Aurelia Butler

Latest story

150 Shares32 Views

3 Questions: How AI is helping us monitor and support vulnerable ecosystems

by

A recent study from Oregon State University estimated that more than 3,500 animal species are at risk of extinction because of factors including habitat alterations, natural resources being overexploited, and climate change.To better understand these changes and protect vulnerable wildlife, conservationists like MIT PhD student and Computer Science and Artificial Intelligence Laboratory (CSAIL) researcher Justin Kay are developing computer vision algorithms that carefully monitor animal populations. A member of the lab of MIT Department of Electrical Engineering and Computer Science assistant professor and CSAIL principal investigator Sara Beery, Kay is currently working on tracking salmon in the Pacific Northwest, where they provide crucial nutrients to predators like birds and bears, while managing the population of prey, like bugs.With all that wildlife data, though, researchers have lots of information to sort through and many AI models to choose from to analyze it all. Kay and his colleagues at CSAIL and the University of Massachusetts Amherst are developing AI methods that make this data-crunching process much more efficient, including a new approach called “consensus-driven active model selection” (or “CODA”) that helps conservationists choose which AI model to use. Their work was named a Highlight Paper at the International Conference on Computer Vision (ICCV) in October.That research was supported, in part, by the National Science Foundation, Natural Sciences and Engineering Research Council of Canada, and Abdul Latif Jameel Water and Food Systems Lab (J-WAFS). Here, Kay discusses this project, among other conservation efforts.Q: In your paper, you pose the question of which AI models will perform the best on a particular dataset. With as many as 1.9 million pre-trained models available in the HuggingFace Models repository alone, how does CODA help us address that challenge?A: Until recently, using AI for data analysis has typically meant training your own model. This requires significant effort to collect and annotate a representative training dataset, as well as iteratively train and validate models. You also need a certain technical skill set to run and modify AI training code. The way people interact with AI is changing, though — in particular, there are now millions of publicly available pre-trained models that can perform a variety of predictive tasks very well. This potentially enables people to use AI to analyze their data without developing their own model, simply by downloading an existing model with the capabilities they need. But this poses a new challenge: Which model, of the millions available, should they use to analyze their data? Typically, answering this model selection question also requires you to spend a lot of time collecting and annotating a large dataset, albeit for testing models rather than training them. This is especially true for real applications where user needs are specific, data distributions are imbalanced and constantly changing, and model performance may be inconsistent across samples. Our goal with CODA was to substantially reduce this effort. We do this by making the data annotation process “active.” Instead of requiring users to bulk-annotate a large test dataset all at once, in active model selection we make the process interactive, guiding users to annotate the most informative data points in their raw data. This is remarkably effective, often requiring users to annotate as few as 25 examples to identify the best model from their set of candidates. We’re very excited about CODA offering a new perspective on how to best utilize human effort in the development and deployment of machine-learning (ML) systems. As AI models become more commonplace, our work emphasizes the value of focusing effort on robust evaluation pipelines, rather than solely on training.Q: You applied the CODA method to classifying wildlife in images. Why did it perform so well, and what role can systems like this have in monitoring ecosystems in the future?A: One key insight was that when considering a collection of candidate AI models, the consensus of all of their predictions is more informative than any individual model’s predictions. This can be seen as a sort of “wisdom of the crowd:” On average, pooling the votes of all models gives you a decent prior over what the labels of individual data points in your raw dataset should be. Our approach with CODA is based on estimating a “confusion matrix” for each AI model — given the true label for some data point is class X, what is the probability that an individual model predicts class X, Y, or Z? This creates informative dependencies between all of the candidate models, the categories you want to label, and the unlabeled points in your dataset.Consider an example application where you are a wildlife ecologist who has just collected a dataset containing potentially hundreds of thousands of images from cameras deployed in the wild. You want to know what species are in these images, a time-consuming task that computer vision classifiers can help automate. You are trying to decide which species classification model to run on your data. If you have labeled 50 images of tigers so far, and some model has performed well on those 50 images, you can be pretty confident it will perform well on the remainder of the (currently unlabeled) images of tigers in your raw dataset as well. You also know that when that model predicts some image contains a tiger, it is likely to be correct, and therefore that any model that predicts a different label for that image is more likely to be wrong. You can use all these interdependencies to construct probabilistic estimates of each model’s confusion matrix, as well as a probability distribution over which model has the highest accuracy on the overall dataset. These design choices allow us to make more informed choices over which data points to label and ultimately are the reason why CODA performs model selection much more efficiently than past work.There are also a lot of exciting possibilities for building on top of our work. We think there may be even better ways of constructing informative priors for model selection based on domain expertise — for instance, if it is already known that one model performs exceptionally well on some subset of classes or poorly on others. There are also opportunities to extend the framework to support more complex machine-learning tasks and more sophisticated probabilistic models of performance. We hope our work can provide inspiration and a starting point for other researchers to keep pushing the state of the art.Q: You work in the Beerylab, led by Sara Beery, where researchers are combining the pattern-recognition capabilities of machine-learning algorithms with computer vision technology to monitor wildlife. What are some other ways your team is tracking and analyzing the natural world, beyond CODA?A: The lab is a really exciting place to work, and new projects are emerging all the time. We have ongoing projects monitoring coral reefs with drones, re-identifying individual elephants over time, and fusing multi-modal Earth observation data from satellites and in-situ cameras, just to name a few. Broadly, we look at emerging technologies for biodiversity monitoring and try to understand where the data analysis bottlenecks are, and develop new computer vision and machine-learning approaches that address those problems in a widely applicable way. It’s an exciting way of approaching problems that sort of targets the “meta-questions” underlying particular data challenges we face. The computer vision algorithms I’ve worked on that count migrating salmon in underwater sonar video are examples of that work. We often deal with shifting data distributions, even as we try to construct the most diverse training datasets we can. We always encounter something new when we deploy a new camera, and this tends to degrade the performance of computer vision algorithms. This is one instance of a general problem in machine learning called domain adaptation, but when we tried to apply existing domain adaptation algorithms to our fisheries data we realized there were serious limitations in how existing algorithms were trained and evaluated. We were able to develop a new domain adaptation framework, published earlier this year in Transactions on Machine Learning Research, that addressed these limitations and led to advancements in fish counting, and even self-driving and spacecraft analysis.One line of work that I’m particularly excited about is understanding how to better develop and analyze the performance of predictive ML algorithms in the context of what they are actually used for. Usually, the outputs from some computer vision algorithm — say, bounding boxes around animals in images — are not actually the thing that people care about, but rather a means to an end to answer a larger problem — say, what species live here, and how is that changing over time? We have been working on methods to analyze predictive performance in this context and reconsider the ways that we input human expertise into ML systems with this in mind. CODA was one example of this, where we showed that we could actually consider the ML models themselves as fixed and build a statistical framework to understand their performance very efficiently. We have been working recently on similar integrated analyses combining ML predictions with multi-stage prediction pipelines, as well as ecological statistical models. The natural world is changing at unprecedented rates and scales, and being able to quickly move from scientific hypotheses or management questions to data-driven answers is more important than ever for protecting ecosystems and the communities that depend on them. Advancements in AI can play an important role, but we need to think critically about the ways that we design, train, and evaluate algorithms in the context of these very real challenges. More

