More stories

  • in

    MIT researchers remotely map crops, field by field

    Crop maps help scientists and policymakers track global food supplies and estimate how they might shift with climate change and growing populations. But getting accurate maps of the types of crops that are grown from farm to farm often requires on-the-ground surveys that only a handful of countries have the resources to maintain.

    Now, MIT engineers have developed a method to quickly and accurately label and map crop types without requiring in-person assessments of every single farm. The team’s method uses a combination of Google Street View images, machine learning, and satellite data to automatically determine the crops grown throughout a region, from one fraction of an acre to the next. 

    The researchers used the technique to automatically generate the first nationwide crop map of Thailand — a smallholder country where small, independent farms make up the predominant form of agriculture. The team created a border-to-border map of Thailand’s four major crops — rice, cassava, sugarcane, and maize — and determined which of the four types was grown, at every 10 meters, and without gaps, across the entire country. The resulting map achieved an accuracy of 93 percent, which the researchers say is comparable to on-the-ground mapping efforts in high-income, big-farm countries.

    The team is applying their mapping technique to other countries such as India, where small farms sustain most of the population but the type of crops grown from farm to farm has historically been poorly recorded.

    “It’s a longstanding gap in knowledge about what is grown around the world,” says Sherrie Wang, the d’Arbeloff Career Development Assistant Professor in MIT’s Department of Mechanical Engineering, and the Institute for Data, Systems, and Society (IDSS). “The final goal is to understand agricultural outcomes like yield, and how to farm more sustainably. One of the key preliminary steps is to map what is even being grown — the more granularly you can map, the more questions you can answer.”

    Wang, along with MIT graduate student Jordi Laguarta Soler and Thomas Friedel of the agtech company PEAT GmbH, will present a paper detailing their mapping method later this month at the AAAI Conference on Artificial Intelligence.

    Ground truth

    Smallholder farms are often run by a single family or farmer, who subsist on the crops and livestock that they raise. It’s estimated that smallholder farms support two-thirds of the world’s rural population and produce 80 percent of the world’s food. Keeping tabs on what is grown and where is essential to tracking and forecasting food supplies around the world. But the majority of these small farms are in low to middle-income countries, where few resources are devoted to keeping track of individual farms’ crop types and yields.

    Crop mapping efforts are mainly carried out in high-income regions such as the United States and Europe, where government agricultural agencies oversee crop surveys and send assessors to farms to label crops from field to field. These “ground truth” labels are then fed into machine-learning models that make connections between the ground labels of actual crops and satellite signals of the same fields. They then label and map wider swaths of farmland that assessors don’t cover but that satellites automatically do.

    “What’s lacking in low- and middle-income countries is this ground label that we can associate with satellite signals,” Laguarta Soler says. “Getting these ground truths to train a model in the first place has been limited in most of the world.”

    The team realized that, while many developing countries do not have the resources to maintain crop surveys, they could potentially use another source of ground data: roadside imagery, captured by services such as Google Street View and Mapillary, which send cars throughout a region to take continuous 360-degree images with dashcams and rooftop cameras.

    In recent years, such services have been able to access low- and middle-income countries. While the goal of these services is not specifically to capture images of crops, the MIT team saw that they could search the roadside images to identify crops.

    Cropped image

    In their new study, the researchers worked with Google Street View (GSV) images taken throughout Thailand — a country that the service has recently imaged fairly thoroughly, and which consists predominantly of smallholder farms.

    Starting with over 200,000 GSV images randomly sampled across Thailand, the team filtered out images that depicted buildings, trees, and general vegetation. About 81,000 images were crop-related. They set aside 2,000 of these, which they sent to an agronomist, who determined and labeled each crop type by eye. They then trained a convolutional neural network to automatically generate crop labels for the other 79,000 images, using various training methods, including iNaturalist — a web-based crowdsourced  biodiversity database, and GPT-4V, a “multimodal large language model” that enables a user to input an image and ask the model to identify what the image is depicting. For each of the 81,000 images, the model generated a label of one of four crops that the image was likely depicting — rice, maize, sugarcane, or cassava.

    The researchers then paired each labeled image with the corresponding satellite data taken of the same location throughout a single growing season. These satellite data include measurements across multiple wavelengths, such as a location’s greenness and its reflectivity (which can be a sign of water). 

    “Each type of crop has a certain signature across these different bands, which changes throughout a growing season,” Laguarta Soler notes.

    The team trained a second model to make associations between a location’s satellite data and its corresponding crop label. They then used this model to process satellite data taken of the rest of the country, where crop labels were not generated or available. From the associations that the model learned, it then assigned crop labels across Thailand, generating a country-wide map of crop types, at a resolution of 10 square meters.

    This first-of-its-kind crop map included locations corresponding to the 2,000 GSV images that the researchers originally set aside, that were labeled by arborists. These human-labeled images were used to validate the map’s labels, and when the team looked to see whether the map’s labels matched the expert, “gold standard” labels, it did so 93 percent of the time.

    “In the U.S., we’re also looking at over 90 percent accuracy, whereas with previous work in India, we’ve only seen 75 percent because ground labels are limited,” Wang says. “Now we can create these labels in a cheap and automated way.”

    The researchers are moving to map crops across India, where roadside images via Google Street View and other services have recently become available.

    “There are over 150 million smallholder farmers in India,” Wang says. “India is covered in agriculture, almost wall-to-wall farms, but very small farms, and historically it’s been very difficult to create maps of India because there are very sparse ground labels.”

    The team is working to generate crop maps in India, which could be used to inform policies having to do with assessing and bolstering yields, as global temperatures and populations rise.

