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

    Co-creating climate futures with real-time data and spatial storytelling

    Virtual story worlds and game engines aren’t just for video games anymore. They are now tools for scientists and storytellers to digitally twin existing physical spaces and then turn them into vessels to dream up speculative climate stories and build collective designs of the future. That’s the theory and practice behind the MIT WORLDING initiative.

    Twice this year, WORLDING matched world-class climate story teams working in XR (extended reality) with relevant labs and researchers across MIT. One global group returned for a virtual gathering online in partnership with Unity for Humanity, while another met for one weekend in person, hosted at the MIT Media Lab.

    “We are witnessing the birth of an emergent field that fuses climate science, urban planning, real-time 3D engines, nonfiction storytelling, and speculative fiction, and it is all fueled by the urgency of the climate crises,” says Katerina Cizek, lead designer of the WORLDING initiative at the Co-Creation Studio of MIT Open Documentary Lab. “Interdisciplinary teams are forming and blossoming around the planet to collectively imagine and tell stories of healthy, livable worlds in virtual 3D spaces and then finding direct ways to translate that back to earth, literally.”

    At this year’s virtual version of WORLDING, five multidisciplinary teams were selected from an open call. In a week-long series of research and development gatherings, the teams met with MIT scientists, staff, fellows, students, and graduates, as well as other leading figures in the field. Guests ranged from curators at film festivals such as Sundance and Venice, climate policy specialists, and award-winning media creators to software engineers and renowned Earth and atmosphere scientists. The teams heard from MIT scholars in diverse domains, including geomorphology, urban planning as acts of democracy, and climate researchers at MIT Media Lab.

    Mapping climate data

    “We are measuring the Earth’s environment in increasingly data-driven ways. Hundreds of terabytes of data are taken every day about our planet in order to study the Earth as a holistic system, so we can address key questions about global climate change,” explains Rachel Connolly, an MIT Media Lab research scientist focused in the “Future Worlds” research theme, in a talk to the group. “Why is this important for your work and storytelling in general? Having the capacity to understand and leverage this data is critical for those who wish to design for and successfully operate in the dynamic Earth environment.”

    Making sense of billions of data points was a key theme during this year’s sessions. In another talk, Taylor Perron, an MIT professor of Earth, atmospheric and planetary sciences, shared how his team uses computational modeling combined with many other scientific processes to better understand how geology, climate, and life intertwine to shape the surfaces of Earth and other planets. His work resonated with one WORLDING team in particular, one aiming to digitally reconstruct the pre-Hispanic Lake Texcoco — where current day Mexico City is now situated — as a way to contrast and examine the region’s current water crisis.

    Democratizing the future

    While WORLDING approaches rely on rigorous science and the interrogation of large datasets, they are also founded on democratizing community-led approaches.

    MIT Department of Urban Studies and Planning graduate Lafayette Cruise MCP ’19 met with the teams to discuss how he moved his own practice as a trained urban planner to include a futurist component involving participatory methods. “I felt we were asking the same limited questions in regards to the future we were wanting to produce. We’re very limited, very constrained, as to whose values and comforts are being centered. There are so many possibilities for how the future could be.”

    Scaling to reach billions

    This work scales from the very local to massive global populations. Climate policymakers are concerned with reaching billions of people in the line of fire. “We have a goal to reach 1 billion people with climate resilience solutions,” says Nidhi Upadhyaya, deputy director at Atlantic Council’s Adrienne Arsht-Rockefeller Foundation Resilience Center. To get that reach, Upadhyaya is turning to games. “There are 3.3 billion-plus people playing video games across the world. Half of these players are women. This industry is worth $300 billion. Africa is currently among the fastest-growing gaming markets in the world, and 55 percent of the global players are in the Asia Pacific region.” She reminded the group that this conversation is about policy and how formats of mass communication can be used for policymaking, bringing about change, changing behavior, and creating empathy within audiences.

    Socially engaged game development is also connected to education at Unity Technologies, a game engine company. “We brought together our education and social impact work because we really see it as a critical flywheel for our business,” said Jessica Lindl, vice president and global head of social impact/education at Unity Technologies, in the opening talk of WORLDING. “We upscale about 900,000 students, in university and high school programs around the world, and about 800,000 adults who are actively learning and reskilling and upskilling in Unity. Ultimately resulting in our mission of the ‘world is a better place with more creators in it,’ millions of creators who reach billions of consumers — telling the world stories, and fostering a more inclusive, sustainable, and equitable world.”