More stories

  • 150 Shares32 Views

    in Environment

    3 Questions: How AI is helping us monitor and support vulnerable ecosystems

    A recent study from Oregon State University estimated that more than 3,500 animal species are at risk of extinction because of factors including habitat alterations, natural resources being overexploited, and climate change.To better understand these changes and protect vulnerable wildlife, conservationists like MIT PhD student and Computer Science and Artificial Intelligence Laboratory (CSAIL) researcher Justin Kay are developing computer vision algorithms that carefully monitor animal populations. A member of the lab of MIT Department of Electrical Engineering and Computer Science assistant professor and CSAIL principal investigator Sara Beery, Kay is currently working on tracking salmon in the Pacific Northwest, where they provide crucial nutrients to predators like birds and bears, while managing the population of prey, like bugs.With all that wildlife data, though, researchers have lots of information to sort through and many AI models to choose from to analyze it all. Kay and his colleagues at CSAIL and the University of Massachusetts Amherst are developing AI methods that make this data-crunching process much more efficient, including a new approach called “consensus-driven active model selection” (or “CODA”) that helps conservationists choose which AI model to use. Their work was named a Highlight Paper at the International Conference on Computer Vision (ICCV) in October.That research was supported, in part, by the National Science Foundation, Natural Sciences and Engineering Research Council of Canada, and Abdul Latif Jameel Water and Food Systems Lab (J-WAFS). Here, Kay discusses this project, among other conservation efforts.Q: In your paper, you pose the question of which AI models will perform the best on a particular dataset. With as many as 1.9 million pre-trained models available in the HuggingFace Models repository alone, how does CODA help us address that challenge?A: Until recently, using AI for data analysis has typically meant training your own model. This requires significant effort to collect and annotate a representative training dataset, as well as iteratively train and validate models. You also need a certain technical skill set to run and modify AI training code. The way people interact with AI is changing, though — in particular, there are now millions of publicly available pre-trained models that can perform a variety of predictive tasks very well. This potentially enables people to use AI to analyze their data without developing their own model, simply by downloading an existing model with the capabilities they need. But this poses a new challenge: Which model, of the millions available, should they use to analyze their data? Typically, answering this model selection question also requires you to spend a lot of time collecting and annotating a large dataset, albeit for testing models rather than training them. This is especially true for real applications where user needs are specific, data distributions are imbalanced and constantly changing, and model performance may be inconsistent across samples. Our goal with CODA was to substantially reduce this effort. We do this by making the data annotation process “active.” Instead of requiring users to bulk-annotate a large test dataset all at once, in active model selection we make the process interactive, guiding users to annotate the most informative data points in their raw data. This is remarkably effective, often requiring users to annotate as few as 25 examples to identify the best model from their set of candidates. We’re very excited about CODA offering a new perspective on how to best utilize human effort in the development and deployment of machine-learning (ML) systems. As AI models become more commonplace, our work emphasizes the value of focusing effort on robust evaluation pipelines, rather than solely on training.Q: You applied the CODA method to classifying wildlife in images. Why did it perform so well, and what role can systems like this have in monitoring ecosystems in the future?A: One key insight was that when considering a collection of candidate AI models, the consensus of all of their predictions is more informative than any individual model’s predictions. This can be seen as a sort of “wisdom of the crowd:” On average, pooling the votes of all models gives you a decent prior over what the labels of individual data points in your raw dataset should be. Our approach with CODA is based on estimating a “confusion matrix” for each AI model — given the true label for some data point is class X, what is the probability that an individual model predicts class X, Y, or Z? This creates informative dependencies between all of the candidate models, the categories you want to label, and the unlabeled points in your dataset.Consider an example application where you are a wildlife ecologist who has just collected a dataset containing potentially hundreds of thousands of images from cameras deployed in the wild. You want to know what species are in these images, a time-consuming task that computer vision classifiers can help automate. You are trying to decide which species classification model to run on your data. If you have labeled 50 images of tigers so far, and some model has performed well on those 50 images, you can be pretty confident it will perform well on the remainder of the (currently unlabeled) images of tigers in your raw dataset as well. You also know that when that model predicts some image contains a tiger, it is likely to be correct, and therefore that any model that predicts a different label for that image is more likely to be wrong. You can use all these interdependencies to construct probabilistic estimates of each model’s confusion matrix, as well as a probability distribution over which model has the highest accuracy on the overall dataset. These design choices allow us to make more informed choices over which data points to label and ultimately are the reason why CODA performs model selection much more efficiently than past work.There are also a lot of exciting possibilities for building on top of our work. We think there may be even better ways of constructing informative priors for model selection based on domain expertise — for instance, if it is already known that one model performs exceptionally well on some subset of classes or poorly on others. There are also opportunities to extend the framework to support more complex machine-learning tasks and more sophisticated probabilistic models of performance. We hope our work can provide inspiration and a starting point for other researchers to keep pushing the state of the art.Q: You work in the Beerylab, led by Sara Beery, where researchers are combining the pattern-recognition capabilities of machine-learning algorithms with computer vision technology to monitor wildlife. What are some other ways your team is tracking and analyzing the natural world, beyond CODA?A: The lab is a really exciting place to work, and new projects are emerging all the time. We have ongoing projects monitoring coral reefs with drones, re-identifying individual elephants over time, and fusing multi-modal Earth observation data from satellites and in-situ cameras, just to name a few. Broadly, we look at emerging technologies for biodiversity monitoring and try to understand where the data analysis bottlenecks are, and develop new computer vision and machine-learning approaches that address those problems in a widely applicable way. It’s an exciting way of approaching problems that sort of targets the “meta-questions” underlying particular data challenges we face. The computer vision algorithms I’ve worked on that count migrating salmon in underwater sonar video are examples of that work. We often deal with shifting data distributions, even as we try to construct the most diverse training datasets we can. We always encounter something new when we deploy a new camera, and this tends to degrade the performance of computer vision algorithms. This is one instance of a general problem in machine learning called domain adaptation, but when we tried to apply existing domain adaptation algorithms to our fisheries data we realized there were serious limitations in how existing algorithms were trained and evaluated. We were able to develop a new domain adaptation framework, published earlier this year in Transactions on Machine Learning Research, that addressed these limitations and led to advancements in fish counting, and even self-driving and spacecraft analysis.One line of work that I’m particularly excited about is understanding how to better develop and analyze the performance of predictive ML algorithms in the context of what they are actually used for. Usually, the outputs from some computer vision algorithm — say, bounding boxes around animals in images — are not actually the thing that people care about, but rather a means to an end to answer a larger problem — say, what species live here, and how is that changing over time? We have been working on methods to analyze predictive performance in this context and reconsider the ways that we input human expertise into ML systems with this in mind. CODA was one example of this, where we showed that we could actually consider the ML models themselves as fixed and build a statistical framework to understand their performance very efficiently. We have been working recently on similar integrated analyses combining ML predictions with multi-stage prediction pipelines, as well as ecological statistical models. The natural world is changing at unprecedented rates and scales, and being able to quickly move from scientific hypotheses or management questions to data-driven answers is more important than ever for protecting ecosystems and the communities that depend on them. Advancements in AI can play an important role, but we need to think critically about the ways that we design, train, and evaluate algorithms in the context of these very real challenges. More