    “What would be interesting would be to create these maps over time,” Wang says. “Then you could start to see trends, and we can try to relate those things to anything like changes in climate and policies.” More

  • in

    Q&A: A blueprint for sustainable innovation

    Atacama Biomaterials is a startup combining architecture, machine learning, and chemical engineering to create eco-friendly materials with multiple applications. Passionate about sustainable innovation, its co-founder Paloma Gonzalez-Rojas SM ’15, PhD ’21 highlights here how MIT has supported the project through several of its entrepreneurship initiatives, and reflects on the role of design in building a holistic vision for an expanding business.

    Q: What role do you see your startup playing in the sustainable materials space?

    A: Atacama Biomaterials is a venture dedicated to advancing sustainable materials through state-of-the-art technology. With my co-founder Jose Tomas Dominguez, we have been working on developing our technology since 2019. We initially started the company in 2020 under another name and received Sandbox funds the next year. In 2021, we went through The Engine’s accelerator, Blueprint, and changed our name to Atacama Biomaterials in 2022 during the MITdesignX program. 

    This technology we have developed allows us to create our own data and material library using artificial intelligence and machine learning, and serves as a platform applicable to various industries horizontally — biofuels, biological drugs, and even mining. Vertically, we produce inexpensive, regionally sourced, and environmentally friendly bio-based polymers and packaging — that is, naturally compostable plastics as a flagship product, along with AI products.

    Q: What motivated you to venture into biomaterials and found Atacama?

    A: I’m from Chile, a country with a beautiful, rich geography and nature where we can see all the problems stemming from industry, waste management, and pollution. We named our company Atacama Biomaterials because the Atacama Desert in Chile — one of the places where you can best see the stars in the world — is becoming a plastic dump, as many other places on Earth. I care deeply about sustainability, and I have an emotional attachment to stop these problems. Considering that manufacturing accounts for 29 percent of global carbon emissions, it is clear that sustainability has a role in how we define technology and entrepreneurship, as well as a socio-economic dimension.

    When I first came to MIT, it was to develop software in the Department of Architecture’s Design and Computation Group, with MIT professors Svafa Gronfeldt as co-advisor and Regina Barzilay as committee member. During my PhD, I studied machine-learning methods simulating pedestrian motion to understand how people move in space. In my work, I would use lots of plastics for 3D printing and I couldn’t stop thinking about sustainability and climate change, so I reached out to material science and mechanical engineering professors to look into biopolymers and degradable bio-based materials. This is how I met my co-founder, as we were both working with MIT Professor Neil Gershenfeld. Together, we were part of one of the first teams in the world to 3D print wood fibers, which is difficult — it’s slow and expensive — and quickly pivoted to sustainable packaging. 

    I then won a fellowship from MCSC [the MIT Climate and Sustainability Consortium], which gave me freedom to explore further, and I eventually got a postdoc in MIT chemical engineering, guided by MIT Professor Gregory Rutledge, a polymer physicist. This was unexpected in my career path. Winning Nucleate Eco Track 2022 and the MITdesignX Innovation Award in 2022 profiled Atacama Biomaterials as one of the rising startups in Boston’s biotechnology and climate-tech scene.

    Q: What is your process to develop new biomaterials?

    A: My PhD research, coupled with my background in material development and molecular dynamics, sparked the realization that principles I studied simulating pedestrian motion could also apply to molecular engineering. This connection may seem unconventional, but for me, it was a natural progression. Early in my career, I developed an intuition for materials, understanding their mechanics and physics.

    Using my experience and skills, and leveraging machine learning as a technology jump, I applied a similar conceptual framework to simulate the trajectories of molecules and find potential applications in biomaterials. Making that parallel and shift was amazing. It allowed me to optimize a state-of-the-art molecular dynamic software to run twice as fast as more traditional technologies through my algorithm presented at the International Conference of Machine Learning this year. This is very important, because this kind of simulation usually takes a week, so narrowing it down to two days has major implications for scientists and industry, in material science, chemical engineering, computer science and related fields. Such work greatly influenced the foundation of Atacama Biomaterials, where we developed our own AI to deploy our materials. In an effort to mitigate the environmental impact of manufacturing, Atacama is targeting a 16.7 percent reduction in carbon dioxide emissions associated with the manufacturing process of its polymers, through the use of renewable energy. 

    Another thing is that I was trained as an architect in Chile, and my degree had a design component. I think design allows me to understand problems at a very high level, and how things interconnect. It contributed to developing a holistic vision for Atacama, because it allowed me to jump from one technology or discipline to another and understand broader applications on a conceptual level. Our design approach also meant that sustainability came to the center of our work from the very beginning, not just a plus or an added cost.

    Q: What was the role of MITdesignX in Atacama’s development?

    A: I have known Svafa Grönfeldt, MITdesignX’s faculty director, for almost six years. She was the co-advisor of my PhD, and we had a mentor-mentee relationship. I admire the fact that she created a space for people interested in business and entrepreneurship to grow within the Department of Architecture. She and Executive Director Gilad Rosenzweig gave us fantastic advice, and we received significant support from mentors. For example, Daniel Tsai helped us with intellectual property, including a crucial patent for Atacama. And we’re still in touch with the rest of the cohort. I really like this “design your company” approach, which I find quite unique, because it gives us the opportunity to reflect on who we want to be as designers, technologists, and entrepreneurs. Studying user insights also allowed us to understand the broad applicability of our research, and align our vision with market demands, ultimately shaping Atacama into a company with a holistic perspective on sustainable material development.

    Q: How does Atacama approach scaling, and what are the immediate next steps for the company?

    A: When I think about accomplishing our vision, I feel really inspired by my 3-year-old daughter. I want her to experience a world with trees and wildlife when she’s 100 years old, and I hope Atacama will contribute to such a future.

    Going back to the designer’s perspective, we designed the whole process holistically, from feedstock to material development, incorporating AI and advanced manufacturing. Having proved that there is a demand for the materials we are developing, and having tested our products, manufacturing process, and technology in critical environments, we are now ready to scale. Our level of technology-readiness is comparable to the one used by NASA (level 4).

