact calculations at each optimum point, and the system was iterated to a desired level of accuracy. The researchers estimate that the technique reduced the number of runs of the CGYRO code by a factor of four.

      New approach increases confidence in predictionsThis work, described in a recent publication in the journal Nuclear Fusion, is the highest fidelity calculation ever made of the core of a fusion plasma. It refines and confirms predictions made with less demanding models. Professor Jonathan Citrin, of the Eindhoven University of Technology and leader of the fusion modeling group for DIFFER, the Dutch Institute for Fundamental Energy Research, commented: “The work significantly accelerates our capabilities in more routinely performing ultra-high-fidelity tokamak scenario prediction. This algorithm can help provide the ultimate validation test of machine design or scenario optimization carried out with faster, more reduced modeling, greatly increasing our confidence in the outcomes.” 

      In addition to increasing confidence in the fusion performance of the SPARC experiment, this technique provides a roadmap to check and calibrate reduced physics models, which run with a small fraction of the computational power. Such models, cross-checked against the results generated from turbulence simulations, will provide a reliable prediction before each SPARC discharge, helping to guide experimental campaigns and improving the scientific exploitation of the device. It can also be used to tweak and improve even simple data-driven models, which run extremely quickly, allowing researchers to sift through enormous parameter ranges to narrow down possible experiments or possible future machines.

      The research was funded by CFS, with computational support from the National Energy Research Scientific Computing Center, a U.S. Department of Energy Office of Science User Facility. More

    • 125 Shares179 Views

      in Environment

      Improving predictions of sea level rise for the next century

      by

      When we think of climate change, one of the most dramatic images that comes to mind is the loss of glacial ice. As the Earth warms, these enormous rivers of ice become a casualty of the rising temperatures. But, as ice sheets retreat, they also become an important contributor to one the more dangerous outcomes of climate change: sea-level rise. At MIT, an interdisciplinary team of scientists is determined to improve sea level rise predictions for the next century, in part by taking a closer look at the physics of ice sheets.

      Last month, two research proposals on the topic, led by Brent Minchew, the Cecil and Ida Green Career Development Professor in the Department of Earth, Atmospheric and Planetary Sciences (EAPS), were announced as finalists in the MIT Climate Grand Challenges initiative. Launched in July 2020, Climate Grand Challenges fielded almost 100 project proposals from collaborators across the Institute who heeded the bold charge: to develop research and innovations that will deliver game-changing advances in the world’s efforts to address the climate challenge.

      As finalists, Minchew and his collaborators from the departments of Urban Studies and Planning, Economics, Civil and Environmental Engineering, the Haystack Observatory, and external partners, received $100,000 to develop their research plans. A subset of the 27 proposals tapped as finalists will be announced next month, making up a portfolio of multiyear “flagship” projects receiving additional funding and support.

      One goal of both Minchew proposals is to more fully understand the most fundamental processes that govern rapid changes in glacial ice, and to use that understanding to build next-generation models that are more predictive of ice sheet behavior as they respond to, and influence, climate change.

      “We need to develop more accurate and computationally efficient models that provide testable projections of sea-level rise over the coming decades. To do so quickly, we want to make better and more frequent observations and learn the physics of ice sheets from these data,” says Minchew. “For example, how much stress do you have to apply to ice before it breaks?”

      Currently, Minchew’s Glacier Dynamics and Remote Sensing group uses satellites to observe the ice sheets on Greenland and Antarctica primarily with interferometric synthetic aperture radar (InSAR). But the data are often collected over long intervals of time, which only gives them “before and after” snapshots of big events. By taking more frequent measurements on shorter time scales, such as hours or days, they can get a more detailed picture of what is happening in the ice.

      “Many of the key unknowns in our projections of what ice sheets are going to look like in the future, and how they’re going to evolve, involve the dynamics of glaciers, or our understanding of how the flow speed and the resistances to flow are related,” says Minchew.

      At the heart of the two proposals is the creation of SACOS, the Stratospheric Airborne Climate Observatory System. The group envisions developing solar-powered drones that can fly in the stratosphere for months at a time, taking more frequent measurements using a new lightweight, low-power radar and other high-resolution instrumentation. They also propose air-dropping sensors directly onto the ice, equipped with seismometers and GPS trackers to measure high-frequency vibrations in the ice and pinpoint the motions of its flow.

      How glaciers contribute to sea level rise

      Current climate models predict an increase in sea levels over the next century, but by just how much is still unclear. Estimates are anywhere from 20 centimeters to two meters, which is a large difference when it comes to enacting policy or mitigation. Minchew points out that response measures will be different, depending on which end of the scale it falls toward. If it’s closer to 20 centimeters, coastal barriers can be built to protect low-level areas. But with higher surges, such measures become too expensive and inefficient to be viable, as entire portions of cities and millions of people would have to be relocated.

      “If we’re looking at a future where we could get more than a meter of sea level rise by the end of the century, then we need to know about that sooner rather than later so that we can start to plan and to do our best to prepare for that scenario,” he says.

      There are two ways glaciers and ice sheets contribute to rising sea levels: direct melting of the ice and accelerated transport of ice to the oceans. In Antarctica, warming waters melt the margins of the ice sheets, which tends to reduce the resistive stresses and allow ice to flow more quickly to the ocean. This thinning can also cause the ice shelves to be more prone to fracture, facilitating the calving of icebergs — events which sometimes cause even further acceleration of ice flow.

      Using data collected by SACOS, Minchew and his group can better understand what material properties in the ice allow for fracturing and calving of icebergs, and build a more complete picture of how ice sheets respond to climate forces. 

      “What I want is to reduce and quantify the uncertainties in projections of sea level rise out to the year 2100,” he says.

      From that more complete picture, the team — which also includes economists, engineers, and urban planning specialists — can work on developing predictive models and methods to help communities and governments estimate the costs associated with sea level rise, develop sound infrastructure strategies, and spur engineering innovation.

      Understanding glacier dynamics

      More frequent radar measurements and the collection of higher-resolution seismic and GPS data will allow Minchew and the team to develop a better understanding of the broad category of glacier dynamics — including calving, an important process in setting the rate of sea level rise which is currently not well understood.  