  • 125 Shares102 Views

    in Environment

    Over 1,000 MIT students inspired to work toward climate solutions

    Recently, more than 1,000 MIT students stepped into the shoes of global decision-makers by trying out En-ROADS, a simulation tool developed to test climate policies, explore solutions, and envision a cleaner and safer environmental future.MIT is committed to climate action, and this year’s new student orientation showcased that commitment. For the first time ever, incoming Leaders for Global Operations (LGO), Executive MBA, Sloan Fellow MBA, MBA, and undergraduate students all explored the capabilities of En-ROADS.“The goal is for MIT to become one of the world’s most prolific, collaborative, and interdisciplinary sources of technological, behavioral, and policy solutions for the global climate challenge over the next decade,” MIT Provost Anantha P. Chandrakasan told an audience of about 300 undergraduates from the Class of 2029. “It is something we need to do urgently, and today is your opportunity to play a role in that bold mission.”Connecting passion with science for changeIn group workshop sessions, students collaborated to create a world in which global warming stays well below 2 degrees Celsius above preindustrial levels — the goal of the 2015 Paris Agreement. Backed by the latest science, the En-ROADS simulator let them explore firsthand how policies like carbon pricing and clean energy investments affect our climate, economy, and health. Over 450 incoming MBA students even role-played as delegates at a global climate summit conference, tasked with negotiating a global agreement to address the harm caused by climate change.For first-year MBA student Allison Somuk, who played the role of President Xi Jinping of China, the workshop was not only eye-opening about climate, but also altered how she plans to approach her future work and advocacy.“Before the simulation, I didn’t have data on climate change, so I was surprised to see how close we are to catastrophic temperature increases. What surprised me most was how difficult it was to slow that trajectory. It required significant action and compromise from nearly every sector, not just a few. As someone passionate about improving maternal health care in developing nations, my view of contributing factors has broadened. I now see how maternal health may be affected by a larger system where climate policy decisions directly affect women’s health outcomes.”MIT Sloan Research Affiliate Andrew Jones, who is also executive director and co-founder of Climate Interactive and co-creator of the En-ROADS tool, presented several sessions during orientation. Looking back on the week, he found the experience personally rewarding.  “Engaging with hundreds of students, I was inspired by the powerful alignment between their passion for climate action and MIT’s increased commitment to delivering on climate goals. This is a pivotal moment for breakthroughs on our campus.”Other presenters included Jennifer Graham, MIT Sustainability Initiative senior associate director; Jason Jay, MIT Sustainability Initiative director; Krystal Noiseux, MIT Climate Pathways Project associate director; Bethany Patten, MIT Climate Policy Center executive director; and John Sterman, Jay W. Forrester Professor of Management, professor in the MIT Institute for Data, Systems, and Society, and director of the MIT System Dynamics Group.Chris Rabe, the MIT Climate Project’s Education Program director, was impressed, but not surprised, by how much students learned so quickly as they worked together to solve the problem with En-ROADS.“By integrating reflection, emotional dynamics, multi-generational perspectives, group work, and inquiry, the En-ROADS simulation provides an ideal foundation for first-year students to explore the breadth of climate and sustainability opportunities at MIT. In the process, students came to recognize the many levers and multi-solving approaches required to address the complex challenges of climate change.”Inspiring climate leadersThe En-ROADS workshops were a true team effort, made possible with the help of senior staff at MIT Sloan School of Management and the MBA program office, and members of the MIT Sloan Sustainability Initiative, Climate Pathways Project, Climate Policy Center, the Climate Project, Office of the First Year, and entire undergraduate Orientation team.“Altogether, over a thousand of the newest members of the MIT community have now had a chance to learn for themselves about the climate crisis,” says Sterman, “and what we can do to create a healthier, safer, more prosperous, and more sustainable world — and how they can get involved to bring that world into being, even as first-year undergrads and MBAs.” By the end of the workshops, the students’ spirits were buoyed. They all had successfully found ways to keep global warming to below 2 C.  When asked, “What would you love about being part of this new future you’ve created?,”  a more positive, optimistic word cloud came into view. Answers included:breathing cleaner air;giving my children a better and safer environment;my hometown would not be flooded constantly;rich marine life and protection of reefs;exciting, new clean industries;increased socioeconomic equality; andproof that we as a global community can work together to save ourselves. First-year MBA student Ruby Eisenbud sums up the sentiment many new MIT students came away with after their workshop.“Coming to Sloan, one of the questions on my mind was: How can we, as future leaders, make a positive impact related to climate change? While En-ROADS is a simulation, it felt like we experienced, in the smallest way, what it could be like to be a leader navigating the diverging interests of all stakeholders involved in mitigating the impacts of the climate crisis. While the simulation prompted us to face the difficult reality of climate change, it also reinforced my motivation to emphasize climate in my work at Sloan and beyond.” More