    We have proof of concept: a biodegradable and recyclable packaging material which is cost- and energy-efficient as a clean energy enabler in large-scale manufacturing. We have received pre-seed funding, and are sustainably scaling by taking advantage of available resources around the world, like repurposing machinery from the paper industry. As presented in the MIT Industrial Liaison and STEX Program’s recent Sustainability Conference, unlike our competitors, we have cost-parity with current packaging materials, as well as low-energy processes. And we also proved the demand for our products, which was an important milestone. Our next steps involve strategically expanding our manufacturing capabilities and research facilities and we are currently evaluating building a factory in Chile and establishing an R&D lab plus a manufacturing plant in the U.S. More

  • in

    New tools are available to help reduce the energy that AI models devour

    When searching for flights on Google, you may have noticed that each flight’s carbon-emission estimate is now presented next to its cost. It’s a way to inform customers about their environmental impact, and to let them factor this information into their decision-making.

    A similar kind of transparency doesn’t yet exist for the computing industry, despite its carbon emissions exceeding those of the entire airline industry. Escalating this energy demand are artificial intelligence models. Huge, popular models like ChatGPT signal a trend of large-scale artificial intelligence, boosting forecasts that predict data centers will draw up to 21 percent of the world’s electricity supply by 2030.

    The MIT Lincoln Laboratory Supercomputing Center (LLSC) is developing techniques to help data centers reel in energy use. Their techniques range from simple but effective changes, like power-capping hardware, to adopting novel tools that can stop AI training early on. Crucially, they have found that these techniques have a minimal impact on model performance.

    In the wider picture, their work is mobilizing green-computing research and promoting a culture of transparency. “Energy-aware computing is not really a research area, because everyone’s been holding on to their data,” says Vijay Gadepally, senior staff in the LLSC who leads energy-aware research efforts. “Somebody has to start, and we’re hoping others will follow.”

    Curbing power and cooling down

    Like many data centers, the LLSC has seen a significant uptick in the number of AI jobs running on its hardware. Noticing an increase in energy usage, computer scientists at the LLSC were curious about ways to run jobs more efficiently. Green computing is a principle of the center, which is powered entirely by carbon-free energy.

    Training an AI model — the process by which it learns patterns from huge datasets — requires using graphics processing units (GPUs), which are power-hungry hardware. As one example, the GPUs that trained GPT-3 (the precursor to ChatGPT) are estimated to have consumed 1,300 megawatt-hours of electricity, roughly equal to that used by 1,450 average U.S. households per month.

    While most people seek out GPUs because of their computational power, manufacturers offer ways to limit the amount of power a GPU is allowed to draw. “We studied the effects of capping power and found that we could reduce energy consumption by about 12 percent to 15 percent, depending on the model,” Siddharth Samsi, a researcher within the LLSC, says.

    The trade-off for capping power is increasing task time — GPUs will take about 3 percent longer to complete a task, an increase Gadepally says is “barely noticeable” considering that models are often trained over days or even months. In one of their experiments in which they trained the popular BERT language model, limiting GPU power to 150 watts saw a two-hour increase in training time (from 80 to 82 hours) but saved the equivalent of a U.S. household’s week of energy.

    The team then built software that plugs this power-capping capability into the widely used scheduler system, Slurm. The software lets data center owners set limits across their system or on a job-by-job basis.

    “We can deploy this intervention today, and we’ve done so across all our systems,” Gadepally says.

    Side benefits have arisen, too. Since putting power constraints in place, the GPUs on LLSC supercomputers have been running about 30 degrees Fahrenheit cooler and at a more consistent temperature, reducing stress on the cooling system. Running the hardware cooler can potentially also increase reliability and service lifetime. They can now consider delaying the purchase of new hardware — reducing the center’s “embodied carbon,” or the emissions created through the manufacturing of equipment — until the efficiencies gained by using new hardware offset this aspect of the carbon footprint. They’re also finding ways to cut down on cooling needs by strategically scheduling jobs to run at night and during the winter months.

    “Data centers can use these easy-to-implement approaches today to increase efficiencies, without requiring modifications to code or infrastructure,” Gadepally says.

    Taking this holistic look at a data center’s operations to find opportunities to cut down can be time-intensive. To make this process easier for others, the team — in collaboration with Professor Devesh Tiwari and Baolin Li at Northeastern University — recently developed and published a comprehensive framework for analyzing the carbon footprint of high-performance computing systems. System practitioners can use this analysis framework to gain a better understanding of how sustainable their current system is and consider changes for next-generation systems.  

    Adjusting how models are trained and used

    On top of making adjustments to data center operations, the team is devising ways to make AI-model development more efficient.

    When training models, AI developers often focus on improving accuracy, and they build upon previous models as a starting point. To achieve the desired output, they have to figure out what parameters to use, and getting it right can take testing thousands of configurations. This process, called hyperparameter optimization, is one area LLSC researchers have found ripe for cutting down energy waste. 

    “We’ve developed a model that basically looks at the rate at which a given configuration is learning,” Gadepally says. Given that rate, their model predicts the likely performance. Underperforming models are stopped early. “We can give you a very accurate estimate early on that the best model will be in this top 10 of 100 models running,” he says.

    In their studies, this early stopping led to dramatic savings: an 80 percent reduction in the energy used for model training. They’ve applied this technique to models developed for computer vision, natural language processing, and material design applications.

    “In my opinion, this technique has the biggest potential for advancing the way AI models are trained,” Gadepally says.

    Training is just one part of an AI model’s emissions. The largest contributor to emissions over time is model inference, or the process of running the model live, like when a user chats with ChatGPT. To respond quickly, these models use redundant hardware, running all the time, waiting for a user to ask a question.