      “Some of what we’re doing is quite similar to what seismologists do,” he says. “They measure seismic waves following an earthquake, or a volcanic eruption, or things of this nature and use those observations to better understand the mechanisms that govern these phenomena.”

      Air-droppable sensors will help them collect information about ice sheet movement, but this method comes with drawbacks — like installation and maintenance, which is difficult to do out on a massive ice sheet that is moving and melting. Also, the instruments can each only take measurements at a single location. Minchew equates it to a bobber in water: All it can tell you is how the bobber moves as the waves disturb it.

      But by also taking continuous radar measurements from the air, Minchew’s team can collect observations both in space and in time. Instead of just watching the bobber in the water, they can effectively make a movie of the waves propagating out, as well as visualize processes like iceberg calving happening in multiple dimensions.

      Once the bobbers are in place and the movies recorded, the next step is developing machine learning algorithms to help analyze all the new data being collected. While this data-driven kind of discovery has been a hot topic in other fields, this is the first time it has been applied to glacier research.

      “We’ve developed this new methodology to ingest this huge amount of data,” he says, “and from that create an entirely new way of analyzing the system to answer these fundamental and critically important questions.”  More

    • 75 Shares149 Views

      in Environment

      Using nature’s structures in wooden buildings

      by

      Concern about climate change has focused significant attention on the buildings sector, in particular on the extraction and processing of construction materials. The concrete and steel industries together are responsible for as much as 15 percent of global carbon dioxide emissions. In contrast, wood provides a natural form of carbon sequestration, so there’s a move to use timber instead. Indeed, some countries are calling for public buildings to be made at least partly from timber, and large-scale timber buildings have been appearing around the world.

      Observing those trends, Caitlin Mueller ’07, SM ’14, PhD ’14, an associate professor of architecture and of civil and environmental engineering in the Building Technology Program at MIT, sees an opportunity for further sustainability gains. As the timber industry seeks to produce wooden replacements for traditional concrete and steel elements, the focus is on harvesting the straight sections of trees. Irregular sections such as knots and forks are turned into pellets and burned, or ground up to make garden mulch, which will decompose within a few years; both approaches release the carbon trapped in the wood to the atmosphere.

      For the past four years, Mueller and her Digital Structures research group have been developing a strategy for “upcycling” those waste materials by using them in construction — not as cladding or finishes aimed at improving appearance, but as structural components. “The greatest value you can give to a material is to give it a load-bearing role in a structure,” she says. But when builders use virgin materials, those structural components are the most emissions-intensive parts of buildings due to their large volume of high-strength materials. Using upcycled materials in place of those high-carbon systems is therefore especially impactful in reducing emissions.

      Mueller and her team focus on tree forks — that is, spots where the trunk or branch of a tree divides in two, forming a Y-shaped piece. In architectural drawings, there are many similar Y-shaped nodes where straight elements come together. In such cases, those units must be strong enough to support critical loads.

      “Tree forks are naturally engineered structural connections that work as cantilevers in trees, which means that they have the potential to transfer force very efficiently thanks to their internal fiber structure,” says Mueller. “If you take a tree fork and slice it down the middle, you see an unbelievable network of fibers that are intertwining to create these often three-dimensional load transfer points in a tree. We’re starting to do the same thing using 3D printing, but we’re nowhere near what nature does in terms of complex fiber orientation and geometry.”

      She and her team have developed a five-step “design-to-fabrication workflow” that combines natural structures such as tree forks with the digital and computational tools now used in architectural design. While there’s long been a “craft” movement to use natural wood in railings and decorative features, the use of computational tools makes it possible to use wood in structural roles — without excessive cutting, which is costly and may compromise the natural geometry and internal grain structure of the wood.

      Given the wide use of digital tools by today’s architects, Mueller believes that her approach is “at least potentially scalable and potentially achievable within our industrialized materials processing systems.” In addition, by combining tree forks with digital design tools, the novel approach can also support the trend among architects to explore new forms. “Many iconic buildings built in the past two decades have unexpected shapes,” says Mueller. “Tree branches have a very specific geometry that sometimes lends itself to an irregular or nonstandard architectural form — driven not by some arbitrary algorithm but by the material itself.”

      Step 0: Find a source, set goals

      Before starting their design-to-fabrication process, the researchers needed to locate a source of tree forks. Mueller found help in the Urban Forestry Division of the City of Somerville, Massachusetts, which maintains a digital inventory of more than 2,000 street trees — including more than 20 species — and records information about the location, approximate trunk diameter, and condition of each tree.

      With permission from the forestry division, the team was on hand in 2018 when a large group of trees was cut down near the site of the new Somerville High School. Among the heavy equipment on site was a chipper, poised to turn all the waste wood into mulch. Instead, the workers obligingly put the waste wood into the researchers’ truck to be brought to MIT.

      In their project, the MIT team sought not only to upcycle that waste material but also to use it to create a structure that would be valued by the public. “Where I live, the city has had to take down a lot of trees due to damage from an invasive species of beetle,” Mueller explains. “People get really upset — understandably. Trees are an important part of the urban fabric, providing shade and beauty.” She and her team hoped to reduce that animosity by “reinstalling the removed trees in the form of a new functional structure that would recreate the atmosphere and spatial experience previously provided by the felled trees.”

      With their source and goals identified, the researchers were ready to demonstrate the five steps in their design-to-fabrication workflow for making spatial structures using an inventory of tree forks.

      Step 1: Create a digital material library

      The first task was to turn their collection of tree forks into a digital library. They began by cutting off excess material to produce isolated tree forks. They then created a 3D scan of each fork. Mueller notes that as a result of recent progress in photogrammetry (measuring objects using photographs) and 3D scanning, they could create high-resolution digital representations of the individual tree forks with relatively inexpensive equipment, even using apps that run on a typical smartphone.

      In the digital library, each fork is represented by a “skeletonized” version showing three straight bars coming together at a point. The relative geometry and orientation of the branches are of particular interest because they determine the internal fiber orientation that gives the component its strength.