  • 125 Shares166 Views

    in Environment

    Book reviews technologies aiming to remove carbon from the atmosphere

    Two leading experts in the field of carbon capture and sequestration (CCS) — Howard J. Herzog, a senior research engineer in the MIT Energy Initiative, and Niall Mac Dowell, a professor in energy systems engineering at Imperial College London — explore methods for removing carbon dioxide already in the atmosphere in their new book, “Carbon Removal.” Published in October, the book is part of the Essential Knowledge series from the MIT Press, which consists of volumes “synthesizing specialized subject matter for nonspecialists” and includes Herzog’s 2018 book, “Carbon Capture.”Burning fossil fuels, as well as other human activities, cause the release of carbon dioxide (CO2) into the atmosphere, where it acts like a blanket that warms the Earth, resulting in climate change. Much attention has focused on mitigation technologies that reduce emissions, but in their book, Herzog and Mac Dowell have turned their attention to “carbon dioxide removal” (CDR), an approach that removes carbon already present in the atmosphere.In this new volume, the authors explain how CO2 naturally moves into and out of the atmosphere and present a brief history of carbon removal as a concept for dealing with climate change. They also describe the full range of “pathways” that have been proposed for removing CO2 from the atmosphere. Those pathways include engineered systems designed for “direct air capture” (DAC), as well as various “nature-based” approaches that call for planting trees or taking steps to enhance removal by biomass or the oceans. The book offers easily accessible explanations of the fundamental science and engineering behind each approach.The authors compare the “quality” of the different pathways based on the following metrics:Accounting. For public acceptance of any carbon-removal strategy, the authors note, the developers need to get the accounting right — and that’s not always easy. “If you’re going to spend money to get CO2 out of the atmosphere, you want to get paid for doing it,” notes Herzog. It can be tricky to measure how much you have removed, because there’s a lot of CO2 going in and out of the atmosphere all the time. Also, if your approach involves, say, burning fossil fuels, you must subtract the amount of CO2 that’s emitted from the total amount you claim to have removed. Then there’s the timing of the removal. With a DAC device, the removal happens right now, and the removed CO2 can be measured. “But if I plant a tree, it’s going to remove CO2 for decades. Is that equivalent to removing it right now?” Herzog queries. How to take that factor into account hasn’t yet been resolved.Permanence. Different approaches keep the CO2 out of the atmosphere for different durations of time. How long is long enough? As the authors explain, this is one of the biggest issues, especially with nature-based solutions, where events such as wildfires or pestilence or land-use changes can release the stored CO2 back into the atmosphere. How do we deal with that?Cost. Cost is another key factor. Using a DAC device to remove CO2 costs far more than planting trees, but it yields immediate removal of a measurable amount of CO2 that can then be locked away forever. How does one monetize that trade-off?Additionality. “You’re doing this project, but would what you’re doing have been done anyway?” asks Herzog. “Is your effort additional to business as usual?” This question comes into play with many of the nature-based approaches involving trees, soils, and so on.Permitting and governance. These issues are especially important — and complicated — with approaches that involve doing things in the ocean. In addition, Herzog points out that some CCS projects could also achieve carbon removal, but they would have a hard time getting permits to build the pipelines and other needed infrastructure.The authors conclude that none of the CDR strategies now being proposed is a clear winner on all the metrics. However, they stress that carbon removal has the potential to play an important role in meeting our climate change goals — not by replacing our emissions-reduction efforts, but rather by supplementing them. However, as Herzog and Mac Dowell make clear in their book, many challenges must be addressed to move CDR from today’s speculation to deployment at scale, and the book supports the wider discussion about how to move forward. Indeed, the authors have fulfilled their stated goal: “to provide an objective analysis of the opportunities and challenges for CDR and to separate myth from reality.” More

  • 138 Shares98 Views

    in Environment

    MIT engineers solve the sticky-cell problem in bioreactors and other industries

    To help mitigate climate change, companies are using bioreactors to grow algae and other microorganisms that are hundreds of times more efficient at absorbing CO2 than trees. Meanwhile, in the pharmaceutical industry, cell culture is used to manufacture biologic drugs and other advanced treatments, including lifesaving gene and cell therapies.Both processes are hampered by cells’ tendency to stick to surfaces, which leads to a huge amount of waste and downtime for cleaning. A similar problem slows down biofuel production, interferes with biosensors and implants, and makes the food and beverage industry less efficient.Now, MIT researchers have developed an approach for detaching cells from surfaces on demand, using electrochemically generated bubbles. In an open-access paper published in Science Advances, the researchers demonstrated their approach in a lab prototype and showed it could work across a range of cells and surfaces without harming the cells.“We wanted to develop a technology that could be high-throughput and plug-and-play, and that would allow cells to attach and detach on demand to improve the workflow in these industrial processes,” says Professor Kripa Varanasi, senior author of the study. “This is a fundamental issue with cells, and we’ve solved it with a process that can scale. It lends itself to many different applications.”Joining Varanasi on the study are co-first authors Bert Vandereydt, a PhD student in mechanical engineering, and former postdoc Baptiste Blanc.Solving a sticky problem