    One way to improve inference efficiency is to use the most appropriate hardware. Also with Northeastern University, the team created an optimizer that matches a model with the most carbon-efficient mix of hardware, such as high-power GPUs for the computationally intense parts of inference and low-power central processing units (CPUs) for the less-demanding aspects. This work recently won the best paper award at the International ACM Symposium on High-Performance Parallel and Distributed Computing.

    Using this optimizer can decrease energy use by 10-20 percent while still meeting the same “quality-of-service target” (how quickly the model can respond).

    This tool is especially helpful for cloud customers, who lease systems from data centers and must select hardware from among thousands of options. “Most customers overestimate what they need; they choose over-capable hardware just because they don’t know any better,” Gadepally says.

    Growing green-computing awareness

    The energy saved by implementing these interventions also reduces the associated costs of developing AI, often by a one-to-one ratio. In fact, cost is usually used as a proxy for energy consumption. Given these savings, why aren’t more data centers investing in green techniques?

    “I think it’s a bit of an incentive-misalignment problem,” Samsi says. “There’s been such a race to build bigger and better models that almost every secondary consideration has been put aside.”

    They point out that while some data centers buy renewable-energy credits, these renewables aren’t enough to cover the growing energy demands. The majority of electricity powering data centers comes from fossil fuels, and water used for cooling is contributing to stressed watersheds. 

    Hesitancy may also exist because systematic studies on energy-saving techniques haven’t been conducted. That’s why the team has been pushing their research in peer-reviewed venues in addition to open-source repositories. Some big industry players, like Google DeepMind, have applied machine learning to increase data center efficiency but have not made their work available for others to deploy or replicate. 

    Top AI conferences are now pushing for ethics statements that consider how AI could be misused. The team sees the climate aspect as an AI ethics topic that has not yet been given much attention, but this also appears to be slowly changing. Some researchers are now disclosing the carbon footprint of training the latest models, and industry is showing a shift in energy transparency too, as in this recent report from Meta AI.

    They also acknowledge that transparency is difficult without tools that can show AI developers their consumption. Reporting is on the LLSC roadmap for this year. They want to be able to show every LLSC user, for every job, how much energy they consume and how this amount compares to others, similar to home energy reports.

    Part of this effort requires working more closely with hardware manufacturers to make getting these data off hardware easier and more accurate. If manufacturers can standardize the way the data are read out, then energy-saving and reporting tools can be applied across different hardware platforms. A collaboration is underway between the LLSC researchers and Intel to work on this very problem.

    Even for AI developers who are aware of the intense energy needs of AI, they can’t do much on their own to curb this energy use. The LLSC team wants to help other data centers apply these interventions and provide users with energy-aware options. Their first partnership is with the U.S. Air Force, a sponsor of this research, which operates thousands of data centers. Applying these techniques can make a significant dent in their energy consumption and cost.

    “We’re putting control into the hands of AI developers who want to lessen their footprint,” Gadepally says. “Do I really need to gratuitously train unpromising models? Am I willing to run my GPUs slower to save energy? To our knowledge, no other supercomputing center is letting you consider these options. Using our tools, today, you get to decide.”

    Visit this webpage to see the group’s publications related to energy-aware computing and findings described in this article. More

  • in

    AI pilot programs look to reduce energy use and emissions on MIT campus

    Smart thermostats have changed the way many people heat and cool their homes by using machine learning to respond to occupancy patterns and preferences, resulting in a lower energy draw. This technology — which can collect and synthesize data — generally focuses on single-dwelling use, but what if this type of artificial intelligence could dynamically manage the heating and cooling of an entire campus? That’s the idea behind a cross-departmental effort working to reduce campus energy use through AI building controls that respond in real-time to internal and external factors. 

    Understanding the challenge

    Heating and cooling can be an energy challenge for campuses like MIT, where existing building management systems (BMS) can’t respond quickly to internal factors like occupancy fluctuations or external factors such as forecast weather or the carbon intensity of the grid. This results in using more energy than needed to heat and cool spaces, often to sub-optimal levels. By engaging AI, researchers have begun to establish a framework to understand and predict optimal temperature set points (the temperature at which a thermostat has been set to maintain) at the individual room level and take into consideration a host of factors, allowing the existing systems to heat and cool more efficiently, all without manual intervention. 

    “It’s not that different from what folks are doing in houses,” explains Les Norford, a professor of architecture at MIT, whose work in energy studies, controls, and ventilation connected him with the effort. “Except we have to think about things like how long a classroom may be used in a day, weather predictions, time needed to heat and cool a room, the effect of the heat from the sun coming in the window, and how the classroom next door might impact all of this.” These factors are at the crux of the research and pilots that Norford and a team are focused on. That team includes Jeremy Gregory, executive director of the MIT Climate and Sustainability Consortium; Audun Botterud, principal research scientist for the Laboratory for Information and Decision Systems; Steve Lanou, project manager in the MIT Office of Sustainability (MITOS); Fran Selvaggio, Department of Facilities Senior Building Management Systems engineer; and Daisy Green and You Lin, both postdocs.

    The group is organized around the call to action to “explore possibilities to employ artificial intelligence to reduce on-campus energy consumption” outlined in Fast Forward: MIT’s Climate Action Plan for the Decade, but efforts extend back to 2019. “As we work to decarbonize our campus, we’re exploring all avenues,” says Vice President for Campus Services and Stewardship Joe Higgins, who originally pitched the idea to students at the 2019 MIT Energy Hack. “To me, it was a great opportunity to utilize MIT expertise and see how we can apply it to our campus and share what we learn with the building industry.” Research into the concept kicked off at the event and continued with undergraduate and graduate student researchers running differential equations and managing pilots to test the bounds of the idea. Soon, Gregory, who is also a MITOS faculty fellow, joined the project and helped identify other individuals to join the team. “My role as a faculty fellow is to find opportunities to connect the research community at MIT with challenges MIT itself is facing — so this was a perfect fit for that,” Gregory says. 

