More stories

  • in

    Physics and the machine-learning “black box”

    Machine-learning algorithms are often referred to as a “black box.” Once data are put into an algorithm, it’s not always known exactly how the algorithm arrives at its prediction. This can be particularly frustrating when things go wrong. A new mechanical engineering (MechE) course at MIT teaches students how to tackle the “black box” problem, through a combination of data science and physics-based engineering.

    In class 2.C161 (Physical Systems Modeling and Design Using Machine Learning), Professor George Barbastathis demonstrates how mechanical engineers can use their unique knowledge of physical systems to keep algorithms in check and develop more accurate predictions.

    “I wanted to take 2.C161 because machine-learning models are usually a “black box,” but this class taught us how to construct a system model that is informed by physics so we can peek inside,” explains Crystal Owens, a mechanical engineering graduate student who took the course in spring 2021.

    As chair of the Committee on the Strategic Integration of Data Science into Mechanical Engineering, Barbastathis has had many conversations with mechanical engineering students, researchers, and faculty to better understand the challenges and successes they’ve had using machine learning in their work.

    “One comment we heard frequently was that these colleagues can see the value of data science methods for problems they are facing in their mechanical engineering-centric research; yet they are lacking the tools to make the most out of it,” says Barbastathis. “Mechanical, civil, electrical, and other types of engineers want a fundamental understanding of data principles without having to convert themselves to being full-time data scientists or AI researchers.”

    Additionally, as mechanical engineering students move on from MIT to their careers, many will need to manage data scientists on their teams someday. Barbastathis hopes to set these students up for success with class 2.C161.

    Bridging MechE and the MIT Schwartzman College of Computing

    Class 2.C161 is part of the MIT Schwartzman College of Computing “Computing Core.” The goal of these classes is to connect data science and physics-based engineering disciplines, like mechanical engineering. Students take the course alongside 6.C402 (Modeling with Machine Learning: from Algorithms to Applications), taught by professors of electrical engineering and computer science Regina Barzilay and Tommi Jaakkola.

    The two classes are taught concurrently during the semester, exposing students to both fundamentals in machine learning and domain-specific applications in mechanical engineering.

    In 2.C161, Barbastathis highlights how complementary physics-based engineering and data science are. Physical laws present a number of ambiguities and unknowns, ranging from temperature and humidity to electromagnetic forces. Data science can be used to predict these physical phenomena. Meanwhile, having an understanding of physical systems helps ensure the resulting output of an algorithm is accurate and explainable.

    “What’s needed is a deeper combined understanding of the associated physical phenomena and the principles of data science, machine learning in particular, to close the gap,” adds Barbastathis. “By combining data with physical principles, the new revolution in physics-based engineering is relatively immune to the “black box” problem facing other types of machine learning.”

    Equipped with a working knowledge of machine-learning topics covered in class 6.C402 and a deeper understanding of how to pair data science with physics, students are charged with developing a final project that solves for an actual physical system.

    Developing solutions for real-world physical systems

    For their final project, students in 2.C161 are asked to identify a real-world problem that requires data science to address the ambiguity inherent in physical systems. After obtaining all relevant data, students are asked to select a machine-learning method, implement their chosen solution, and present and critique the results.

    Topics this past semester ranged from weather forecasting to the flow of gas in combustion engines, with two student teams drawing inspiration from the ongoing Covid-19 pandemic.

    Owens and her teammates, fellow graduate students Arun Krishnadas and Joshua David John Rathinaraj, set out to develop a model for the Covid-19 vaccine rollout.

    “We developed a method of combining a neural network with a susceptible-infected-recovered (SIR) epidemiological model to create a physics-informed prediction system for the spread of Covid-19 after vaccinations started,” explains Owens.

    The team accounted for various unknowns including population mobility, weather, and political climate. This combined approach resulted in a prediction of Covid-19’s spread during the vaccine rollout that was more reliable than using either the SIR model or a neural network alone.

    Another team, including graduate student Yiwen Hu, developed a model to predict mutation rates in Covid-19, a topic that became all too pertinent as the delta variant began its global spread.

    “We used machine learning to predict the time-series-based mutation rate of Covid-19, and then incorporated that as an independent parameter into the prediction of pandemic dynamics to see if it could help us better predict the trend of the Covid-19 pandemic,” says Hu.

    Hu, who had previously conducted research into how vibrations on coronavirus protein spikes affect infection rates, hopes to apply the physics-based machine-learning approaches he learned in 2.C161 to his research on de novo protein design.

    Whatever the physical system students addressed in their final projects, Barbastathis was careful to stress one unifying goal: the need to assess ethical implications in data science. While more traditional computing methods like face or voice recognition have proven to be rife with ethical issues, there is an opportunity to combine physical systems with machine learning in a fair, ethical way.

    “We must ensure that collection and use of data are carried out equitably and inclusively, respecting the diversity in our society and avoiding well-known problems that computer scientists in the past have run into,” says Barbastathis.

    Barbastathis hopes that by encouraging mechanical engineering students to be both ethics-literate and well-versed in data science, they can move on to develop reliable, ethically sound solutions and predictions for physical-based engineering challenges. More

  • in

    Tackling hard computational problems

    The notion that some computational problems in math and computer science can be hard should come as no surprise. There is, in fact, an entire class of problems deemed impossible to solve algorithmically. Just below this class lie slightly “easier” problems that are less well-understood — and may be impossible, too.

    David Gamarnik, professor of operations research at the MIT Sloan School of Management and the Institute for Data, Systems, and Society, is focusing his attention on the latter, less-studied category of problems, which are more relevant to the everyday world because they involve randomness — an integral feature of natural systems. He and his colleagues have developed a potent tool for analyzing these problems called the overlap gap property (or OGP). Gamarnik described the new methodology in a recent paper in the Proceedings of the National Academy of Sciences.