    Credit: Joy Zheng

    The researchers began with a mission.“We’ve been working on figuring out how we can efficiently capture CO2 across different sources and convert it into valuable products for various end markets,” Varanasi says. “That’s where this photobioreactor and cell detachment comes into the picture.”Photobioreactors are used to grow carbon-absorbing algae cells by creating tightly controlled environments involving water and sunlight. They feature long, winding tubes with clear surfaces to let in the light algae need to grow. When algae stick to those surfaces, they block out the light, requiring cleaning.“You have to shut down and clean up the entire reactor as frequently as every two weeks,” Varanasi says. “It’s a huge operational challenge.”The researchers realized other industries have similar problem due to many cells’ natural adhesion, or stickiness. Each industry has its own solution for cell adhesion depending on how important it is that the cells survive. Some people scrape the surfaces clean, while others use special coatings that are toxic to cells.In the pharmaceutical and biotech industries, cell detachment is typically carried out using enzymes. However, this method poses several challenges — it can damage cell membranes, is time-consuming, and requires large amounts of consumables, resulting in millions of liters of biowaste.To create a better solution, the researchers began by studying other efforts to clear surfaces with bubbles, which mainly involved spraying bubbles onto surfaces and had been largely ineffective.“We realized we needed the bubbles to form on the surfaces where we don’t want these cells to stick, so when the bubbles detach it creates a local fluid flow that creates shear stress at the interface and removes the cells,” Varanasi explains.Electric currents generate bubbles by splitting water into hydrogen and oxygen. But previous attempts at using electricity to detach cells were hampered because the cell culture mediums contain sodium chloride, which turns into bleach when combined with an electric current. The bleach damages the cells, making it impractical for many applications.“The culprit is the anode — that’s where the sodium chloride turns to bleach,” Vandereydt explained. “We figured if we could separate that electrode from the rest of the system, we could prevent bleach from being generated.”To make a better system, the researchers built a 3-square-inch glass surface and deposited a gold electrode on top of it. The layer of gold is so thin it doesn’t block out light. To keep the other electrode separate, the researchers integrated a special membrane that only allows protons to pass through. The set up allowed the researchers to send a current through without generating bleach.To test their setup, they allowed algae cells from a concentrated solution to stick to the surfaces. When they applied a voltage, the bubbles separated the cells from the surfaces without harming them.The researchers also studied the interaction between the bubbles and cells, finding the higher the current density, the more bubbles were created and the more algae was removed. They developed a model for understanding how much current would be needed to remove algae in different settings and matched it with results from experiments involving algae as well as cells from ovarian cancer and bones.“Mammalian cells are orders of magnitude more sensitive than algae cells, but even with those cells, we were able to detach them with no impact to the viability of the cell,” Vandereydt says.Getting to scaleThe researchers say their system could represent a breakthrough in applications where bleach or other chemicals would harm cells. That includes pharmaceutical and food production.“If we can keep these systems running without fouling and other problems, then we can make them much more economical,” Varanasi says.For cell culture plates used in the pharmaceutical industry, the team envisions their system comprising an electrode that could be robotically moved from one culture plate to the next, to detach cells as they’re grown. It could also be coiled around algae harvesting systems.“This has general applicability because it doesn’t rely on any specific biological or chemical treatments, but on a physical force that is system-agnostic,” Varanasi says. “It’s also highly scalable to a lot of different processes, including particle removal.”Varanasi cautions there is much work to be done to scale up the system. But he hopes it can one day make algae and other cell harvesting more efficient.“The burning problem of our time is to somehow capture CO2 in a way that’s economically feasible,” Varanasi says. “These photobioreactors could be used for that, but we have to overcome the cell adhesion problem.”The work was supported, in part, by Eni S.p.A through the MIT Energy Initiative, the Belgian American Educational Foundation Fellowship, and the Maria Zambrano Fellowship. More

  • 113 Shares156 Views

    in Security

    Optimizing food subsidies: Applying digital platforms to maximize nutrition

    Oct. 16 is World Food Day, a global campaign to celebrate the founding of the Food and Agriculture Organization 80 years ago, and to work toward a healthy, sustainable, food-secure future. More than 670 million people in the world are facing hunger. Millions of others are facing rising obesity rates and struggle to get healthy food for proper nutrition. World Food Day calls on not only world governments, but business, academia, the media, and even the youth to take action to promote resilient food systems and combat hunger. This year, the Abdul Latif Jameel Water and Food Systems Laboratory (J-WAFS) is spotlighting an MIT researcher who is working toward this goal by studying food and water systems in the Global South.J-WAFS seed grants provide funding to early-stage research projects that are unique to prior work. In an 11th round of seed grant funding in 2025, 10 MIT faculty members received support to carry out their cutting-edge water and food research. Ali Aouad PhD ’17, assistant professor of operations management at the MIT Sloan School of Management, was one of those grantees. “I had searched before joining MIT what kind of research centers and initiatives were available that tried to coalesce research on food systems,” Aouad says. “And so, I was very excited about J-WAFS.” Aouad gathered more information about J-WAFS at the new faculty orientation session in August 2024, where he spoke to J-WAFS staff and learned about the program’s grant opportunities for water and food research. Later that fall semester, he attended a few J-WAFS seminars on agricultural economics and water resource management. That’s when Aouad knew that his project was perfectly aligned with the J-WAFS mission of securing humankind’s water and food.Aouad’s seed project focuses on food subsidies. With a background in operations research and an interest in digital platforms, much of his work has centered on aligning supply-side operations with heterogeneous customer preferences. Past projects include ones on retail and matching systems. “I started thinking that these types of demand-driven approaches may be also very relevant to important social challenges, particularly as they relate to food security,” Aouad says. Before starting his PhD at MIT, Aouad worked on projects that looked at subsidies for smallholder farmers in low- and middle-income countries. “I think in the back of my mind, I’ve always been fascinated by trying to solve these issues,” he noted.His seed grant project, Optimal subsidy design: Application to food assistance programs, aims to leverage data on preferences and purchasing habits from local grocery stores in India to inform food assistance policy and optimize the design of subsidies. Typical data collection systems, like point-of-sales, are not as readily available in India’s local groceries, making this type of data hard to come by for low-income individuals. “Mom-and-pop stores are extremely important last-mile operators when it comes to nutrition,” he explains. For this project, the research team gave local grocers point-of-sale scanners to track purchasing habits. “We aim to develop an algorithm that converts these transactions into some sort of ‘revelation’ of the individuals’ latent preferences,” says Aouad. “As such, we can model and optimize the food assistance programs — how much variety and flexibility is offered, taking into account the expected demand uptake.” He continues, “now, of course, our ability to answer detailed design questions [across various products and prices] depends on the quality of our inference from  the data, and so this is where we need more sophisticated and robust algorithms.”Following the data collection and model development, the ultimate goal of this research is to inform policy surrounding food assistance programs through an “optimization approach.” Aouad describes the complexities of using optimization to guide policy. “Policies are often informed by domain expertise, legacy systems, or political deliberation. A lot of researchers build rigorous evidence to inform food policy, but it’s fair to say that the kind of approach that I’m proposing in this research is not something that is commonly used. I see an opportunity for bringing a new approach and methodological tradition to a problem that has been central for policy for many decades.” The overall health of consumers is the reason food assistance programs exist, yet measuring long-term nutritional impacts and shifts in purchase behavior is difficult. In past research, Aouad notes that the short-term effects of food assistance interventions can be significant. However, these effects are often short-lived. “This is a fascinating question that I don’t think we will be able to address within the space of interventions that we will be considering. However, I think it is something I would like to capture in the research, and maybe develop hypotheses for future work around how we can shift nutrition-related behaviors in the long run.”While his project develops a new methodology to calibrate food assistance programs, large-scale applications are not promised. “A lot of what drives subsidy mechanisms and food assistance programs is also, quite frankly, how easy it is and how cost-effective it is to implement these policies in the first place,” comments Aouad. Cost and infrastructure barriers are unavoidable to this kind of policy research, as well as sustaining these programs. Aouad’s effort will provide insights into customer preferences and subsidy optimization in a pilot setup, but replicating this approach on a real scale may be costly. Aouad hopes to be able to gather proxy information from customers that would both feed into the model and provide insight into a more cost-effective way to collect data for large-scale implementation.There is still much work to be done to ensure food security for all, whether it’s advances in agriculture, food-assistance programs, or ways to boost adequate nutrition. As the 2026 seed grant deadline approaches, J-WAFS will continue its mission of supporting MIT faculty as they pursue innovative projects that have practical and real impacts on water and food system challenges. More