      Step 2: Find the best match between the initial design and the material library

      Like a tree, a typical architectural design is filled with Y-shaped nodes where three straight elements meet up to support a critical load. The goal was therefore to match the tree forks in the material library with the nodes in a sample architectural design.

      First, the researchers developed a “mismatch metric” for quantifying how well the geometries of a particular tree fork aligned with a given design node. “We’re trying to line up the straight elements in the structure with where the branches originally were in the tree,” explains Mueller. “That gives us the optimal orientation for load transfer and maximizes use of the inherent strength of the wood fiber.” The poorer the alignment, the higher the mismatch metric.

      The goal was to get the best overall distribution of all the tree forks among the nodes in the target design. Therefore, the researchers needed to try different fork-to-node distributions and, for each distribution, add up the individual fork-to-node mismatch errors to generate an overall, or global, matching score. The distribution with the best matching score would produce the most structurally efficient use of the total tree fork inventory.

      Since performing that process manually would take far too long to be practical, they turned to the “Hungarian algorithm,” a technique developed in 1955 for solving such problems. “The brilliance of the algorithm is solving that [matching] problem very quickly,” Mueller says. She notes that it’s a very general-use algorithm. “It’s used for things like marriage match-making. It can be used any time you have two collections of things that you’re trying to find unique matches between. So, we definitely didn’t invent the algorithm, but we were the first to identify that it could be used for this problem.”

      The researchers performed repeated tests to show possible distributions of the tree forks in their inventory and found that the matching score improved as the number of forks available in the material library increased — up to a point. In general, the researchers concluded that the mismatch score was lowest, and thus best, when there were about three times as many forks in the material library as there were nodes in the target design.

      Step 3: Balance designer intention with structural performance

      The next step in the process was to incorporate the intention or preference of the designer. To permit that flexibility, each design includes a limited number of critical parameters, such as bar length and bending strain. Using those parameters, the designer can manually change the overall shape, or geometry, of the design or can use an algorithm that automatically changes, or “morphs,” the geometry. And every time the design geometry changes, the Hungarian algorithm recalculates the optimal fork-to-node matching.

      “Because the Hungarian algorithm is extremely fast, all the morphing and the design updating can be really fluid,” notes Mueller. In addition, any change to a new geometry is followed by a structural analysis that checks the deflections, strain energy, and other performance measures of the structure. On occasion, the automatically generated design that yields the best matching score may deviate far from the designer’s initial intention. In such cases, an alternative solution can be found that satisfactorily balances the design intention with a low matching score.

      Step 4: Automatically generate the machine code for fast cutting

      When the structural geometry and distribution of tree forks have been finalized, it’s time to think about actually building the structure. To simplify assembly and maintenance, the researchers prepare the tree forks by recutting their end faces to better match adjoining straight timbers and cutting off any remaining bark to reduce susceptibility to rot and fire.

      To guide that process, they developed a custom algorithm that automatically computes the cuts needed to make a given tree fork fit into its assigned node and to strip off the bark. The goal is to remove as little material as possible but also to avoid a complex, time-consuming machining process. “If we make too few cuts, we’ll cut off too much of the critical structural material. But we don’t want to make a million tiny cuts because it will take forever,” Mueller explains.

      The team uses facilities at the Autodesk Boston Technology Center Build Space, where the robots are far larger than any at MIT and the processing is all automated. To prepare each tree fork, they mount it on a robotic arm that pushes the joint through a traditional band saw in different orientations, guided by computer-generated instructions. The robot also mills all the holes for the structural connections. “That’s helpful because it ensures that everything is aligned the way you expect it to be,” says Mueller.

      Step 5: Assemble the available forks and linear elements to build the structure

      The final step is to assemble the structure. The tree-fork-based joints are all irregular, and combining them with the precut, straight wooden elements could be difficult. However, they’re all labeled. “All the information for the geometry is embedded in the joint, so the assembly process is really low-tech,” says Mueller. “It’s like a child’s toy set. You just follow the instructions on the joints to put all the pieces together.”

      They installed their final structure temporarily on the MIT campus, but Mueller notes that it was only a portion of the structure they plan to eventually build. “It had 12 nodes that we designed and fabricated using our process,” she says, adding that the team’s work was “a little interrupted by the pandemic.” As activity on campus resumes, the researchers plan to finish designing and building the complete structure, which will include about 40 nodes and will be installed as an outdoor pavilion on the site of the felled trees in Somerville.

      In addition, they will continue their research. Plans include working with larger material libraries, some with multibranch forks, and replacing their 3D-scanning technique with computerized tomography scanning technologies that can automatically generate a detailed geometric representation of a tree fork, including its precise fiber orientation and density. And in a parallel project, they’ve been exploring using their process with other sources of materials, with one case study focusing on using material from a demolished wood-framed house to construct more than a dozen geodesic domes.

      To Mueller, the work to date already provides new guidance for the architectural design process. With digital tools, it has become easy for architects to analyze the embodied carbon or future energy use of a design option. “Now we have a new metric of performance: How well am I using available resources?” she says. “With the Hungarian algorithm, we can compute that metric basically in real time, so we can work rapidly and creatively with that as another input to the design process.”

      This research was supported by MIT’s School of Architecture and Planning via the HASS Award.

      This article appears in the Autumn 2021 issue of Energy Futures, the magazine of the MIT Energy Initiative. More

    • 150 Shares99 Views

      in Environment

      New maps show airplane contrails over the U.S. dropped steeply in 2020

      by

      As Covid-19’s initial wave crested around the world, travel restrictions and a drop in passengers led to a record number of grounded flights in 2020. The air travel reduction cleared the skies of not just jets but also the fluffy white contrails they produce high in the atmosphere.

      MIT engineers have mapped the contrails that were generated over the United States in 2020, and compared the results to prepandemic years. They found that on any given day in 2018, and again in 2019, contrails covered a total area equal to Massachusetts and Connecticut combined. In 2020, this contrail coverage shrank by about 20 percent, mirroring a similar drop in U.S. flights.  