    Early pilots of the project focused on testing thermostat set points in NW23, home to the Department of Facilities and Office of Campus Planning, but Norford quickly realized that classrooms provide many more variables to test, and the pilot was expanded to Building 66, a mixed-use building that is home to classrooms, offices, and lab spaces. “We shifted our attention to study classrooms in part because of their complexity, but also the sheer scale — there are hundreds of them on campus, so [they offer] more opportunities to gather data and determine parameters of what we are testing,” says Norford. 

    Developing the technology

    The work to develop smarter building controls starts with a physics-based model using differential equations to understand how objects can heat up or cool down, store heat, and how the heat may flow across a building façade. External data like weather, carbon intensity of the power grid, and classroom schedules are also inputs, with the AI responding to these conditions to deliver an optimal thermostat set point each hour — one that provides the best trade-off between the two objectives of thermal comfort of occupants and energy use. That set point then tells the existing BMS how much to heat up or cool down a space. Real-life testing follows, surveying building occupants about their comfort. Botterud, whose research focuses on the interactions between engineering, economics, and policy in electricity markets, works to ensure that the AI algorithms can then translate this learning into energy and carbon emission savings. 

    Currently the pilots are focused on six classrooms within Building 66, with the intent to move onto lab spaces before expanding to the entire building. “The goal here is energy savings, but that’s not something we can fully assess until we complete a whole building,” explains Norford. “We have to work classroom by classroom to gather the data, but are looking at a much bigger picture.” The research team used its data-driven simulations to estimate significant energy savings while maintaining thermal comfort in the six classrooms over two days, but further work is needed to implement the controls and measure savings across an entire year. 

    With significant savings estimated across individual classrooms, the energy savings derived from an entire building could be substantial, and AI can help meet that goal, explains Botterud: “This whole concept of scalability is really at the heart of what we are doing. We’re spending a lot of time in Building 66 to figure out how it works and hoping that these algorithms can be scaled up with much less effort to other rooms and buildings so solutions we are developing can make a big impact at MIT,” he says.

    Part of that big impact involves operational staff, like Selvaggio, who are essential in connecting the research to current operations and putting them into practice across campus. “Much of the BMS team’s work is done in the pilot stage for a project like this,” he says. “We were able to get these AI systems up and running with our existing BMS within a matter of weeks, allowing the pilots to get off the ground quickly.” Selvaggio says in preparation for the completion of the pilots, the BMS team has identified an additional 50 buildings on campus where the technology can easily be installed in the future to start energy savings. The BMS team also collaborates with the building automation company, Schneider Electric, that has implemented the new control algorithms in Building 66 classrooms and is ready to expand to new pilot locations. 

    Expanding impact

    The successful completion of these programs will also open the possibility for even greater energy savings — bringing MIT closer to its decarbonization goals. “Beyond just energy savings, we can eventually turn our campus buildings into a virtual energy network, where thousands of thermostats are aggregated and coordinated to function as a unified virtual entity,” explains Higgins. These types of energy networks can accelerate power sector decarbonization by decreasing the need for carbon-intensive power plants at peak times and allowing for more efficient power grid energy use.

    As pilots continue, they fulfill another call to action in Fast Forward — for campus to be a “test bed for change.” Says Gregory: “This project is a great example of using our campus as a test bed — it brings in cutting-edge research to apply to decarbonizing our own campus. It’s a great project for its specific focus, but also for serving as a model for how to utilize the campus as a living lab.” More

  • in

    Jackson Jewett wants to design buildings that use less concrete

    After three years leading biking tours through U.S. National Parks, Jackson Jewett decided it was time for a change.

    “It was a lot of fun, but I realized I missed buildings,” says Jewett. “I really wanted to be a part of that industry, learn more about it, and reconnect with my roots in the built environment.”

    Jewett grew up in California in what he describes as a “very creative household.”

    “I remember making very elaborate Halloween costumes with my parents, making fun dioramas for school projects, and building forts in the backyard, that kind of thing,” Jewett explains.

    Both of his parents have backgrounds in design; his mother studied art in college and his father is a practicing architect. From a young age, Jewett was interested in following in his father’s footsteps. But when he arrived at the University of California at Berkeley in the midst of the 2009 housing crash, it didn’t seem like the right time. Jewett graduated with a degree in cognitive science and a minor in history of architecture. And even as he led tours through Yellowstone, the Grand Canyon, and other parks, buildings were in the back of his mind.

    It wasn’t just the built environment that Jewett was missing. He also longed for the rigor and structure of an academic environment.

    Jewett arrived at MIT in 2017, initially only planning on completing the master’s program in civil and environmental engineering. It was then that he first met Josephine Carstensen, a newly hired lecturer in the department. Jewett was interested in Carstensen’s work on “topology optimization,” which uses algorithms to design structures that can achieve their performance requirements while using only a limited amount of material. He was particularly interested in applying this approach to concrete design, and he collaborated with Carstensen to help demonstrate its viability.

    After earning his master’s, Jewett spent a year and a half as a structural engineer in New York City. But when Carstensen was hired as a professor, she reached out to Jewett about joining her lab as a PhD student. He was ready for another change.

    Now in the third year of his PhD program, Jewett’s dissertation work builds upon his master’s thesis to further refine algorithms that can design building-scale concrete structures that use less material, which would help lower carbon emissions from the construction industry. It is estimated that the concrete industry alone is responsible for 8 percent of global carbon emissions, so any efforts to reduce that number could help in the fight against climate change.

    Implementing new ideas

    Topology optimization is a small field, with the bulk of the prior work being computational without any experimental verification. The work Jewett completed for his master’s thesis was just the start of a long learning process.

    “I do feel like I’m just getting to the part where I can start implementing my own ideas without as much support as I’ve needed in the past,” says Jewett. “In the last couple of months, I’ve been working on a reinforced concrete optimization algorithm that I hope will be the cornerstone of my thesis.”