  • 113 Shares188 Views

    in Environment

    How to reduce greenhouse gas emissions from ammonia production

    Ammonia is one of the most widely produced chemicals in the world, used mostly as fertilizer, but also for the production of some plastics, textiles, and other applications. Its production, through processes that require high heat and pressure, accounts for up to 20 percent of all the greenhouse gases from the entire chemical industry, so efforts have been underway worldwide to find ways to reduce those emissions.Now, researchers at MIT have come up with a clever way of combining two different methods of producing the compound that minimizes waste products, that, when combined with some other simple upgrades, could reduce the greenhouse emissions from production by as much as 63 percent, compared to the leading “low-emissions” approach being used today.The new approach is described in the journal Energy & Fuels, in a paper by MIT Energy Initiative (MITEI) Director William H. Green, graduate student Sayandeep Biswas, MITEI Director of Research Randall Field, and two others.“Ammonia has the most carbon dioxide emissions of any kind of chemical,” says Green, who is the Hoyt C. Hottel Professor in Chemical Engineering. “It’s a very important chemical,” he says, because its use as a fertilizer is crucial to being able to feed the world’s population.Until late in the 19th century, the most widely used source of nitrogen fertilizer was mined deposits of bat or bird guano, mostly from Chile, but that source was beginning to run out, and there were predictions that the world would soon be running short of food to sustain the population. But then a new chemical process, called the Haber-Bosch process after its inventors, made it possible to make ammonia out of nitrogen from the air and hydrogen, which was mostly derived from methane. But both the burning of fossil fuels to provide the needed heat and the use of methane to make the hydrogen led to massive climate-warming emissions from the process.To address this, two newer variations of ammonia production have been developed: so-called “blue ammonia,” where the greenhouse gases are captured right at the factory and then sequestered deep underground, and “green ammonia,” produced by a different chemical pathway, using electricity instead of fossil fuels to hydrolyze water to make hydrogen.Blue ammonia is already beginning to be used, with a few plants operating now in Louisiana, Green says, and the ammonia mostly being shipped to Japan, “so that’s already kind of commercial.” Other parts of the world are starting to use green ammonia, especially in places that have lots of hydropower, solar, or wind to provide inexpensive electricity, including a giant plant now under construction in Saudi Arabia.But in most places, both blue and green ammonia are still more expensive than the traditional fossil-fuel-based version, so many teams around the world have been working on ways to cut these costs as much as possible so that the difference is small enough to be made up through tax subsidies or other incentives.The problem is growing, because as the population grows, and as wealth increases, there will be ever-increasing demands for nitrogen fertilizer. At the same time, ammonia is a promising substitute fuel to power hard-to-decarbonize transportation such as cargo ships and heavy trucks, which could lead to even greater needs for the chemical.“It definitely works” as a transportation fuel, by powering fuel cells that have been demonstrated for use by everything from drones to barges and tugboats and trucks, Green says. “People think that the most likely market of that type would be for shipping,” he says, “because the downside of ammonia is it’s toxic and it’s smelly, and that makes it slightly dangerous to handle and to ship around.” So its best uses may be where it’s used in high volume and in relatively remote locations, like the high seas. In fact, the International Maritime Organization will soon be voting on new rules that might give a strong boost to the ammonia alternative for shipping.The key to the new proposed system is to combine the two existing approaches in one facility, with a blue ammonia factory next to a green ammonia factory. The process of generating hydrogen for the green ammonia plant leaves a lot of leftover oxygen that just gets vented to the air. Blue ammonia, on the other hand, uses a process called autothermal reforming that requires a source of pure oxygen, so if there’s a green ammonia plant next door, it can use that excess oxygen.“Putting them next to each other turns out to have significant economic value,” Green says. This synergy could help hybrid “blue-green ammonia” facilities serve as an important bridge toward a future where eventually green ammonia, the cleanest version, could finally dominate. But that future is likely decades away, Green says, so having the combined plants could be an important step along the way.“It might be a really long time before [green ammonia] is actually attractive” economically, he says. “Right now, it’s nowhere close, except in very special situations.” But the combined plants “could be a really appealing concept, and maybe a good way to start the industry,” because so far only small, standalone demonstration plants of the green process are being built.“If green or blue ammonia is going to become the new way of making ammonia, you need to find ways to make it relatively affordable in a lot of countries, with whatever resources they’ve got,” he says. This new proposed combination, he says, “looks like a really good idea that can help push things along. Ultimately, there’s got to be a lot of green ammonia plants in a lot of places,” and starting out with the combined plants, which could be more affordable now, could help to make that happen. The team has filed for a patent on the process.Although the team did a detailed study of both the technology and the economics that show the system has great promise, Green points out that “no one has ever built one. We did the analysis, it looks good, but surely when people build the first one, they’ll find funny little things that need some attention,” such as details of how to start up or shut down the process. “I would say there’s plenty of additional work to do to make it a real industry.” But the results of this study, which shows the costs to be much more affordable than existing blue or green plants in isolation, “definitely encourages the possibility of people making the big investments that would be needed to really make this industry feasible.”This proposed integration of the two methods “improves efficiency, reduces greenhouse gas emissions, and lowers overall cost,” says Kevin van Geem, a professor in the Center for Sustainable Chemistry at Ghent University, who was not associated with this research. “The analysis is rigorous, with validated process models, transparent assumptions, and comparisons to literature benchmarks. By combining techno-economic analysis with emissions accounting, the work provides a credible and balanced view of the trade-offs.”He adds that, “given the scale of global ammonia production, such a reduction could have a highly impactful effect on decarbonizing one of the most emissions-intensive chemical industries.”The research team also included MIT postdoc Angiras Menon and MITEI research lead Guiyan Zang. The work was supported by IHI Japan through the MIT Energy Initiative and the Martin Family Society of Fellows for Sustainability.  More