      While 2020’s contrail dip may not be surprising, the findings are proof that the team’s mapping technique works. Their study marks the first time researchers have captured the fine and ephemeral details of contrails over a large continental scale.

      Now, the researchers are applying the technique to predict where in the atmosphere contrails are likely to form. The cloud-like formations are known to play a significant role in aviation-related global warming. The team is working with major airlines to forecast regions in the atmosphere where contrails may form, and to reroute planes around these regions to minimize contrail production.

      “This kind of technology can help divert planes to prevent contrails, in real time,” says Steven Barrett, professor and associate head of MIT’s Department of Aeronautics and Astronautics. “There’s an unusual opportunity to halve aviation’s climate impact by eliminating most of the contrails produced today.”

      Barrett and his colleagues have published their results today in the journal Environmental Research Letters. His co-authors at MIT include graduate student Vincent Meijer, former graduate student Luke Kulik, research scientists Sebastian Eastham, Florian Allroggen, and Raymond Speth, and LIDS Director and professor Sertac Karaman.

      Trail training

      About half of the aviation industry’s contribution to global warming comes directly from planes’ carbon dioxide emissions. The other half is thought to be a consequence of their contrails. The signature white tails are produced when a plane’s hot, humid exhaust mixes with cool humid air high in the atmosphere. Emitted in thin lines, contrails quickly spread out and can act as blankets that trap the Earth’s outgoing heat.

      While a single contrail may not have much of a warming effect, taken together contrails have a significant impact. But the estimates of this effect are uncertain and based on computer modeling as well as limited satellite data. What’s more, traditional computer vision algorithms that analyze contrail data have a hard time discerning the wispy tails from natural clouds.

      To precisely pick out and track contrails over a large scale, the MIT team looked to images taken by NASA’s GOES-16, a geostationary satellite that hovers over the same swath of the Earth, including the United States, taking continuous, high-resolution images.

      The team first obtained about 100 images taken by the satellite, and trained a set of people to interpret remote sensing data and label each image’s pixel as either part of a contrail or not. They used this labeled dataset to train a computer-vision algorithm to discern a contrail from a cloud or other image feature.

      The researchers then ran the algorithm on about 100,000 satellite images, amounting to nearly 6 trillion pixels, each pixel representing an area of about 2 square kilometers. The images covered the contiguous U.S., along with parts of Canada and Mexico, and were taken about every 15 minutes, between Jan. 1, 2018, and Dec. 31, 2020.

      The algorithm automatically classified each pixel as either a contrail or not a contrail, and generated daily maps of contrails over the United States. These maps mirrored the major flight paths of most U.S. airlines, with some notable differences. For instance, contrail “holes” appeared around major airports, which reflects the fact that planes landing and taking off around airports are generally not high enough in the atmosphere for contrails to form.

      “The algorithm knows nothing about where planes fly, and yet when processing the satellite imagery, it resulted in recognizable flight routes,” Barrett says. “That’s one piece of evidence that says this method really does capture contrails over a large scale.”

      Cloudy patterns

      Based on the algorithm’s maps, the researchers calculated the total area covered each day by contrails in the US. On an average day in 2018 and in 2019, U.S. contrails took up about 43,000 square kilometers. This coverage dropped by 20 percent in March of 2020 as the pandemic set in. From then on, contrails slowly reappeared as air travel resumed through the year.

      The team also observed daily and seasonal patterns. In general, contrails appeared to peak in the morning and decline in the afternoon. This may be a training artifact: As natural cirrus clouds are more likely to form in the afternoon, the algorithm may have trouble discerning contrails amid the clouds later in the day. But it might also be an important indication about when contrails form most. Contrails also peaked in late winter and early spring, when more of the air is naturally colder and more conducive for contrail formation.

      The team has now adapted the technique to predict where contrails are likely to form in real time. Avoiding these regions, Barrett says, could take a significant, almost immediate chunk out of aviation’s global warming contribution.  

      “Most measures to make aviation sustainable take a long time,” Barrett says. “(Contrail avoidance) could be accomplished in a few years, because it requires small changes to how aircraft are flown, with existing airplanes and observational technology. It’s a near-term way of reducing aviation’s warming by about half.”

      The team is now working towards this objective of large-scale contrail avoidance using realtime satellite observations.

      This research was supported in part by NASA and the MIT Environmental Solutions Initiative. More

    • 100 Shares139 Views

      in Energy

      3 Questions: Anuradha Annaswamy on building smart infrastructures

      by

      Much of Anuradha Annaswamy’s research hinges on uncertainty. How does cloudy weather affect a grid powered by solar energy? How do we ensure that electricity is delivered to the consumer if a grid is powered by wind and the wind does not blow? What’s the best course of action if a bird hits a plane engine on takeoff? How can you predict the behavior of a cyber attacker?

      A senior research scientist in MIT’s Department of Mechanical Engineering, Annaswamy spends most of her research time dealing with decision-making under uncertainty. Designing smart infrastructures that are resilient to uncertainty can lead to safer, more reliable systems, she says.

      Annaswamy serves as the director of MIT’s Active Adaptive Control Laboratory. A world-leading expert in adaptive control theory, she was named president of the Institute of Electrical and Electronics Engineers Control Systems Society for 2020. Her team uses adaptive control and optimization to account for various uncertainties and anomalies in autonomous systems. In particular, they are developing smart infrastructures in the energy and transportation sectors.

      Using a combination of control theory, cognitive science, economic modeling, and cyber-physical systems, Annaswamy and her team have designed intelligent systems that could someday transform the way we travel and consume energy. Their research includes a diverse range of topics such as safer autopilot systems on airplanes, the efficient dispatch of resources in electrical grids, better ride-sharing services, and price-responsive railway systems.

      In a recent interview, Annaswamy spoke about how these smart systems could help support a safer and more sustainable future.

      Q: How is your team using adaptive control to make air travel safer?

      A: We want to develop an advanced autopilot system that can safely recover the airplane in the event of a severe anomaly — such as the wing becoming damaged mid-flight, or a bird flying into the engine. In the airplane, you have a pilot and autopilot to make decisions. We’re asking: How do you combine those two decision-makers?