    The process of fine-tuning a generative algorithm is slow going, particularly when tackling a multifaceted problem.

    “It can take days or usually weeks to take a step toward making it work as an entire integrated system,” says Jewett. “The days when that breakthrough happens and I can see the algorithm converging on a solution that makes sense — those are really exciting moments.”

    By harnessing computational power, Jewett is searching for materially efficient components that can be used to make up structures such as bridges or buildings. These are other constraints to consider as well, particularly ensuring that the cost of manufacturing isn’t too high. Having worked in the industry before starting the PhD program, Jewett has an eye toward doing work that can be feasibly implemented.

    Inspiring others

    When Jewett first visited MIT campus, he was drawn in by the collaborative environment of the institute and the students’ drive to learn. Now, he’s a part of that process as a teaching assistant and a supervisor in the Undergraduate Research Opportunities Program.  

    Working as a teaching assistant isn’t a requirement for Jewett’s program, but it’s been one of his favorite parts of his time at MIT.

    “The MIT undergrads are so gifted and just constantly impress me,” says Jewett. “Being able to teach, especially in the context of what MIT values is a lot of fun. And I learn, too. My coding practices have gotten so much better since working with undergrads here.”

    Jewett’s experiences have inspired him to pursue a career in academia after the completion of his program, which he expects to complete in the spring of 2025. But he’s making sure to take care of himself along the way. He still finds time to plan cycling trips with his friends and has gotten into running ever since moving to Boston. So far, he’s completed two marathons.

    “It’s so inspiring to be in a place where so many good ideas are just bouncing back and forth all over campus,” says Jewett. “And on most days, I remember that and it inspires me. But it’s also the case that academics is hard, PhD programs are hard, and MIT — there’s pressure being here, and sometimes that pressure can feel like it’s working against you.”

    Jewett is grateful for the mental health resources that MIT provides students. While he says it can be imperfect, it’s been a crucial part of his journey.

    “My PhD thesis will be done in 2025, but the work won’t be done. The time horizon of when these things need to be implemented is relatively short if we want to make an impact before global temperatures have already risen too high. My PhD research will be developing a framework for how that could be done with concrete construction, but I’d like to keep thinking about other materials and construction methods even after this project is finished.” More

  • in

    Technologies for water conservation and treatment move closer to commercialization

    The Abdul Latif Jameel Water and Food Systems Lab (J-WAFS) provides Solutions Grants to help MIT researchers launch startup companies or products to commercialize breakthrough technologies in water and food systems. The Solutions Grant Program began in 2015 and is supported by Community Jameel. In addition to one-year, renewable grants of up to $150,000, the program also matches grantees with industry mentors and facilitates introductions to potential investors. Since its inception, the J-WAFS Solutions Program has awarded over $3 million in funding to the MIT community. Numerous startups and products, including a portable desalination device and a company commercializing a novel food safety sensor, have spun out of this support.

    The 2023 J-WAFS Solutions Grantees are Professor C. Cem Tasan of the Department of Materials Science and Engineering and Professor Andrew Whittle of the Department of Civil and Environmental Engineering. Tasan’s project involves reducing water use in steel manufacturing and Whittle’s project tackles harmful algal blooms in water. Project work commences this September.

    “This year’s Solutions Grants are being award to professors Tasan and Whittle to help commercialize technologies they have been developing at MIT,” says J-WAFS executive director Renee J. Robins. “With J-WAFS’ support, we hope to see the teams move their technologies from the lab to the market, so they can have a beneficial impact on water use and water quality challenges,” Robins adds.

    Reducing water consumption by solid-state steelmaking

    Water is a major requirement for steel production. The steel industry ranks fourth in industrial freshwater consumption worldwide, since large amounts of water are needed mainly for cooling purposes in the process. Unfortunately, a strong correlation has also been shown to exist between freshwater use in steelmaking and water contamination. As the global demand for steel increases and freshwater availability decreases due to climate change, improved methods for more sustainable steel production are needed.

    A strategy to reduce the water footprint of steelmaking is to explore steel recycling processes that avoid liquid metal processing. With this motivation, Cem Tasan, the Thomas B. King Associate Professor of Metallurgy in the Department of Materials Science and Engineering, and postdoc Onur Guvenc PhD created a new process called Scrap Metal Consolidation (SMC). SMC is based on a well-established metal forming process known as roll bonding. Conventionally, roll bonding requires intensive prior surface treatment of the raw material, specific atmospheric conditions, and high deformation levels. Tasan and Guvenc’s research revealed that SMC can overcome these restrictions by enabling the solid-state bonding of scrap into a sheet metal form, even when the surface quality, atmospheric conditions, and deformation levels are suboptimal. Through lab-scale proof-of-principle investigations, they have already identified SMC process conditions and validated the mechanical formability of resulting steel sheets, focusing on mild steel, the most common sheet metal scrap.

    The J-WAFS Solutions Grant will help the team to build customer product prototypes, design the processing unit, and develop a scale-up strategy and business model. By simultaneously decreasing water usage, energy demand, contamination risk, and carbon dioxide burden, SMC has the potential to decrease the energy need for steel recycling by up to 86 percent, as well as reduce the linked carbon dioxide emissions and safeguard the freshwater resources that would otherwise be directed to industrial consumption. 

    Detecting harmful algal blooms in water before it’s too late

    Harmful algal blooms (HABs) are a growing problem in both freshwater and saltwater environments worldwide, causing an estimated $13 billion in annual damage to drinking water, water for recreational use, commercial fishing areas, and desalination activities. HABs pose a threat to both human health and aquaculture, thereby threatening the food supply. Toxins in HABs are produced by some cyanobacteria, or blue-green algae, whose communities change in composition in response to eutrophication from agricultural runoff, sewer overflows, or other events. Mitigation of risks from HABs are most effective when there is advance warning of these changes in algal communities. 