    P ≠ NP

    Fifty years ago, the most famous problem in theoretical computer science was formulated. Labeled “P ≠ NP,” it asks if problems involving vast datasets exist for which an answer can be verified relatively quickly, but whose solution — even if worked out on the fastest available computers — would take an absurdly long time.

    The P ≠ NP conjecture is still unproven, yet most computer scientists believe that many familiar problems — including, for instance, the traveling salesman problem — fall into this impossibly hard category. The challenge in the salesman example is to find the shortest route, in terms of distance or time, through N different cities. The task is easily managed when N=4, because there are only six possible routes to consider. But for 30 cities, there are more than 1030 possible routes, and the numbers rise dramatically from there. The biggest difficulty comes in designing an algorithm that quickly solves the problem in all cases, for all integer values of N. Computer scientists are confident, based on algorithmic complexity theory, that no such algorithm exists, thus affirming that P ≠ NP.

    There are many other examples of intractable problems like this. Suppose, for instance, you have a giant table of numbers with thousands of rows and thousands of columns. Can you find, among all possible combinations, the precise arrangement of 10 rows and 10 columns such that its 100 entries will have the highest sum attainable? “We call them optimization tasks,” Gamarnik says, “because you’re always trying to find the biggest or best — the biggest sum of numbers, the best route through cities, and so forth.”

    Computer scientists have long recognized that you can’t create a fast algorithm that can, in all cases, efficiently solve problems like the saga of the traveling salesman. “Such a thing is likely impossible for reasons that are well-understood,” Gamarnik notes. “But in real life, nature doesn’t generate problems from an adversarial perspective. It’s not trying to thwart you with the most challenging, hand-picked problem conceivable.” In fact, people normally encounter problems under more random, less contrived circumstances, and those are the problems the OGP is intended to address.

    Peaks and valleys

    To understand what the OGP is all about, it might first be instructive to see how the idea arose. Since the 1970s, physicists have been studying spin glasses — materials with properties of both liquids and solids that have unusual magnetic behaviors. Research into spin glasses has given rise to a general theory of complex systems that’s relevant to problems in physics, math, computer science, materials science, and other fields. (This work earned Giorgio Parisi a 2021 Nobel Prize in Physics.)

    One vexing issue physicists have wrestled with is trying to predict the energy states, and particularly the lowest energy configurations, of different spin glass structures. The situation is sometimes depicted by a “landscape” of countless mountain peaks separated by valleys, where the goal is to identify the highest peak. In this case, the highest peak actually represents the lowest energy state (though one could flip the picture around and instead look for the deepest hole). This turns out to be an optimization problem similar in form to the traveling salesman’s dilemma, Gamarnik explains: “You’ve got this huge collection of mountains, and the only way to find the highest appears to be by climbing up each one” — a Sisyphean chore comparable to finding a needle in a haystack.

    Physicists have shown that you can simplify this picture, and take a step toward a solution, by slicing the mountains at a certain, predetermined elevation and ignoring everything below that cutoff level. You’d then be left with a collection of peaks protruding above a uniform layer of clouds, with each point on those peaks representing a potential solution to the original problem.

    In a 2014 paper, Gamarnik and his coauthors noticed something that had previously been overlooked. In some cases, they realized, the diameter of each peak will be much smaller than the distances between different peaks. Consequently, if one were to pick any two points on this sprawling landscape — any two possible “solutions” — they would either be very close (if they came from the same peak) or very far apart (if drawn from different peaks). In other words, there would be a telltale “gap” in these distances — either small or large, but nothing in-between. A system in this state, Gamarnik and colleagues proposed, is characterized by the OGP.

    “We discovered that all known problems of a random nature that are algorithmically hard have a version of this property” — namely, that the mountain diameter in the schematic model is much smaller than the space between mountains, Gamarnik asserts. “This provides a more precise measure of algorithmic hardness.”

    Unlocking the secrets of algorithmic complexity

    The emergence of the OGP can help researchers assess the difficulty of creating fast algorithms to tackle particular problems. And it has already enabled them “to mathematically [and] rigorously rule out a large class of algorithms as potential contenders,” Gamarnik says. “We’ve learned, specifically, that stable algorithms — those whose output won’t change much if the input only changes a little — will fail at solving this type of optimization problem.” This negative result applies not only to conventional computers but also to quantum computers and, specifically, to so-called “quantum approximation optimization algorithms” (QAOAs), which some investigators had hoped could solve these same optimization problems. Now, owing to Gamarnik and his co-authors’ findings, those hopes have been moderated by the recognition that many layers of operations would be required for QAOA-type algorithms to succeed, which could be technically challenging.

    “Whether that’s good news or bad news depends on your perspective,” he says. “I think it’s good news in the sense that it helps us unlock the secrets of algorithmic complexity and enhances our knowledge as to what is in the realm of possibility and what is not. It’s bad news in the sense that it tells us that these problems are hard, even if nature produces them, and even if they’re generated in a random way.” The news is not really surprising, he adds. “Many of us expected it all along, but we now we have a more solid basis upon which to make this claim.”

    That still leaves researchers light-years away from being able to prove the nonexistence of fast algorithms that could solve these optimization problems in random settings. Having such a proof would provide a definitive answer to the P ≠ NP problem. “If we could show that we can’t have an algorithm that works most of the time,” he says, “that would tell us we certainly can’t have an algorithm that works all the time.”

    Predicting how long it will take before the P ≠ NP problem is resolved appears to be an intractable problem in itself. It’s likely there will be many more peaks to climb, and valleys to traverse, before researchers gain a clearer perspective on the situation. More

  • in

    Understanding air pollution from space

    Climate change and air pollution are interlocking crises that threaten human health. Reducing emissions of some air pollutants can help achieve climate goals, and some climate mitigation efforts can in turn improve air quality.