      The answer we landed on was developing a shared pilot-autopilot control architecture. We collaborated with David Woods, an expert in cognitive engineering at The Ohio State University, to develop an intelligent system that takes the pilot’s behavior into account. For example, all humans have something known as “capacity for maneuver” and “graceful command degradation” that inform how we react in the face of adversity. Using mathematical models of pilot behavior, we proposed a shared control architecture where the pilot and the autopilot work together to make an intelligent decision on how to react in the face of uncertainties. In this system, the pilot reports the anomaly to an adaptive autopilot system that ensures resilient flight control.

      Q: How does your research on adaptive control fit into the concept of smart cities?

      A: Smart cities are an interesting way we can use intelligent systems to promote sustainability. Our team is looking at ride-sharing services in particular. Services like Uber and Lyft have provided new transportation options, but their impact on the carbon footprint has to be considered. We’re looking at developing a system where the number of passenger-miles per unit of energy is maximized through something called “shared mobility on demand services.” Using the alternating minimization approach, we’ve developed an algorithm that can determine the optimal route for multiple passengers traveling to various destinations.

      As with the pilot-autopilot dynamic, human behavior is at play here. In sociology there is an interesting concept of behavioral dynamics known as Prospect Theory. If we give passengers options with regards to which route their shared ride service will take, we are empowering them with free will to accept or reject a route. Prospect Theory shows that if you can use pricing as an incentive, people are much more loss-averse so they would be willing to walk a bit extra or wait a few minutes longer to join a low-cost ride with an optimized route. If everyone utilized a system like this, the carbon footprint of ride-sharing services could decrease substantially.

      Q: What other ways are you using intelligent systems to promote sustainability?

      A: Renewable energy and sustainability are huge drivers for our research. To enable a world where all of our energy is coming from renewable sources like solar or wind, we need to develop a smart grid that can account for the fact that the sun isn’t always shining and wind isn’t always blowing. These uncertainties are the biggest hurdles to achieving an all-renewable grid. Of course, there are many technologies being developed for batteries that can help store renewable energy, but we are taking a different approach.

      We have created algorithms that can optimally schedule distributed energy resources within the grid — this includes making decisions on when to use onsite generators, how to operate storage devices, and when to call upon demand response technologies, all in response to the economics of using such resources and their physical constraints. If we can develop an interconnected smart grid where, for example, the air conditioning setting in a house is set to 72 degrees instead of 69 degrees automatically when demand is high, there could be a substantial savings in energy usage without impacting human comfort. In one of our studies, we applied a distributed proximal atomic coordination algorithm to the grid in Tokyo to demonstrate how this intelligent system could account for the uncertainties present in a grid powered by renewable resources. More

    • 150 Shares169 Views

      in Environment

      SMART researchers develop method for early detection of bacterial infection in crops

      by

      Researchers from the Disruptive and Sustainable Technologies for Agricultural Precision (DiSTAP) Interdisciplinary Research Group (IRG) ofSingapore-MIT Alliance for Research and Technology (SMART), MIT’s research enterprise in Singapore, and their local collaborators from Temasek Life Sciences Laboratory (TLL), have developed a rapid Raman spectroscopy-based method for detecting and quantifying early bacterial infection in crops. The Raman spectral biomarkers and diagnostic algorithm enable the noninvasive and early diagnosis of bacterial infections in crop plants, which can be critical for the progress of plant disease management and agricultural productivity.

      Due to the increasing demand for global food supply and security, there is a growing need to improve agricultural production systems and increase crop productivity. Globally, bacterial pathogen infection in crop plants is one of the major contributors to agricultural yield losses. Climate change also adds to the problem by accelerating the spread of plant diseases. Hence, developing methods for rapid and early detection of pathogen-infected crops is important to improve plant disease management and reduce crop loss.

      The breakthrough by SMART and TLL researchers offers a faster and more accurate method to detect bacterial infection in crop plants at an earlier stage, as compared to existing techniques. The new results appear in a paper titled “Rapid detection and quantification of plant innate immunity response using Raman spectroscopy” published in the journal Frontiers in Plant Science.

      “The early detection of pathogen-infected crop plants is a significant step to improve plant disease management,” says Chua Nam Hai, DiSTAP co-lead principal investigator, professor, TLL deputy chair, and co-corresponding author. “It will allow the fast and selective removal of pathogen load and curb the further spread of disease to other neighboring crops.”

      Traditionally, plant disease diagnosis involves a simple visual inspection of plants for disease symptoms and severity. “Visual inspection methods are often ineffective, as disease symptoms usually manifest only at relatively later stages of infection, when the pathogen load is already high and reparative measures are limited. Hence, new methods are required for rapid and early detection of bacterial infection. The idea would be akin to having medical tests to identify human diseases at an early stage, instead of waiting for visual symptoms to show, so that early intervention or treatment can be applied,” says MIT Professor Rajeev Ram, who is a DiSTAP principal investigator and co-corresponding author on the paper.

      While existing techniques, such as current molecular detection methods, can detect bacterial infection in plants, they are often limited in their use. Molecular detection methods largely depend on the availability of pathogen-specific gene sequences or antibodies to identify bacterial infection in crops; the implementation is also time-consuming and nonadaptable for on-site field application due to the high cost and bulky equipment required, making it impractical for use in agricultural farms.

      “At DiSTAP, we have developed a quantitative Raman spectroscopy-based algorithm that can help farmers to identify bacterial infection rapidly. The developed diagnostic algorithm makes use of Raman spectral biomarkers and can be easily implemented in cloud-based computing and prediction platforms. It is more effective than existing techniques as it enables accurate identification and early detection of bacterial infection, both of which are crucial to saving crop plants that would otherwise be destroyed,” explains Gajendra Pratap Singh, scientific director and principal investigator at DiSTAP and co-lead author.

      A portable Raman system can be used on farms and provides farmers with an accurate and simple yes-or-no response when used to test for the presence of bacterial infections in crops. The development of this rapid and noninvasive method could improve plant disease management and have a transformative impact on agricultural farms by efficiently reducing agricultural yield loss and increasing productivity.