    Most in situ measurements of algae are based on fluorescence spectroscopy that is conducted with LED-induced fluorescence (LEDIF) devices, or probes that induce fluorescence of specific algal pigments using LED light sources. While LEDIFs provide reasonable estimates of concentrations of individual pigments, they lack resolution to discriminate algal classes within complex mixtures found in natural water bodies. In prior research, Andrew Whittle, the Edmund K. Turner Professor of Civil and Environmental Engineering, worked with colleagues to design REMORA, a low-cost, field-deployable prototype spectrofluorometer for measuring induced fluorescence. This research was part of a collaboration between MIT and the AMS Institute. Whittle and the team successfully trained a machine learning model to discriminate and quantify cell concentrations for mixtures of different algal groups in water samples through an extensive laboratory calibration program using various algae cultures. The group demonstrated these capabilities in a series of field measurements at locations in Boston and Amsterdam. 

    Whittle will work with Fábio Duarte of the Department of Urban Studies and Planning, the Senseable City Lab, and MIT’s Center for Real Estate to refine the design of REMORA. They will develop software for autonomous operation of the sensor that can be deployed remotely on mobile vessels or platforms to enable high-resolution spatiotemporal monitoring for harmful algae. Sensor commercialization will hopefully be able to exploit the unique capabilities of REMORA for long-term monitoring applications by water utilities, environmental regulatory agencies, and water-intensive industries.  More

  • in

    Fast-tracking fusion energy’s arrival with AI and accessibility

    As the impacts of climate change continue to grow, so does interest in fusion’s potential as a clean energy source. While fusion reactions have been studied in laboratories since the 1930s, there are still many critical questions scientists must answer to make fusion power a reality, and time is of the essence. As part of their strategy to accelerate fusion energy’s arrival and reach carbon neutrality by 2050, the U.S. Department of Energy (DoE) has announced new funding for a project led by researchers at MIT’s Plasma Science and Fusion Center (PSFC) and four collaborating institutions.

    Cristina Rea, a research scientist and group leader at the PSFC, will serve as the primary investigator for the newly funded three-year collaboration to pilot the integration of fusion data into a system that can be read by AI-powered tools. The PSFC, together with scientists from the College of William and Mary, the University of Wisconsin at Madison, Auburn University, and the nonprofit HDF Group, plan to create a holistic fusion data platform, the elements of which could offer unprecedented access for researchers, especially underrepresented students. The project aims to encourage diverse participation in fusion and data science, both in academia and the workforce, through outreach programs led by the group’s co-investigators, of whom four out of five are women. 

    The DoE’s award, part of a $29 million funding package for seven projects across 19 institutions, will support the group’s efforts to distribute data produced by fusion devices like the PSFC’s Alcator C-Mod, a donut-shaped “tokamak” that utilized powerful magnets to control and confine fusion reactions. Alcator C-Mod operated from 1991 to 2016 and its data are still being studied, thanks in part to the PSFC’s commitment to the free exchange of knowledge.

    Currently, there are nearly 50 public experimental magnetic confinement-type fusion devices; however, both historical and current data from these devices can be difficult to access. Some fusion databases require signing user agreements, and not all data are catalogued and organized the same way. Moreover, it can be difficult to leverage machine learning, a class of AI tools, for data analysis and to enable scientific discovery without time-consuming data reorganization. The result is fewer scientists working on fusion, greater barriers to discovery, and a bottleneck in harnessing AI to accelerate progress.

    The project’s proposed data platform addresses technical barriers by being FAIR — Findable, Interoperable, Accessible, Reusable — and by adhering to UNESCO’s Open Science (OS) recommendations to improve the transparency and inclusivity of science; all of the researchers’ deliverables will adhere to FAIR and OS principles, as required by the DoE. The platform’s databases will be built using MDSplusML, an upgraded version of the MDSplus open-source software developed by PSFC researchers in the 1980s to catalogue the results of Alcator C-Mod’s experiments. Today, nearly 40 fusion research institutes use MDSplus to store and provide external access to their fusion data. The release of MDSplusML aims to continue that legacy of open collaboration.

    The researchers intend to address barriers to participation for women and disadvantaged groups not only by improving general access to fusion data, but also through a subsidized summer school that will focus on topics at the intersection of fusion and machine learning, which will be held at William and Mary for the next three years.

    Of the importance of their research, Rea says, “This project is about responding to the fusion community’s needs and setting ourselves up for success. Scientific advancements in fusion are enabled via multidisciplinary collaboration and cross-pollination, so accessibility is absolutely essential. I think we all understand now that diverse communities have more diverse ideas, and they allow faster problem-solving.”

    The collaboration’s work also aligns with vital areas of research identified in the International Atomic Energy Agency’s “AI for Fusion” Coordinated Research Project (CRP). Rea was selected as the technical coordinator for the IAEA’s CRP emphasizing community engagement and knowledge access to accelerate fusion research and development. In a letter of support written for the group’s proposed project, the IAEA stated that, “the work [the researchers] will carry out […] will be beneficial not only to our CRP but also to the international fusion community in large.”

    PSFC Director and Hitachi America Professor of Engineering Dennis Whyte adds, “I am thrilled to see PSFC and our collaborators be at the forefront of applying new AI tools while simultaneously encouraging and enabling extraction of critical data from our experiments.”

    “Having the opportunity to lead such an important project is extremely meaningful, and I feel a responsibility to show that women are leaders in STEM,” says Rea. “We have an incredible team, strongly motivated to improve our fusion ecosystem and to contribute to making fusion energy a reality.” More

  • in

    The curse of variety in transportation systems

    Cathy Wu has always delighted in systems that run smoothly. In high school, she designed a project to optimize the best route for getting to class on time. Her research interests and career track are evidence of a propensity for organizing and optimizing, coupled with a strong sense of responsibility to contribute to society instilled by her parents at a young age.