    One part of MIT Professor Arlene Fiore’s research program is to investigate the fundamental science in understanding air pollutants — how long they persist and move through our environment to affect air quality.

    “We need to understand the conditions under which pollutants, such as ozone, form. How much ozone is formed locally and how much is transported long distances?” says Fiore, who notes that Asian air pollution can be transported across the Pacific Ocean to North America. “We need to think about processes spanning local to global dimensions.”

    Fiore, the Peter H. Stone and Paola Malanotte Stone Professor in Earth, Atmospheric and Planetary Sciences, analyzes data from on-the-ground readings and from satellites, along with models, to better understand the chemistry and behavior of air pollutants — which ultimately can inform mitigation strategies and policy setting.

    A global concern

    At the United Nations’ most recent climate change conference, COP26, air quality management was a topic discussed over two days of presentations.

    “Breathing is vital. It’s life. But for the vast majority of people on this planet right now, the air that they breathe is not giving life, but cutting it short,” said Sarah Vogel, senior vice president for health at the Environmental Defense Fund, at the COP26 session.

    “We need to confront this twin challenge now through both a climate and clean air lens, of targeting those pollutants that warm both the air and harm our health.”

    Earlier this year, the World Health Organization (WHO) updated its global air quality guidelines it had issued 15 years earlier for six key pollutants including ozone (O3), nitrogen dioxide (NO2), sulfur dioxide (SO2), and carbon monoxide (CO). The new guidelines are more stringent based on what the WHO stated is the “quality and quantity of evidence” of how these pollutants affect human health. WHO estimates that roughly 7 million premature deaths are attributable to the joint effects of air pollution.

    “We’ve had all these health-motivated reductions of aerosol and ozone precursor emissions. What are the implications for the climate system, both locally but also around the globe? How does air quality respond to climate change? We study these two-way interactions between air pollution and the climate system,” says Fiore.

    But fundamental science is still required to understand how gases, such as ozone and nitrogen dioxide, linger and move throughout the troposphere — the lowermost layer of our atmosphere, containing the air we breathe.

    “We care about ozone in the air we’re breathing where we live at the Earth’s surface,” says Fiore. “Ozone reacts with biological tissue, and can be damaging to plants and human lungs. Even if you’re a healthy adult, if you’re out running hard during an ozone smog event, you might feel an extra weight on your lungs.”

    Telltale signs from space

    Ozone is not emitted directly, but instead forms through chemical reactions catalyzed by radiation from the sun interacting with nitrogen oxides — pollutants released in large part from burning fossil fuels—and volatile organic compounds. However, current satellite instruments cannot sense ground-level ozone.

    “We can’t retrieve surface- or even near-surface ozone from space,” says Fiore of the satellite data, “although the anticipated launch of a new instrument looks promising for new advances in retrieving lower-tropospheric ozone”. Instead, scientists can look at signatures from other gas emissions to get a sense of ozone formation. “Nitrogen dioxide and formaldehyde are a heavy focus of our research because they serve as proxies for two of the key ingredients that go on to form ozone in the atmosphere.”

    To understand ozone formation via these precursor pollutants, scientists have gathered data for more than two decades using spectrometer instruments aboard satellites that measure sunlight in ultraviolet and visible wavelengths that interact with these pollutants in the Earth’s atmosphere — known as solar backscatter radiation.

    Satellites, such as NASA’s Aura, carry instruments like the Ozone Monitoring Instrument (OMI). OMI, along with European-launched satellites such as the Global Ozone Monitoring Experiment (GOME) and the Scanning Imaging Absorption spectroMeter for Atmospheric CartograpHY (SCIAMACHY), and the newest generation TROPOspheric Monitoring instrument (TROPOMI), all orbit the Earth, collecting data during daylight hours when sunlight is interacting with the atmosphere over a particular location.

    In a recent paper from Fiore’s group, former graduate student Xiaomeng Jin (now a postdoc at the University of California at Berkeley), demonstrated that she could bring together and “beat down the noise in the data,” as Fiore says, to identify trends in ozone formation chemistry over several U.S. metropolitan areas that “are consistent with our on-the-ground understanding from in situ ozone measurements.”

    “This finding implies that we can use these records to learn about changes in surface ozone chemistry in places where we lack on-the-ground monitoring,” says Fiore. Extracting these signals by stringing together satellite data — OMI, GOME, and SCIAMACHY — to produce a two-decade record required reconciling the instruments’ differing orbit days, times, and fields of view on the ground, or spatial resolutions. 

    Currently, spectrometer instruments aboard satellites are retrieving data once per day. However, newer instruments, such as the Geostationary Environment Monitoring Spectrometer launched in February 2020 by the National Institute of Environmental Research in the Ministry of Environment of South Korea, will monitor a particular region continuously, providing much more data in real time.

    Over North America, the Tropospheric Emissions: Monitoring of Pollution Search (TEMPO) collaboration between NASA and the Smithsonian Astrophysical Observatory, led by Kelly Chance of Harvard University, will provide not only a stationary view of the atmospheric chemistry over the continent, but also a finer-resolution view — with the instrument recording pollution data from only a few square miles per pixel (with an anticipated launch in 2022).

    “What we’re very excited about is the opportunity to have continuous coverage where we get hourly measurements that allow us to follow pollution from morning rush hour through the course of the day and see how plumes of pollution are evolving in real time,” says Fiore.

    Data for the people

    Providing Earth-observing data to people in addition to scientists — namely environmental managers, city planners, and other government officials — is the goal for the NASA Health and Air Quality Applied Sciences Team (HAQAST).