      “Using the diagnostic algorithm method, we experimented on several edible plants such as choy sum,” says DiSTAP and TLL principal investigator and co-corresponding author Rajani Sarojam. “The results showed that the Raman spectroscopy-based method can swiftly detect and quantify innate immunity response in plants infected with bacterial pathogens. We believe that this technology will be beneficial for agricultural farms to increase their productivity by reducing their yield loss due to plant diseases.”

      The researchers are currently working on the development of high-throughput, custom-made portable or hand-held Raman spectrometers that will allow Raman spectral analysis to be quickly and easily performed on field-grown crops.

      SMART and TLL developed and discovered the diagnostic algorithm and Raman spectral biomarkers. TLL also confirmed and validated the detection method through mutant plants. The research is carried out by SMART and supported by the National Research Foundation of Singapore under its Campus for Research Excellence And Technological Enterprise (CREATE) program.

      SMART was established by MIT and the NRF in 2007. The first entity in CREATE developed by NRF, SMART serves as an intellectual and innovation hub for research interactions between MIT and Singapore, undertaking cutting-edge research projects in areas of interest to both Singapore and MIT. SMART 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. SMART research is funded by the NRF under the CREATE program.

      Led by Professor Michael Strano of MIT and Professor Chua Nam Hai of Temasek Lifesciences Laboratory, 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 biomaterial 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, and drought and pathogen resistance; and applying these technologies to improve urban farming. More

    • 38 Shares199 Views

      in Energy

      Design’s new frontier

      by

      In the 1960s, the advent of computer-aided design (CAD) sparked a revolution in design. For his PhD thesis in 1963, MIT Professor Ivan Sutherland developed Sketchpad, a game-changing software program that enabled users to draw, move, and resize shapes on a computer. Over the course of the next few decades, CAD software reshaped how everything from consumer products to buildings and airplanes were designed.

      “CAD was part of the first wave in computing in design. The ability of researchers and practitioners to represent and model designs using computers was a major breakthrough and still is one of the biggest outcomes of design research, in my opinion,” says Maria Yang, Gail E. Kendall Professor and director of MIT’s Ideation Lab.

      Innovations in 3D printing during the 1980s and 1990s expanded CAD’s capabilities beyond traditional injection molding and casting methods, providing designers even more flexibility. Designers could sketch, ideate, and develop prototypes or models faster and more efficiently. Meanwhile, with the push of a button, software like that developed by Professor Emeritus David Gossard of MIT’s CAD Lab could solve equations simultaneously to produce a new geometry on the fly.

      In recent years, mechanical engineers have expanded the computing tools they use to ideate, design, and prototype. More sophisticated algorithms and the explosion of machine learning and artificial intelligence technologies have sparked a second revolution in design engineering.

      Researchers and faculty at MIT’s Department of Mechanical Engineering are utilizing these technologies to re-imagine how the products, systems, and infrastructures we use are designed. These researchers are at the forefront of the new frontier in design.

      Computational design

      Faez Ahmed wants to reinvent the wheel, or at least the bicycle wheel. He and his team at MIT’s Design Computation & Digital Engineering Lab (DeCoDE) use an artificial intelligence-driven design method that can generate entirely novel and improved designs for a range of products — including the traditional bicycle. They create advanced computational methods to blend human-driven design with simulation-based design.

      “The focus of our DeCoDE lab is computational design. We are looking at how we can create machine learning and AI algorithms to help us discover new designs that are optimized based on specific performance parameters,” says Ahmed, an assistant professor of mechanical engineering at MIT.

      For their work using AI-driven design for bicycles, Ahmed and his collaborator Professor Daniel Frey wanted to make it easier to design customizable bicycles, and by extension, encourage more people to use bicycles over transportation methods that emit greenhouse gases.

      To start, the group gathered a dataset of 4,500 bicycle designs. Using this massive dataset, they tested the limits of what machine learning could do. First, they developed algorithms to group bicycles that looked similar together and explore the design space. They then created machine learning models that could successfully predict what components are key in identifying a bicycle style, such as a road bike versus a mountain bike.

      Once the algorithms were good enough at identifying bicycle designs and parts, the team proposed novel machine learning tools that could use this data to create a unique and creative design for a bicycle based on certain performance parameters and rider dimensions.

      Ahmed used a generative adversarial network — or GAN — as the basis of this model. GAN models utilize neural networks that can create new designs based on vast amounts of data. However, using GAN models alone would result in homogeneous designs that lack novelty and can’t be assessed in terms of performance. To address these issues in design problems, Ahmed has developed a new method which he calls “PaDGAN,” performance augmented diverse GAN.

      “When we apply this type of model, what we see is that we can get large improvements in the diversity, quality, as well as novelty of the designs,” Ahmed explains.

      Using this approach, Ahmed’s team developed an open-source computational design tool for bicycles freely available on their lab website. They hope to further develop a set of generalizable tools that can be used across industries and products.

      Longer term, Ahmed has his sights set on loftier goals. He hopes the computational design tools he develops could lead to “design democratization,” putting more power in the hands of the end user.

      “With these algorithms, you can have more individualization where the algorithm assists a customer in understanding their needs and helps them create a product that satisfies their exact requirements,” he adds.

      Using algorithms to democratize the design process is a goal shared by Stefanie Mueller, an associate professor in electrical engineering and computer science and mechanical engineering.

      Personal fabrication

      Platforms like Instagram give users the freedom to instantly edit their photographs or videos using filters. In one click, users can alter the palette, tone, and brightness of their content by applying filters that range from bold colors to sepia-toned or black-and-white. Mueller, X-Window Consortium Career Development Professor, wants to bring this concept of the Instagram filter to the physical world.

      “We want to explore how digital capabilities can be applied to tangible objects. Our goal is to bring reprogrammable appearance to the physical world,” explains Mueller, director of the HCI Engineering Group based out of MIT’s Computer Science and Artificial Intelligence Laboratory.