  • 113 Shares99 Views

    in Security

    Matthew Shoulders named head of the Department of Chemistry

    Matthew D. Shoulders, the Class of 1942 Professor of Chemistry, a MacVicar Faculty Fellow, and an associate member of the Broad Institute of MIT and Harvard, has been named head of the MIT Department of Chemistry, effective Jan. 16, 2026. “Matt has made pioneering contributions to the chemistry research community through his research on mechanisms of proteostasis and his development of next-generation techniques to address challenges in biomedicine and agriculture,” says Nergis Mavalvala, dean of the MIT School of Science and the Curtis and Kathleen Marble Professor of Astrophysics. “He is also a dedicated educator, beloved by undergraduates and graduates alike. I know the department will be in good hands as we double down on our commitment to world-leading research and education in the face of financial headwinds.”Shoulders succeeds Troy Van Voorhis, the Robert T. Haslam and Bradley Dewey Professor of Chemistry, who has been at the helm since October 2019.“I am tremendously grateful to Troy for his leadership the past six years, building a fantastic community here in our department. We face challenges, but also many exciting opportunities, as a department in the years to come,” says Shoulders. “One thing is certain: Chemistry innovations are critical to solving pressing global challenges. Through the research that we do and the scientists we train, our department has a huge role to play in shaping the future.”Shoulders studies how cells fold proteins, and he develops ​and applies novel protein engineering techniques to challenges in biotechnology. His work across chemistry and biochemistry fields including proteostasis, extracellular matrix biology, virology, evolution, and synthetic biology is yielding not just important insights into topics like how cells build healthy tissues and how proteins evolve, but also influencing approaches to disease therapy and biotechnology development.“Matt is an outstanding researcher whose work touches on fundamental questions about how the cell machinery directs the synthesis and folding of proteins. His discoveries about how that machinery breaks down as a result of mutations or in response to stress has a fundamental impact on how we think about and treat human diseases,” says Van Voorhis.In one part of Matt’s current research program, he is studying how protein folding systems in cells — known as chaperones — shape the evolution of their clients. Amongst other discoveries, his lab has shown that viral pathogens hijack human chaperones to enable their rapid evolution and escape from host immunity. In related recent work, they have discovered that these same chaperones can promote access to malignancy-driving mutations in tumors. Beyond fundamental insights into evolutionary biology, these findings hold potential to open new therapeutic strategies to target cancer and viral infections.“Matt’s ability to see both the details and the big picture makes him an outstanding researcher and a natural leader for the department,” says Timothy Swager, the John D. MacArthur Professor of Chemistry. “MIT Chemistry can only benefit from his dedication to understanding and addressing the parts and the whole.” Shoulders also leads a food security project through the Abdul Latif Jameel Water and Food Systems Lab (J-WAFS). Shoulders, along with MIT Research Scientist Robbie Wilson, assembled an interdisciplinary team based at MIT to enhance climate resilience in agriculture by improving one of the most inefficient aspects of photosynthesis, the carbon dioxide-fixing plant enzyme RuBisCO. J-WAFS funded this high-risk, high-reward MIT Grand Challenge project in 2023, and it has received further support from federal research agencies and the Grantham Foundation for the Protection of the Environment. “Our collaborative team of biochemists and synthetic biologists, computational biologists, and chemists is deeply integrated with plant biologists, creating a robust feedback loop for enzyme engineering,” Shoulders says. “Together, this team is making a concerted effort using state-of-the-art techniques to engineer crop RuBisCO with an eye to helping make meaningful gains in securing a stable crop supply, hopefully with accompanying improvements in both food and water security.”In addition to his research contributions, Shoulders has taught multiple classes for Course V, including 5.54 (Advances in Chemical Biology) and 5.111 (Principles of Chemical Science), along with a number of other key chemistry classes. His contributions to a 5.111 “bootcamp” through the MITx platform served to address gaps in the classroom curriculum by providing online tools to help undergraduate students better grasp the material in the chemistry General Institute Requirement (GIR). His development of Guided Learning Demonstrations to support first-year chemistry courses at MIT has helped bring the lab to the GIR, and also contributed to the popularity of 5.111 courses offered regularly via MITx.“I have had the pleasure of teaching with Matt on several occasions, and he is a fantastic educator. He is an innovator both inside and outside the classroom and has an unwavering commitment to his students’ success,” says Van Voorhis of Shoulders, who was named a 2022 MacVicar Faculty Fellow, and who received a Committed to Caring award through the Office of Graduate Education.Shoulders also founded the MIT Homeschool Internship Program for Science and Technology, which brings high school students to campus for paid summer research experiences in labs across the Institute.He is a founding member of the Department of Chemistry’s Quality of Life Committee and chair for the last six years, helping to improve all aspects of opportunity, professional development, and experience in the department: “countless changes that have helped make MIT a better place for all,” as Van Voorhis notes, including creating a peer mentoring program for graduate students and establishing universal graduate student exit interviews to collect data for department-wide assessment and improvement.At the Institute level, Shoulders has served on the Committee on Graduate Programs, Committee on Sexual Misconduct Prevention and Response (in which he co-chaired the provost’s working group on the Faculty and Staff Sexual Misconduct Survey), and the Committee on Assessment of Biohazards and Embryonic Stem Cell Research Oversight, among other roles.Shoulders graduated summa cum laude from Virginia Tech in 2004, earning a BS in chemistry with a minor in biochemistry. He earned a PhD in chemistry at the University of Wisconsin at Madison in 2009 under Professor Ronald Raines. Following an American Cancer Society Postdoctoral Fellowship at Scripps Research Institute, working with professors Jeffery Kelly and Luke Wiseman, Shoulders joined the MIT Department of Chemistry faculty as an assistant professor in 2012. Shoulders also serves as an associate member of the Broad Institute and an investigator at the Center for Musculoskeletal Research at Massachusetts General Hospital.Among his many awards, Shoulders has received a NIH Director’s New Innovator Award under the NIH High-Risk, High-Reward Research Program; an NSF CAREER Award; an American Cancer Society Research Scholar Award; the Camille Dreyfus Teacher-Scholar Award; and most recently the Ono Pharma Foundation Breakthrough Science Award. More