    Since 2016, Fiore has been part of HAQAST, including collaborative “tiger teams” — projects that bring together scientists, nongovernment entities, and government officials — to bring data to bear on real issues.

    For example, in 2017, Fiore led a tiger team that provided guidance to state air management agencies on how satellite data can be incorporated into state implementation plans (SIPs). “Submission of a SIP is required for any state with a region in non-attainment of U.S. National Ambient Air Quality Standards to demonstrate their approach to achieving compliance with the standard,” says Fiore. “What we found is that small tweaks in, for example, the metrics we use to convey the science findings, can go a long way to making the science more usable, especially when there are detailed policy frameworks in place that must be followed.”

    Now, in 2021, Fiore is part of two tiger teams announced by HAQAST in late September. One team is looking at data to address environmental justice issues, by providing data to assess communities disproportionately affected by environmental health risks. Such information can be used to estimate the benefits of governmental investments in environmental improvements for disproportionately burdened communities. The other team is looking at urban emissions of nitrogen oxides to try to better quantify and communicate uncertainties in the estimates of anthropogenic sources of pollution.

    “For our HAQAST work, we’re looking at not just the estimate of the exposure to air pollutants, or in other words their concentrations,” says Fiore, “but how confident are we in our exposure estimates, which in turn affect our understanding of the public health burden due to exposure. We have stakeholder partners at the New York Department of Health who will pair exposure datasets with health data to help prioritize decisions around public health.

    “I enjoy working with stakeholders who have questions that require science to answer and can make a difference in their decisions.” Fiore says. More

  • in

    Reducing food waste to increase access to affordable foods

    About a third of the world’s food supply never gets eaten. That means the water, labor, energy, and fertilizer that went into growing, processing, and distributing the food is wasted.

    On the other end of the supply chain are cash-strapped consumers, who have been further distressed in recent years by factors like the Covid-19 pandemic and inflation.

    Spoiler Alert, a company founded by two MIT alumni, is helping companies bridge the gap between food waste and food insecurity with a platform connecting major food and beverage brands with discount grocers, retailers, and nonprofits. The platform helps brands discount or donate excess and short-dated inventory days, weeks, and months before it expires.

    “There is a tremendous amount of underutilized data that exists in the manufacturing and distribution space that results in good food going to waste,” says Ricky Ashenfelter MBA ’15, who co-founded the company with Emily Malina MBA ’15.

    Spoiler Alert helps brands manage distressed inventory data, create offers for potential buyers, and review and accept bids. The platform is designed to work with companies’ existing inventory and fulfillment systems, using automation and pricing intelligence to further streamline sales.

    “At a high level, we’re a waste-prevention software built for sales and supply-chain teams,” Ashenfelter says. “You can think of it as a private [business-to-business] eBay of sorts.”

    Spoiler Alert is working with global companies like Nestle, Kraft Heinz, and Danone, as well as discount grocers like the United Grocery Outlet and Misfits Market. Those brands are already using the platform to reduce food waste and get more food on people’s tables.

    “Project Drawdown [a nonprofit working on climate solutions] has identified food waste as the number one priority to address the global climate crisis, so these types of corporate initiatives can be really powerful from an environmental standpoint,” Ashenfelter says, noting the nonprofit estimates food waste accounts for 8 percent of global greenhouse gas emissions. “Contrast that with growing levels of food insecurity and folks not being able to access affordable nutrition, and you start to see how tackling supply-chain inefficiency can have a dramatic impact from both an environmental and a social lens. That’s what motivates us.”

    Untapped data for change

    Ashenfelter came to MIT’s Sloan School of Management after several years in sustainability software and management consulting within the retail and consumer products industries.

    “I was really attracted to transitioning into something much more entrepreneurial, and to leverage not only Sloan’s focus on entrepreneurship, but also the broader MIT ecosystem’s focus on technology, entrepreneurship, clean tech innovation, and other themes along that front,” he says.

    Ashenfelter met Malina at one of Sloan’s admitted students events in 2013, and the founders soon set out to use data to decrease food waste.

    “For us, the idea was clear: How do we better leverage data to manage excess and short-dated inventory?” Ashenfelter says. “How we go about that has evolved over the last six years, but it’s all rooted in solving an enormous climate problem, solving a major food insecurity problem, and from a capitalistic standpoint, helping businesses cut costs and generate revenue from otherwise wasted products.”

    The founders spent many hours in the Martin Trust Center for MIT Entrepreneurship with support from the Sloan Sustainability Initiative, and used Spoiler Alert as a case study in nearly every class they took, thinking through product development, sales, marketing, pricing, and more through their coursework.

    “We brought our idea into just about every action learning class that we could at Sloan and MIT,” Ashenfelter says.

    They also participated in the MIT $100K Entrepreneurship Competition and received support from the Venture Mentoring Service and the IDEAS Global Challenge program.

    Upon graduation, the founders initially began building a platform to facilitate donations of excess inventory, but soon learned big companies’ processes for discounting that inventory were also highly manual. Today, more than 90 percent of Spoiler Alert’s transaction volume is discounted, with the remainder donated.

    Different teams within an organization can upload excess inventory reports to Spoiler Alert’s system, eliminating the need to manually aggregate datasets and preparing what the industry refers to as “blowout lists” to sell. Spoiler Alert uses machine-learning-based tools to help both parties with pricing and negotiations to close deals more quickly.

    “Companies are taking pretty manual and slow approaches to deciding [what to do with excess inventory],” Ashenfelter says. “And when you have slow decision-making, you’re losing days or even weeks of shelf life on that product. That can be the difference between selling product versus donating, and donating versus dumping.”