      Mueller’s team utilizes a combination of smart materials, optics, and computation to advance personal fabrication technologies that would allow end users to alter the design and appearance of the products they own. They tested this concept in a project they dubbed “Photo-Chromeleon.”

      First, a mix of photochromic cyan, magenta, and yellow dies are airbrushed onto an object — in this instance, a 3D sculpture of a chameleon. Using software they developed, the team sketches the exact color pattern they want to achieve on the object itself. An ultraviolet light shines on the object to activate the dyes.

      To actually create the physical pattern on the object, Mueller has developed an optimization algorithm to use alongside a normal office projector outfitted with red, green, and blue LED lights. These lights shine on specific pixels on the object for a given period of time to physically change the makeup of the photochromic pigments.

      “This fancy algorithm tells us exactly how long we have to shine the red, green, and blue light on every single pixel of an object to get the exact pattern we’ve programmed in our software,” says Mueller.

      Giving this freedom to the end user enables limitless possibilities. Mueller’s team has applied this technology to iPhone cases, shoes, and even cars. In the case of shoes, Mueller envisions a shoebox embedded with UV and LED light projectors. Users could put their shoes in the box overnight and the next day have a pair of shoes in a completely new pattern.

      Mueller wants to expand her personal fabrication methods to the clothes we wear. Rather than utilize the light projection technique developed in the PhotoChromeleon project, her team is exploring the possibility of weaving LEDs directly into clothing fibers, allowing people to change their shirt’s appearance as they wear it. These personal fabrication technologies could completely alter consumer habits.

      “It’s very interesting for me to think about how these computational techniques will change product design on a high level,” adds Mueller. “In the future, a consumer could buy a blank iPhone case and update the design on a weekly or daily basis.”

      Computational fluid dynamics and participatory design

      Another team of mechanical engineers, including Sili Deng, the Brit (1961) & Alex (1949) d’Arbeloff Career Development Professor, are developing a different kind of design tool that could have a large impact on individuals in low- and middle-income countries across the world.

      As Deng walked down the hallway of Building 1 on MIT’s campus, a monitor playing a video caught her eye. The video featured work done by mechanical engineers and MIT D-Lab on developing cleaner burning briquettes for cookstoves in Uganda. Deng immediately knew she wanted to get involved.

      “As a combustion scientist, I’ve always wanted to work on such a tangible real-world problem, but the field of combustion tends to focus more heavily on the academic side of things,” explains Deng.

      After reaching out to colleagues in MIT D-Lab, Deng joined a collaborative effort to develop a new cookstove design tool for the 3 billion people across the world who burn solid fuels to cook and heat their homes. These stoves often emit soot and carbon monoxide, leading not only to millions of deaths each year, but also worsening the world’s greenhouse gas emission problem.

      The team is taking a three-pronged approach to developing this solution, using a combination of participatory design, physical modeling, and experimental validation to create a tool that will lead to the production of high-performing, low-cost energy products.

      Deng and her team in the Deng Energy and Nanotechnology Group use physics-based modeling for the combustion and emission process in cookstoves.

      “My team is focused on computational fluid dynamics. We use computational and numerical studies to understand the flow field where the fuel is burned and releases heat,” says Deng.

      These flow mechanics are crucial to understanding how to minimize heat loss and make cookstoves more efficient, as well as learning how dangerous pollutants are formed and released in the process.

      Using computational methods, Deng’s team performs three-dimensional simulations of the complex chemistry and transport coupling at play in the combustion and emission processes. They then use these simulations to build a combustion model for how fuel is burned and a pollution model that predicts carbon monoxide emissions.

      Deng’s models are used by a group led by Daniel Sweeney in MIT D-Lab to test the experimental validation in prototypes of stoves. Finally, Professor Maria Yang uses participatory design methods to integrate user feedback, ensuring the design tool can actually be used by people across the world.

      The end goal for this collaborative team is to not only provide local manufacturers with a prototype they could produce themselves, but to also provide them with a tool that can tweak the design based on local needs and available materials.

      Deng sees wide-ranging applications for the computational fluid dynamics her team is developing.

      “We see an opportunity to use physics-based modeling, augmented with a machine learning approach, to come up with chemical models for practical fuels that help us better understand combustion. Therefore, we can design new methods to minimize carbon emissions,” she adds.

      While Deng is utilizing simulations and machine learning at the molecular level to improve designs, others are taking a more macro approach.

      Designing intelligent systems

      When it comes to intelligent design, Navid Azizan thinks big. He hopes to help create future intelligent systems that are capable of making decisions autonomously by using the enormous amounts of data emerging from the physical world. From smart robots and autonomous vehicles to smart power grids and smart cities, Azizan focuses on the analysis, design, and control of intelligent systems.

      Achieving such massive feats takes a truly interdisciplinary approach that draws upon various fields such as machine learning, dynamical systems, control, optimization, statistics, and network science, among others.

      “Developing intelligent systems is a multifaceted problem, and it really requires a confluence of disciplines,” says Azizan, assistant professor of mechanical engineering with a dual appointment in MIT’s Institute for Data, Systems, and Society (IDSS). “To create such systems, we need to go beyond standard approaches to machine learning, such as those commonly used in computer vision, and devise algorithms that can enable safe, efficient, real-time decision-making for physical systems.”

      For robot control to work in the complex dynamic environments that arise in the real world, real-time adaptation is key. If, for example, an autonomous vehicle is going to drive in icy conditions or a drone is operating in windy conditions, they need to be able to adapt to their new environment quickly.

      To address this challenge, Azizan and his collaborators at MIT and Stanford University have developed a new algorithm that combines adaptive control, a powerful methodology from control theory, with meta learning, a new machine learning paradigm.

      “This ‘control-oriented’ learning approach outperforms the existing ‘regression-oriented’ methods, which are mostly focused on just fitting the data, by a wide margin,” says Azizan.

      Another critical aspect of deploying machine learning algorithms in physical systems that Azizan and his team hope to address is safety. Deep neural networks are a crucial part of autonomous systems. They are used for interpreting complex visual inputs and making data-driven predictions of future behavior in real time. However, Azizan urges caution.