  • 125 Shares99 Views

    in Environment

    Report: Sustainability in supply chains is still a firm-level priority

    Corporations are actively seeking sustainability advances in their supply chains — but many need to improve the business metrics they use in this area to realize more progress, according to a new report by MIT researchers.   During a time of shifting policies globally and continued economic uncertainty, the survey-based report finds 85 percent of companies say they are continuing supply chain sustainability practices at the same level as in recent years, or are increasing those efforts.“What we found is strong evidence that sustainability still matters,” says Josué Velázquez Martínez, a research scientist and director of the MIT Sustainable Supply Chain Lab, which helped produce the report. “There are many things that remain to be done to accomplish those goals, but there’s a strong willingness from companies in all parts of the world to do something about sustainability.”The new analysis, titled “Sustainability Still Matters,” was released today. It is the sixth annual report on the subject prepared by the MIT Sustainable Supply Chain Lab, which is part of MIT’s Center for Transportation and Logistics. The Council of Supply Chain Management Professionals collaborated on the project as well.The report is based on a global survey, with responses from 1,203 professionals in 97 countries. This year, the report analyzes three issues in depth, including regulations and the role they play in corporate approaches to supply chain management. A second core topic is management and mitigation of what industry professionals call “Scope 3” emissions, which are those not from a firm itself, but from a firm’s supply chain. And a third issue of focus is the future of freight transportation, which by itself accounts for a substantial portion of supply chain emissions.Broadly, the survey finds that for European-based firms, the principal driver of action in this area remains government mandates, such as the Corporate Sustainability Reporting Directive, which requires companies to publish regular reports on their environmental impact and the risks to society involved. In North America, firm leadership and investor priorities are more likely to be decisive factors in shaping a company’s efforts.“In Europe the pressure primarily comes more from regulation, but in the U.S. it comes more from investors, or from competitors,” Velázquez Martínez says.The survey responses on Scope 3 emissions reveal a number of opportunities for improvement. In business and sustainability terms, Scope 1 greenhouse gas emissions are those a firm produces directly. Scope 2 emissions are the energy it has purchased. And Scope 3 emissions are those produced across a firm’s value chain, including the supply chain activities involved in producing, transporting, using, and disposing of its products.The report reveals that about 40 percent of firms keep close track of Scope 1 and 2 emissions, but far fewer tabulate Scope 3 on equivalent terms. And yet Scope 3 may account for roughly 75 percent of total firm emissions, on aggregate. About 70 percent of firms in the survey say they do not have enough data from suppliers to accurately tabulate the total greenhouse gas and climate impact of their supply chains.Certainly it can be hard to calculate the total emissions when a supply chain has many layers, including smaller suppliers lacking data capacity. But firms can upgrade their analytics in this area, too. For instance, 50 percent of North American firms are still using spreadsheets to tabulate emissions data, often making rough estimates that correlate emissions to simple economic activity. An alternative is life cycle assessment software that provides more sophisticated estimates of a product’s emissions, from the extraction of its materials to its post-use disposal. By contrast, only 32 percent of European firms are still using spreadsheets rather than life cycle assessment tools.“You get what you measure,” Velázquez Martínez says. “If you measure poorly, you’re going to get poor decisions that most likely won’t drive the reductions you’re expecting. So we pay a lot of attention to that particular issue, which is decisive to defining an action plan. Firms pay a lot of attention to metrics in their financials, but in sustainability they’re often using simplistic measurements.”When it comes to transportation, meanwhile, the report shows that firms are still grappling with the best ways to reduce emissions. Some see biofuels as the best short-term alternative to fossil fuels; others are investing in electric vehicles; some are waiting for hydrogen-powered vehicles to gain traction. Supply chains, after all, frequently involve long-haul trips. For firms, as for individual consumers, electric vehicles are more practical with a larger infrastructure of charging stations. There are advances on that front but more work to do as well.That said, “Transportation has made a lot of progress in general,” Velázquez Martínez says, noting the increased acceptance of new modes of vehicle power in general.Even as new technologies loom on the horizon, though, supply chain sustainability is not wholly depend on their introduction. One factor continuing to propel sustainability in supply chains is the incentives companies have to lower costs. In a competitive business environment, spending less on fossil fuels usually means savings. And firms can often find ways to alter their logistics to consume and spend less.“Along with new technologies, there is another side of supply chain sustainability that is related to better use of the current infrastructure,” Velázquez Martínez observes. “There is always a need to revise traditional ways of operating to find opportunities for more efficiency.”  More