    Once a deal has been made, Spoiler Alert automatically generates the forms and workflows needed by fulfillment teams to get the product out the door. The relationships companies build on the platform are also a major driver for cutting down waste.

    “We’re providing suppliers with the ability to control where their discounted and donated product ends up,” Ashenfelter says. “That’s really powerful because it allows these CPG brands to ensure that this product is, in many cases, getting to affordable nutrition outlets in underserved communities.”

    Ashenfelter says the majority of inventory goes to regional and national discount grocers, supplemented with extensive purchasing from local and nonprofit grocery chains.

    “Everything we do is oriented around helping sell as much product as possible to a reputable set of buyers at the most fair, equitable prices possible,” Ashenfelter says.

    Scaling for impact

    The pandemic has disrupted many aspects of the food supply chains. But Ashenfelter says it has also accelerated the adoption of digital solutions that can better manage such volatility.

    When Campbell began using Spoiler Alert’s system in 2019, for instance, it achieved a 36 percent increase in discount sales and a 27 percent increase in donations over the first five months.

    Ashenfelter says the results have proven that companies’ sustainability targets can go hand in hand with initiatives that boost their bottom lines. In fact, because Spoiler Alert focuses so much on the untapped revenue associated with food waste, many customers don’t even realize Spoiler Alert is a sustainability company until after they’ve signed on.

    “What’s neat about this program is that it becomes an incredibly powerful case study internally for how sustainability and operational outcomes aren’t in conflict and can drive both business results as well as overall environmental impact,” Ashenfelter says.

    Going forward, Spoiler Alert will continue building out algorithmic solutions that could further cut down on waste internationally and across a wider array of products.

    “At every step in our process, we’re collecting a tremendous amount of data in terms of what is and isn’t selling, at what price point, to which buyers, out of which geographies, and with how much remaining shelf life,” Ashenfelter explains. “We are only starting to scratch the surface in terms of bringing our recommendations engine to life for our suppliers and buyers. Ultimately our goal is to power the waste-free economy, and rooted in that is making better decisions faster, in collaboration with a growing ecosystem of supply chain partners, and with as little manual intervention as possible.” More

  • in

    Meet the 2021-22 Accenture Fellows

    Launched in October of 2020, the MIT and Accenture Convergence Initiative for Industry and Technology underscores the ways in which industry and technology come together to spur innovation. The five-year initiative aims to achieve its mission through research, education, and fellowships. To that end, Accenture has once again awarded five annual fellowships to MIT graduate students working on research in industry and technology convergence who are underrepresented, including by race, ethnicity, and gender.

    This year’s Accenture Fellows work across disciplines including robotics, manufacturing, artificial intelligence, and biomedicine. Their research covers a wide array of subjects, including: advancing manufacturing through computational design, with the potential to benefit global vaccine production; designing low-energy robotics for both consumer electronics and the aerospace industry; developing robotics and machine learning systems that may aid the elderly in their homes; and creating ingestible biomedical devices that can help gather medical data from inside a patient’s body.

    Student nominations from each unit within the School of Engineering, as well as from the four other MIT schools and the MIT Schwarzman College of Computing, were invited as part of the application process. Five exceptional students were selected as fellows in the initiative’s second year.

    Xinming (Lily) Liu is a PhD student in operations research at MIT Sloan School of Management. Her work is focused on behavioral and data-driven operations for social good, incorporating human behaviors into traditional optimization models, designing incentives, and analyzing real-world data. Her current research looks at the convergence of social media, digital platforms, and agriculture, with particular attention to expanding technological equity and economic opportunity in developing countries. Liu earned her BS from Cornell University, with a double major in operations research and computer science.

    Caris Moses is a PhD student in electrical engineering and computer science specializing inartificial intelligence. Moses’ research focuses on using machine learning, optimization, and electromechanical engineering to build robotics systems that are robust, flexible, intelligent, and can learn on the job. The technology she is developing holds promise for industries including flexible, small-batch manufacturing; robots to assist the elderly in their households; and warehouse management and fulfillment. Moses earned her BS in mechanical engineering from Cornell University and her MS in computer science from Northeastern University.

    Sergio Rodriguez Aponte is a PhD student in biological engineering. He is working on the convergence of computational design and manufacturing practices, which have the potential to impact industries such as biopharmaceuticals, food, and wellness/nutrition. His current research aims to develop strategies for applying computational tools, such as multiscale modeling and machine learning, to the design and production of manufacturable and accessible vaccine candidates that could eventually be available globally. Rodriguez Aponte earned his BS in industrial biotechnology from the University of Puerto Rico at Mayaguez.

    Soumya Sudhakar SM ’20 is a PhD student in aeronautics and astronautics. Her work is focused on theco-design of new algorithms and integrated circuits for autonomous low-energy robotics that could have novel applications in aerospace and consumer electronics. Her contributions bring together the emerging robotics industry, integrated circuits industry, aerospace industry, and consumer electronics industry. Sudhakar earned her BSE in mechanical and aerospace engineering from Princeton University and her MS in aeronautics and astronautics from MIT.

    So-Yoon Yang is a PhD student in electrical engineering and computer science. Her work on the development of low-power, wireless, ingestible biomedical devices for health care is at the intersection of the medical device, integrated circuit, artificial intelligence, and pharmaceutical fields. Currently, the majority of wireless biomedical devices can only provide a limited range of medical data measured from outside the body. Ingestible devices hold promise for the next generation of personal health care because they do not require surgical implantation, can be useful for detecting physiological and pathophysiological signals, and can also function as therapeutic alternatives when treatment cannot be done externally. Yang earned her BS in electrical and computer engineering from Seoul National University in South Korea and her MS in electrical engineering from Caltech. More

  • in

    Nonsense can make sense to machine-learning models

    For all that neural networks can accomplish, we still don’t really understand how they operate. Sure, we can program them to learn, but making sense of a machine’s decision-making process remains much like a fancy puzzle with a dizzying, complex pattern where plenty of integral pieces have yet to be fitted. 