    Access to these technologies is key, especially the hardware. “Accessibility has been missing in XR,” explains Reginé Gilbert, who studies and teaches accessibility and disability in user experience design at New York University. “XR is being used in artificial intelligence, assistive technology, business, retail, communications, education, empathy, entertainment, recreation, events, gaming, health, rehabilitation meetings, navigation, therapy, training, video programming, virtual assistance wayfinding, and so many other uses. This is a fun fact for folks: 97.8 percent of the world hasn’t tried VR [virtual reality] yet, actually.”

    Meanwhile, new hardware is on its way. The WORLDING group got early insights into the highly anticipated Apple Vision Pro headset, which promises to integrate many forms of XR and personal computing in one device. “They’re really pushing this kind of pass-through or mixed reality,” said Dan Miller, a Unity engineer on the poly spatial team, collaborating with Apple, who described the experience of the device as “You are viewing the real world. You’re pulling up windows, you’re interacting with content. It’s a kind of spatial computing device where you have multiple apps open, whether it’s your email client next to your messaging client with a 3D game in the middle. You’re interacting with all these things in the same space and at different times.”

    “WORLDING combines our passion for social-impact storytelling and incredible innovative storytelling,” said Paisley Smith of the Unity for Humanity Program at Unity Technologies. She added, “This is an opportunity for creators to incubate their game-changing projects and connect with experts across climate, story, and technology.”

    Meeting at MIT

    In a new in-person iteration of WORLDING this year, organizers collaborated closely with Connolly at the MIT Media Lab to co-design an in-person weekend conference Oct. 25 – Nov. 7 with 45 scholars and professionals who visualize climate data at NASA, the National Oceanic and Atmospheric Administration, planetariums, and museums across the United States.

    A participant said of the event, “An incredible workshop that had had a profound effect on my understanding of climate data storytelling and how to combine different components together for a more [holistic] solution.”

    “With this gathering under our new Future Worlds banner,” says Dava Newman, director of the MIT Media Lab and Apollo Program Professor of Astronautics chair, “the Media Lab seeks to affect human behavior and help societies everywhere to improve life here on Earth and in worlds beyond, so that all — the sentient, natural, and cosmic — worlds may flourish.” 

    “WORLDING’s virtual-only component has been our biggest strength because it has enabled a true, international cohort to gather, build, and create together. But this year, an in-person version showed broader opportunities that spatial interactivity generates — informal Q&As, physical worksheets, and larger-scale ideation, all leading to deeper trust-building,” says WORLDING producer Srushti Kamat SM ’23.

    The future and potential of WORLDING lies in the ongoing dialogue between the virtual and physical, both in the work itself and in the format of the workshops. More

  • in

    To excel at engineering design, generative AI must learn to innovate, study finds

    ChatGPT and other deep generative models are proving to be uncanny mimics. These AI supermodels can churn out poems, finish symphonies, and create new videos and images by automatically learning from millions of examples of previous works. These enormously powerful and versatile tools excel at generating new content that resembles everything they’ve seen before.

    But as MIT engineers say in a new study, similarity isn’t enough if you want to truly innovate in engineering tasks.

    “Deep generative models (DGMs) are very promising, but also inherently flawed,” says study author Lyle Regenwetter, a mechanical engineering graduate student at MIT. “The objective of these models is to mimic a dataset. But as engineers and designers, we often don’t want to create a design that’s already out there.”

    He and his colleagues make the case that if mechanical engineers want help from AI to generate novel ideas and designs, they will have to first refocus those models beyond “statistical similarity.”

    “The performance of a lot of these models is explicitly tied to how statistically similar a generated sample is to what the model has already seen,” says co-author Faez Ahmed, assistant professor of mechanical engineering at MIT. “But in design, being different could be important if you want to innovate.”

    In their study, Ahmed and Regenwetter reveal the pitfalls of deep generative models when they are tasked with solving engineering design problems. In a case study of bicycle frame design, the team shows that these models end up generating new frames that mimic previous designs but falter on engineering performance and requirements.

    When the researchers presented the same bicycle frame problem to DGMs that they specifically designed with engineering-focused objectives, rather than only statistical similarity, these models produced more innovative, higher-performing frames.

    The team’s results show that similarity-focused AI models don’t quite translate when applied to engineering problems. But, as the researchers also highlight in their study, with some careful planning of task-appropriate metrics, AI models could be an effective design “co-pilot.”

    “This is about how AI can help engineers be better and faster at creating innovative products,” Ahmed says. “To do that, we have to first understand the requirements. This is one step in that direction.”

    The team’s new study appeared recently online, and will be in the December print edition of the journal Computer Aided Design. The research is a collaboration between computer scientists at MIT-IBM Watson AI Lab and mechanical engineers in MIT’s DeCoDe Lab. The study’s co-authors include Akash Srivastava and Dan Gutreund at the MIT-IBM Watson AI Lab.