      “These deep neural networks are only as good as their training data, and their predictions can often be untrustworthy in scenarios not covered by their training data,” he says. Making decisions based on such untrustworthy predictions could lead to fatal accidents in autonomous vehicles or other safety-critical systems.

      To avoid these potentially catastrophic events, Azizan proposes that it is imperative to equip neural networks with a measure of their uncertainty. When the uncertainty is high, they can then be switched to a “safe policy.”

      In pursuit of this goal, Azizan and his collaborators have developed a new algorithm known as SCOD — Sketching Curvature of Out-of-Distribution Detection. This framework could be embedded within any deep neural network to equip them with a measure of their uncertainty.

      “This algorithm is model-agnostic and can be applied to neural networks used in various kinds of autonomous systems, whether it’s drones, vehicles, or robots,” says Azizan.

      Azizan hopes to continue working on algorithms for even larger-scale systems. He and his team are designing efficient algorithms to better control supply and demand in smart energy grids. According to Azizan, even if we create the most efficient solar panels and batteries, we can never achieve a sustainable grid powered by renewable resources without the right control mechanisms.

      Mechanical engineers like Ahmed, Mueller, Deng, and Azizan serve as the key to realizing the next revolution of computing in design.

      “MechE is in a unique position at the intersection of the computational and physical worlds,” Azizan says. “Mechanical engineers build a bridge between theoretical, algorithmic tools and real, physical world applications.”

      Sophisticated computational tools, coupled with the ground truth mechanical engineers have in the physical world, could unlock limitless possibilities for design engineering, well beyond what could have been imagined in those early days of CAD. More

    • 63 Shares169 Views

      in Security

      Saving seaweed with machine learning

      by

      Last year, Charlene Xia ’17, SM ’20 found herself at a crossroads. She was finishing up her master’s degree in media arts and sciences from the MIT Media Lab and had just submitted applications to doctoral degree programs. All Xia could do was sit and wait. In the meantime, she narrowed down her career options, regardless of whether she was accepted to any program.

      “I had two thoughts: I’m either going to get a PhD to work on a project that protects our planet, or I’m going to start a restaurant,” recalls Xia.

      Xia poured over her extensive cookbook collection, researching international cuisines as she anxiously awaited word about her graduate school applications. She even looked into the cost of a food truck permit in the Boston area. Just as she started hatching plans to open a plant-based skewer restaurant, Xia received word that she had been accepted into the mechanical engineering graduate program at MIT.

      Shortly after starting her doctoral studies, Xia’s advisor, Professor David Wallace, approached her with an interesting opportunity. MathWorks, a software company known for developing the MATLAB computing platform, had announced a new seed funding program in MIT’s Department of Mechanical Engineering. The program encouraged collaborative research projects focused on the health of the planet.

      “I saw this as a super-fun opportunity to combine my passion for food, my technical expertise in ocean engineering, and my interest in sustainably helping our planet,” says Xia.

      Play video

      From MIT Mechanical Engineering: “Saving Seaweed with Machine Learning”

      Wallace knew Xia would be up to the task of taking an interdisciplinary approach to solve an issue related to the health of the planet. “Charlene is a remarkable student with extraordinary talent and deep thoughtfulness. She is pretty much fearless, embracing challenges in almost any domain with the well-founded belief that, with effort, she will become a master,” says Wallace.

      Alongside Wallace and Associate Professor Stefanie Mueller, Xia proposed a project to predict and prevent the spread of diseases in aquaculture. The team focused on seaweed farms in particular.

      Already popular in East Asian cuisines, seaweed holds tremendous potential as a sustainable food source for the world’s ever-growing population. In addition to its nutritive value, seaweed combats various environmental threats. It helps fight climate change by absorbing excess carbon dioxide in the atmosphere, and can also absorb fertilizer run-off, keeping coasts cleaner.

      As with so much of marine life, seaweed is threatened by the very thing it helps mitigate against: climate change. Climate stressors like warm temperatures or minimal sunlight encourage the growth of harmful bacteria such as ice-ice disease. Within days, entire seaweed farms are decimated by unchecked bacterial growth.

      To solve this problem, Xia turned to the microbiota present in these seaweed farms as a predictive indicator of any threat to the seaweed or livestock. “Our project is to develop a low-cost device that can detect and prevent diseases before they affect seaweed or livestock by monitoring the microbiome of the environment,” says Xia.

      The team pairs old technology with the latest in computing. Using a submersible digital holographic microscope, they take a 2D image. They then use a machine learning system known as a neural network to convert the 2D image into a representation of the microbiome present in the 3D environment.

      “Using a machine learning network, you can take a 2D image and reconstruct it almost in real time to get an idea of what the microbiome looks like in a 3D space,” says Xia.

      The software can be run in a small Raspberry Pi that could be attached to the holographic microscope. To figure out how to communicate these data back to the research team, Xia drew upon her master’s degree research.

      In that work, under the guidance of Professor Allan Adams and Professor Joseph Paradiso in the Media Lab, Xia focused on developing small underwater communication devices that can relay data about the ocean back to researchers. Rather than the usual $4,000, these devices were designed to cost less than $100, helping lower the cost barrier for those interested in uncovering the many mysteries of our oceans. The communication devices can be used to relay data about the ocean environment from the machine learning algorithms.

      By combining these low-cost communication devices along with microscopic images and machine learning, Xia hopes to design a low-cost, real-time monitoring system that can be scaled to cover entire seaweed farms.

      “It’s almost like having the ‘internet of things’ underwater,” adds Xia. “I’m developing this whole underwater camera system alongside the wireless communication I developed that can give me the data while I’m sitting on dry land.”

      Armed with these data about the microbiome, Xia and her team can detect whether or not a disease is about to strike and jeopardize seaweed or livestock before it is too late.

      While Xia still daydreams about opening a restaurant, she hopes the seaweed project will prompt people to rethink how they consider food production in general.

      “We should think about farming and food production in terms of the entire ecosystem,” she says. “My meta-goal for this project would be to get people to think about food production in a more holistic and natural way.” More