    If a model was trying to classify an image of said puzzle, for example, it could encounter well-known, but annoying adversarial attacks, or even more run-of-the-mill data or processing issues. But a new, more subtle type of failure recently identified by MIT scientists is another cause for concern: “overinterpretation,” where algorithms make confident predictions based on details that don’t make sense to humans, like random patterns or image borders. 

    This could be particularly worrisome for high-stakes environments, like split-second decisions for self-driving cars, and medical diagnostics for diseases that need more immediate attention. Autonomous vehicles in particular rely heavily on systems that can accurately understand surroundings and then make quick, safe decisions. The network used specific backgrounds, edges, or particular patterns of the sky to classify traffic lights and street signs — irrespective of what else was in the image. 

    The team found that neural networks trained on popular datasets like CIFAR-10 and ImageNet suffered from overinterpretation. Models trained on CIFAR-10, for example, made confident predictions even when 95 percent of input images were missing, and the remainder is senseless to humans. 

    “Overinterpretation is a dataset problem that’s caused by these nonsensical signals in datasets. Not only are these high-confidence images unrecognizable, but they contain less than 10 percent of the original image in unimportant areas, such as borders. We found that these images were meaningless to humans, yet models can still classify them with high confidence,” says Brandon Carter, MIT Computer Science and Artificial Intelligence Laboratory PhD student and lead author on a paper about the research. 

    Deep-image classifiers are widely used. In addition to medical diagnosis and boosting autonomous vehicle technology, there are use cases in security, gaming, and even an app that tells you if something is or isn’t a hot dog, because sometimes we need reassurance. The tech in discussion works by processing individual pixels from tons of pre-labeled images for the network to “learn.” 

    Image classification is hard, because machine-learning models have the ability to latch onto these nonsensical subtle signals. Then, when image classifiers are trained on datasets such as ImageNet, they can make seemingly reliable predictions based on those signals. 

    Although these nonsensical signals can lead to model fragility in the real world, the signals are actually valid in the datasets, meaning overinterpretation can’t be diagnosed using typical evaluation methods based on that accuracy. 

    To find the rationale for the model’s prediction on a particular input, the methods in the present study start with the full image and repeatedly ask, what can I remove from this image? Essentially, it keeps covering up the image, until you’re left with the smallest piece that still makes a confident decision. 

    To that end, it could also be possible to use these methods as a type of validation criteria. For example, if you have an autonomously driving car that uses a trained machine-learning method for recognizing stop signs, you could test that method by identifying the smallest input subset that constitutes a stop sign. If that consists of a tree branch, a particular time of day, or something that’s not a stop sign, you could be concerned that the car might come to a stop at a place it’s not supposed to.

    While it may seem that the model is the likely culprit here, the datasets are more likely to blame. “There’s the question of how we can modify the datasets in a way that would enable models to be trained to more closely mimic how a human would think about classifying images and therefore, hopefully, generalize better in these real-world scenarios, like autonomous driving and medical diagnosis, so that the models don’t have this nonsensical behavior,” says Carter. 

    This may mean creating datasets in more controlled environments. Currently, it’s just pictures that are extracted from public domains that are then classified. But if you want to do object identification, for example, it might be necessary to train models with objects with an uninformative background. 

    This work was supported by Schmidt Futures and the National Institutes of Health. Carter wrote the paper alongside Siddhartha Jain and Jonas Mueller, scientists at Amazon, and MIT Professor David Gifford. They are presenting the work at the 2021 Conference on Neural Information Processing Systems. More

  • in

    Q&A: More-sustainable concrete with machine learning

    As a building material, concrete withstands the test of time. Its use dates back to early civilizations, and today it is the most popular composite choice in the world. However, it’s not without its faults. Production of its key ingredient, cement, contributes 8-9 percent of the global anthropogenic CO2 emissions and 2-3 percent of energy consumption, which is only projected to increase in the coming years. With aging United States infrastructure, the federal government recently passed a milestone bill to revitalize and upgrade it, along with a push to reduce greenhouse gas emissions where possible, putting concrete in the crosshairs for modernization, too.

    Elsa Olivetti, the Esther and Harold E. Edgerton Associate Professor in the MIT Department of Materials Science and Engineering, and Jie Chen, MIT-IBM Watson AI Lab research scientist and manager, think artificial intelligence can help meet this need by designing and formulating new, more sustainable concrete mixtures, with lower costs and carbon dioxide emissions, while improving material performance and reusing manufacturing byproducts in the material itself. Olivetti’s research improves environmental and economic sustainability of materials, and Chen develops and optimizes machine learning and computational techniques, which he can apply to materials reformulation. Olivetti and Chen, along with their collaborators, have recently teamed up for an MIT-IBM Watson AI Lab project to make concrete more sustainable for the benefit of society, the climate, and the economy.

    Q: What applications does concrete have, and what properties make it a preferred building material?

    Olivetti: Concrete is the dominant building material globally with an annual consumption of 30 billion metric tons. That is over 20 times the next most produced material, steel, and the scale of its use leads to considerable environmental impact, approximately 5-8 percent of global greenhouse gas (GHG) emissions. It can be made locally, has a broad range of structural applications, and is cost-effective. Concrete is a mixture of fine and coarse aggregate, water, cement binder (the glue), and other additives.

    Q: Why isn’t it sustainable, and what research problems are you trying to tackle with this project?

    Olivetti: The community is working on several ways to reduce the impact of this material, including alternative fuels use for heating the cement mixture, increasing energy and materials efficiency and carbon sequestration at production facilities, but one important opportunity is to develop an alternative to the cement binder.