    Framing a problem

    As Ahmed and Regenwetter write, DGMs are “powerful learners, boasting unparalleled ability” to process huge amounts of data. DGM is a broad term for any machine-learning model that is trained to learn distribution of data and then use that to generate new, statistically similar content. The enormously popular ChatGPT is one type of deep generative model known as a large language model, or LLM, which incorporates natural language processing capabilities into the model to enable the app to generate realistic imagery and speech in response to conversational queries. Other popular models for image generation include DALL-E and Stable Diffusion.

    Because of their ability to learn from data and generate realistic samples, DGMs have been increasingly applied in multiple engineering domains. Designers have used deep generative models to draft new aircraft frames, metamaterial designs, and optimal geometries for bridges and cars. But for the most part, the models have mimicked existing designs, without improving the performance on existing designs.

    “Designers who are working with DGMs are sort of missing this cherry on top, which is adjusting the model’s training objective to focus on the design requirements,” Regenwetter says. “So, people end up generating designs that are very similar to the dataset.”

    In the new study, he outlines the main pitfalls in applying DGMs to engineering tasks, and shows that the fundamental objective of standard DGMs does not take into account specific design requirements. To illustrate this, the team invokes a simple case of bicycle frame design and demonstrates that problems can crop up as early as the initial learning phase. As a model learns from thousands of existing bike frames of various sizes and shapes, it might consider two frames of similar dimensions to have similar performance, when in fact a small disconnect in one frame — too small to register as a significant difference in statistical similarity metrics — makes the frame much weaker than the other, visually similar frame.

    Beyond “vanilla”
    An animation depicting transformations across common bicycle designs. Credit: Courtesy of the researchers

    The researchers carried the bicycle example forward to see what designs a DGM would actually generate after having learned from existing designs. They first tested a conventional “vanilla” generative adversarial network, or GAN — a model that has widely been used in image and text synthesis, and is tuned simply to generate statistically similar content. They trained the model on a dataset of thousands of bicycle frames, including commercially manufactured designs and less conventional, one-off frames designed by hobbyists.

    Once the model learned from the data, the researchers asked it to generate hundreds of new bike frames. The model produced realistic designs that resembled existing frames. But none of the designs showed significant improvement in performance, and some were even a bit inferior, with heavier, less structurally sound frames.

    The team then carried out the same test with two other DGMs that were specifically designed for engineering tasks. The first model is one that Ahmed previously developed to generate high-performing airfoil designs. He built this model to prioritize statistical similarity as well as functional performance. When applied to the bike frame task, this model generated realistic designs that also were lighter and stronger than existing designs. But it also produced physically “invalid” frames, with components that didn’t quite fit or overlapped in physically impossible ways.

    “We saw designs that were significantly better than the dataset, but also designs that were geometrically incompatible because the model wasn’t focused on meeting design constraints,” Regenwetter says.

    The last model the team tested was one that Regenwetter built to generate new geometric structures. This model was designed with the same priorities as the previous models, with the added ingredient of design constraints, and prioritizing physically viable frames, for instance, with no disconnections or overlapping bars. This last model produced the highest-performing designs, that were also physically feasible.

    “We found that when a model goes beyond statistical similarity, it can come up with designs that are better than the ones that are already out there,” Ahmed says. “It’s a proof of what AI can do, if it is explicitly trained on a design task.”

    For instance, if DGMs can be built with other priorities, such as performance, design constraints, and novelty, Ahmed foresees “numerous engineering fields, such as molecular design and civil infrastructure, would greatly benefit. By shedding light on the potential pitfalls of relying solely on statistical similarity, we hope to inspire new pathways and strategies in generative AI applications outside multimedia.” More

  • in

    Making sense of cell fate

    Despite the proliferation of novel therapies such as immunotherapy or targeted therapies, radiation and chemotherapy remain the frontline treatment for cancer patients. About half of all patients still receive radiation and 60-80 percent receive chemotherapy.

    Both radiation and chemotherapy work by damaging DNA, taking advantage of a vulnerability specific to cancer cells. Healthy cells are more likely to survive radiation and chemotherapy since their mechanisms for identifying and repairing DNA damage are intact. In cancer cells, these repair mechanisms are compromised by mutations. When cancer cells cannot adequately respond to the DNA damage caused by radiation and chemotherapy, ideally, they undergo apoptosis or die by other means.

    However, there is another fate for cells after DNA damage: senescence — a state where cells survive, but stop dividing. Senescent cells’ DNA has not been damaged enough to induce apoptosis but is too damaged to support cell division. While senescent cancer cells themselves are unable to proliferate and spread, they are bad actors in the fight against cancer because they seem to enable other cancer cells to develop more aggressively. Although a cancer cell’s fate is not apparent until a few days after treatment, the decision to survive, die, or enter senescence is made much earlier. But, precisely when and how that decision is made has not been well understood.