    As an undergraduate at MIT, Wu explored domains like agriculture, energy, and education, eventually homing in on transportation. “Transportation touches each of our lives,” she says. “Every day, we experience the inefficiencies and safety issues as well as the environmental harms associated with our transportation systems. I believe we can and should do better.”

    But doing so is complicated. Consider the long-standing issue of traffic systems control. Wu explains that it is not one problem, but more accurately a family of control problems impacted by variables like time of day, weather, and vehicle type — not to mention the types of sensing and communication technologies used to measure roadway information. Every differentiating factor introduces an exponentially larger set of control problems. There are thousands of control-problem variations and hundreds, if not thousands, of studies and papers dedicated to each problem. Wu refers to the sheer number of variations as the curse of variety — and it is hindering innovation.

    Play video

    “To prove that a new control strategy can be safely deployed on our streets can take years. As time lags, we lose opportunities to improve safety and equity while mitigating environmental impacts. Accelerating this process has huge potential,” says Wu.  

    Which is why she and her group in the MIT Laboratory for Information and Decision Systems are devising machine learning-based methods to solve not just a single control problem or a single optimization problem, but families of control and optimization problems at scale. “In our case, we’re examining emerging transportation problems that people have spent decades trying to solve with classical approaches. It seems to me that we need a different approach.”

    Optimizing intersections

    Currently, Wu’s largest research endeavor is called Project Greenwave. There are many sectors that directly contribute to climate change, but transportation is responsible for the largest share of greenhouse gas emissions — 29 percent, of which 81 percent is due to land transportation. And while much of the conversation around mitigating environmental impacts related to mobility is focused on electric vehicles (EVs), electrification has its drawbacks. EV fleet turnover is time-consuming (“on the order of decades,” says Wu), and limited global access to the technology presents a significant barrier to widespread adoption.

    Wu’s research, on the other hand, addresses traffic control problems by leveraging deep reinforcement learning. Specifically, she is looking at traffic intersections — and for good reason. In the United States alone, there are more than 300,000 signalized intersections where vehicles must stop or slow down before re-accelerating. And every re-acceleration burns fossil fuels and contributes to greenhouse gas emissions.

    Highlighting the magnitude of the issue, Wu says, “We have done preliminary analysis indicating that up to 15 percent of land transportation CO2 is wasted through energy spent idling and re-accelerating at intersections.”

    To date, she and her group have modeled 30,000 different intersections across 10 major metropolitan areas in the United States. That is 30,000 different configurations, roadway topologies (e.g., grade of road or elevation), different weather conditions, and variations in travel demand and fuel mix. Each intersection and its corresponding scenarios represents a unique multi-agent control problem.

    Wu and her team are devising techniques that can solve not just one, but a whole family of problems comprised of tens of thousands of scenarios. Put simply, the idea is to coordinate the timing of vehicles so they arrive at intersections when traffic lights are green, thereby eliminating the start, stop, re-accelerate conundrum. Along the way, they are building an ecosystem of tools, datasets, and methods to enable roadway interventions and impact assessments of strategies to significantly reduce carbon-intense urban driving.

    Play video

    Their collaborator on the project is the Utah Department of Transportation, which Wu says has played an essential role, in part by sharing data and practical knowledge that she and her group otherwise would not have been able to access publicly.

    “I appreciate industry and public sector collaborations,” says Wu. “When it comes to important societal problems, one really needs grounding with practitioners. One needs to be able to hear the perspectives in the field. My interactions with practitioners expand my horizons and help ground my research. You never know when you’ll hear the perspective that is the key to the solution, or perhaps the key to understanding the problem.”

    Finding the best routes

    In a similar vein, she and her research group are tackling large coordination problems. For example, vehicle routing. “Every day, delivery trucks route more than a hundred thousand packages for the city of Boston alone,” says Wu. Accomplishing the task requires, among other things, figuring out which trucks to use, which packages to deliver, and the order in which to deliver them as efficiently as possible. If and when the trucks are electrified, they will need to be charged, adding another wrinkle to the process and further complicating route optimization.

    The vehicle routing problem, and therefore the scope of Wu’s work, extends beyond truck routing for package delivery. Ride-hailing cars may need to pick up objects as well as drop them off; and what if delivery is done by bicycle or drone? In partnership with Amazon, for example, Wu and her team addressed routing and path planning for hundreds of robots (up to 800) in their warehouses.

    Every variation requires custom heuristics that are expensive and time-consuming to develop. Again, this is really a family of problems — each one complicated, time-consuming, and currently unsolved by classical techniques — and they are all variations of a central routing problem. The curse of variety meets operations and logistics.

    By combining classical approaches with modern deep-learning methods, Wu is looking for a way to automatically identify heuristics that can effectively solve all of these vehicle routing problems. So far, her approach has proved successful.

    “We’ve contributed hybrid learning approaches that take existing solution methods for small problems and incorporate them into our learning framework to scale and accelerate that existing solver for large problems. And we’re able to do this in a way that can automatically identify heuristics for specialized variations of the vehicle routing problem.” The next step, says Wu, is applying a similar approach to multi-agent robotics problems in automated warehouses.

    Wu and her group are making big strides, in part due to their dedication to use-inspired basic research. Rather than applying known methods or science to a problem, they develop new methods, new science, to address problems. The methods she and her team employ are necessitated by societal problems with practical implications. The inspiration for the approach? None other than Louis Pasteur, who described his research style in a now-famous article titled “Pasteur’s Quadrant.” Anthrax was decimating the sheep population, and Pasteur wanted to better understand why and what could be done about it. The tools of the time could not solve the problem, so he invented a new field, microbiology, not out of curiosity but out of necessity. More