    While cement is 10 percent of the concrete mass, it accounts for 80 percent of the GHG footprint. This impact is derived from the fuel burned to heat and run the chemical reaction required in manufacturing, but also the chemical reaction itself releases CO2 from the calcination of limestone. Therefore, partially replacing the input ingredients to cement (traditionally ordinary Portland cement or OPC) with alternative materials from waste and byproducts can reduce the GHG footprint. But use of these alternatives is not inherently more sustainable because wastes might have to travel long distances, which adds to fuel emissions and cost, or might require pretreatment processes. The optimal way to make use of these alternate materials will be situation-dependent. But because of the vast scale, we also need solutions that account for the huge volumes of concrete needed. This project is trying to develop novel concrete mixtures that will decrease the GHG impact of the cement and concrete, moving away from the trial-and-error processes towards those that are more predictive.

    Chen: If we want to fight climate change and make our environment better, are there alternative ingredients or a reformulation we could use so that less greenhouse gas is emitted? We hope that through this project using machine learning we’ll be able to find a good answer.

    Q: Why is this problem important to address now, at this point in history?

    Olivetti: There is urgent need to address greenhouse gas emissions as aggressively as possible, and the road to doing so isn’t necessarily straightforward for all areas of industry. For transportation and electricity generation, there are paths that have been identified to decarbonize those sectors. We need to move much more aggressively to achieve those in the time needed; further, the technological approaches to achieve that are more clear. However, for tough-to-decarbonize sectors, such as industrial materials production, the pathways to decarbonization are not as mapped out.

    Q: How are you planning to address this problem to produce better concrete?

    Olivetti: The goal is to predict mixtures that will both meet performance criteria, such as strength and durability, with those that also balance economic and environmental impact. A key to this is to use industrial wastes in blended cements and concretes. To do this, we need to understand the glass and mineral reactivity of constituent materials. This reactivity not only determines the limit of the possible use in cement systems but also controls concrete processing, and the development of strength and pore structure, which ultimately control concrete durability and life-cycle CO2 emissions.

    Chen: We investigate using waste materials to replace part of the cement component. This is something that we’ve hypothesized would be more sustainable and economic — actually waste materials are common, and they cost less. Because of the reduction in the use of cement, the final concrete product would be responsible for much less carbon dioxide production. Figuring out the right concrete mixture proportion that makes endurable concretes while achieving other goals is a very challenging problem. Machine learning is giving us an opportunity to explore the advancement of predictive modeling, uncertainty quantification, and optimization to solve the issue. What we are doing is exploring options using deep learning as well as multi-objective optimization techniques to find an answer. These efforts are now more feasible to carry out, and they will produce results with reliability estimates that we need to understand what makes a good concrete.

    Q: What kinds of AI and computational techniques are you employing for this?

    Olivetti: We use AI techniques to collect data on individual concrete ingredients, mix proportions, and concrete performance from the literature through natural language processing. We also add data obtained from industry and/or high throughput atomistic modeling and experiments to optimize the design of concrete mixtures. Then we use this information to develop insight into the reactivity of possible waste and byproduct materials as alternatives to cement materials for low-CO2 concrete. By incorporating generic information on concrete ingredients, the resulting concrete performance predictors are expected to be more reliable and transformative than existing AI models.

    Chen: The final objective is to figure out what constituents, and how much of each, to put into the recipe for producing the concrete that optimizes the various factors: strength, cost, environmental impact, performance, etc. For each of the objectives, we need certain models: We need a model to predict the performance of the concrete (like, how long does it last and how much weight does it sustain?), a model to estimate the cost, and a model to estimate how much carbon dioxide is generated. We will need to build these models by using data from literature, from industry, and from lab experiments.

    We are exploring Gaussian process models to predict the concrete strength, going forward into days and weeks. This model can give us an uncertainty estimate of the prediction as well. Such a model needs specification of parameters, for which we will use another model to calculate. At the same time, we also explore neural network models because we can inject domain knowledge from human experience into them. Some models are as simple as multi-layer perceptions, while some are more complex, like graph neural networks. The goal here is that we want to have a model that is not only accurate but also robust — the input data is noisy, and the model must embrace the noise, so that its prediction is still accurate and reliable for the multi-objective optimization.

    Once we have built models that we are confident with, we will inject their predictions and uncertainty estimates into the optimization of multiple objectives, under constraints and under uncertainties.

    Q: How do you balance cost-benefit trade-offs?

    Chen: The multiple objectives we consider are not necessarily consistent, and sometimes they are at odds with each other. The goal is to identify scenarios where the values for our objectives cannot be further pushed simultaneously without compromising one or a few. For example, if you want to further reduce the cost, you probably have to suffer the performance or suffer the environmental impact. Eventually, we will give the results to policymakers and they will look into the results and weigh the options. For example, they may be able to tolerate a slightly higher cost under a significant reduction in greenhouse gas. Alternatively, if the cost varies little but the concrete performance changes drastically, say, doubles or triples, then this is definitely a favorable outcome.

    Q: What kinds of challenges do you face in this work?

    Chen: The data we get either from industry or from literature are very noisy; the concrete measurements can vary a lot, depending on where and when they are taken. There are also substantial missing data when we integrate them from different sources, so, we need to spend a lot of effort to organize and make the data usable for building and training machine learning models. We also explore imputation techniques that substitute missing features, as well as models that tolerate missing features, in our predictive modeling and uncertainty estimate.

    Q: What do you hope to achieve through this work?

    Chen: In the end, we are suggesting either one or a few concrete recipes, or a continuum of recipes, to manufacturers and policymakers. We hope that this will provide invaluable information for both the construction industry and for the effort of protecting our beloved Earth.

    Olivetti: We’d like to develop a robust way to design cements that make use of waste materials to lower their CO2 footprint. Nobody is trying to make waste, so we can’t rely on one stream as a feedstock if we want this to be massively scalable. We have to be flexible and robust to shift with feedstocks changes, and for that we need improved understanding. Our approach to develop local, dynamic, and flexible alternatives is to learn what makes these wastes reactive, so we know how to optimize their use and do so as broadly as possible. We do that through predictive model development through software we have developed in my group to automatically extract data from literature on over 5 million texts and patents on various topics. We link this to the creative capabilities of our IBM collaborators to design methods that predict the final impact of new cements. If we are successful, we can lower the emissions of this ubiquitous material and play our part in achieving carbon emissions mitigation goals.

    Other researchers involved with this project include Stefanie Jegelka, the X-Window Consortium Career Development Associate Professor in the MIT Department of Electrical Engineering and Computer Science; Richard Goodwin, IBM principal researcher; Soumya Ghosh, MIT-IBM Watson AI Lab research staff member; and Kristen Severson, former research staff member. Collaborators included Nghia Hoang, former research staff member with MIT-IBM Watson AI Lab and IBM Research; and Jeremy Gregory, research scientist in the MIT Department of Civil and Environmental Engineering and executive director of the MIT Concrete Sustainability Hub.

    This research is supported by the MIT-IBM Watson AI Lab. More

  • in

    The reasons behind lithium-ion batteries’ rapid cost decline

    Lithium-ion batteries, those marvels of lightweight power that have made possible today’s age of handheld electronics and electric vehicles, have plunged in cost since their introduction three decades ago at a rate similar to the drop in solar panel prices, as documented by a study published last March. But what brought about such an astonishing cost decline, of about 97 percent?

    Some of the researchers behind that earlier study have now analyzed what accounted for the extraordinary savings. They found that by far the biggest factor was work on research and development, particularly in chemistry and materials science. This outweighed the gains achieved through economies of scale, though that turned out to be the second-largest category of reductions.

    The new findings are being published today in the journal Energy and Environmental Science, in a paper by MIT postdoc Micah Ziegler, recent graduate student Juhyun Song PhD ’19, and Jessika Trancik, a professor in MIT’s Institute for Data, Systems and Society.

    The findings could be useful for policymakers and planners to help guide spending priorities in order to continue the pathway toward ever-lower costs for this and other crucial energy storage technologies, according to Trancik. Their work suggests that there is still considerable room for further improvement in electrochemical battery technologies, she says.

    The analysis required digging through a variety of sources, since much of the relevant information consists of closely held proprietary business data. “The data collection effort was extensive,” Ziegler says. “We looked at academic articles, industry and government reports, press releases, and specification sheets. We even looked at some legal filings that came out. We had to piece together data from many different sources to get a sense of what was happening.” He says they collected “about 15,000 qualitative and quantitative data points, across 1,000 individual records from approximately 280 references.”

    Data from the earliest times are hardest to access and can have the greatest uncertainties, Trancik says, but by comparing different data sources from the same period they have attempted to account for these uncertainties.

    Overall, she says, “we estimate that the majority of the cost decline, more than 50 percent, came from research-and-development-related activities.” That included both private sector and government-funded research and development, and “the vast majority” of that cost decline within that R&D category came from chemistry and materials research.

    That was an interesting finding, she says, because “there were so many variables that people were working on through very different kinds of efforts,” including the design of the battery cells themselves, their manufacturing systems, supply chains, and so on. “The cost improvement emerged from a diverse set of efforts and many people, and not from the work of only a few individuals.”

    The findings about the importance of investment in R&D were especially significant, Ziegler says, because much of this investment happened after lithium-ion battery technology was commercialized, a stage at which some analysts thought the research contribution would become less significant. Over roughly a 20-year period starting five years after the batteries’ introduction in the early 1990s, he says, “most of the cost reduction still came from R&D. The R&D contribution didn’t end when commercialization began. In fact, it was still the biggest contributor to cost reduction.”

    The study took advantage of an analytical approach that Trancik and her team initially developed to analyze the similarly precipitous drop in costs of silicon solar panels over the last few decades. They also applied the approach to understand the rising costs of nuclear energy. “This is really getting at the fundamental mechanisms of technological change,” she says. “And we can also develop these models looking forward in time, which allows us to uncover the levers that people could use to improve the technology in the future.”

    One advantage of the methodology Trancik and her colleagues have developed, she says, is that it helps to sort out the relative importance of different factors when many variables are changing all at once, which typically happens as a technology improves. “It’s not simply adding up the cost effects of these variables,” she says, “because many of these variables affect many different cost components. There’s this kind of intricate web of dependencies.” But the team’s methodology makes it possible to “look at how that overall cost change can be attributed to those variables, by essentially mapping out that network of dependencies,” she says.

    This can help provide guidance on public spending, private investments, and other incentives. “What are all the things that different decision makers could do?” she asks. “What decisions do they have agency over so that they could improve the technology, which is important in the case of low-carbon technologies, where we’re looking for solutions to climate change and we have limited time and limited resources? The new approach allows us to potentially be a bit more intentional about where we make those investments of time and money.”

    “This paper collects data available in a systematic way to determine changes in the cost components of lithium-ion batteries between 1990-1995 and 2010-2015,” says Laura Diaz Anadon, a professor of climate change policy at Cambridge University, who was not connected to this research. “This period was an important one in the history of the technology, and understanding the evolution of cost components lays the groundwork for future work on mechanisms and could help inform research efforts in other types of batteries.”

    The research was supported by the Alfred P. Sloan Foundation, the Environmental Defense Fund, and the MIT Technology and Policy Program. More