    In an open-access study of ovarian and osteosarcoma cancer cells appearing July 19 in Cell Systems, MIT researchers show that cell signaling proteins commonly associated with cell proliferation and apoptosis instead commit cancer cells to senescence within 12 hours of treatment with low doses of certain kinds of chemotherapy.

    “When it comes to treating cancer, this study underscores that it’s important not to think too linearly about cell signaling,” says Michael Yaffe, who is a David H. Koch Professor of Science at MIT, the director of the MIT Center for Precision Cancer Medicine, a member of MIT’s Koch Institute for Integrative Cancer Research, and the senior author of the study. “If you assume that a particular treatment will always affect cancer cell signaling in the same way — you may be setting yourself up for many surprises, and treating cancers with the wrong combination of drugs.”

    Using a combination of experiments with cancer cells and computational modeling, the team investigated the cell signaling mechanisms that prompt cancer cells to enter senescence after treatment with a commonly used anti-cancer agent. Their efforts singled out two protein kinases and a component of the AP-1 transcription factor complex as highly associated with the induction of senescence after DNA damage, despite the well-established roles for all of these molecules in promoting cell proliferation in cancer.

    The researchers treated cancer cells with low and high doses of doxorubicin, a chemotherapy that interferes with the function with topoisomerase II, an enzyme that breaks and then repairs DNA strands during replication to fix tangles and other topological problems.

    By measuring the effects of DNA damage on single cells at several time points ranging from six hours to four days after the initial exposure, the team created two datasets. In one dataset, the researchers tracked cell fate over time. For the second set, researchers measured relative cell signaling activity levels across a variety of proteins associated with responses to DNA damage or cellular stress, determination of cell fate, and progress through cell growth and division.

    The two datasets were used to build a computational model that identifies correlations between time, dosage, signal, and cell fate. The model identified the activities of the MAP kinases Erk and JNK, and the transcription factor c-Jun as key components of the AP-1 protein likewise understood to involved in the induction of senescence. The researchers then validated these computational findings by showing that inhibition of JNK and Erk after DNA damage successfully prevented cells from entering senescence.

    The researchers leveraged JNK and Erk inhibition to pinpoint exactly when cells made the decision to enter senescence. Surprisingly, they found that the decision to enter senescence was made within 12 hours of DNA damage, even though it took days to actually see the senescent cells accumulate. The team also found that with the passage of more time, these MAP kinases took on a different function: promoting the secretion of proinflammatory proteins called cytokines that are responsible for making other cancer cells proliferate and develop resistance to chemotherapy.

    “Proteins like cytokines encourage ‘bad behavior’ in neighboring tumor cells that lead to more aggressive cancer progression,” says Tatiana Netterfield, a graduate student in the Yaffe lab and the lead author of the study. “Because of this, it is thought that senescent cells that stay near the tumor for long periods of time are detrimental to treating cancer.”

    This study’s findings apply to cancer cells treated with a commonly used type of chemotherapy that stalls DNA replication after repair. But more broadly, the study emphasizes that “when treating cancer, it’s extremely important to understand the molecular characteristics of cancer cells and the contextual factors such as time and dosing that determine cell fate,” explains Netterfield.

    The study, however, has more immediate implications for treatments that are already in use. One class of Erk inhibitors, MEK inhibitors, are used in the clinic with the expectation that they will curb cancer growth.

    “We must be cautious about administering MEK inhibitors together with chemotherapies,” says Yaffe. “The combination may have the unintended effect of driving cells into proliferation, rather than senescence.”

    In future work, the team will perform studies to understand how and why individual cells choose to proliferate instead of enter senescence. Additionally, the team is employing next-generation sequencing to understand which genes c-Jun is regulating in order to push cells toward senescence.

    This study was funded, in part, by the Charles and Marjorie Holloway Foundation and the MIT Center for Precision Cancer Medicine. More

  • in

    Learning the language of molecules to predict their properties

    Discovering new materials and drugs typically involves a manual, trial-and-error process that can take decades and cost millions of dollars. To streamline this process, scientists often use machine learning to predict molecular properties and narrow down the molecules they need to synthesize and test in the lab.

    Researchers from MIT and the MIT-Watson AI Lab have developed a new, unified framework that can simultaneously predict molecular properties and generate new molecules much more efficiently than these popular deep-learning approaches.

    To teach a machine-learning model to predict a molecule’s biological or mechanical properties, researchers must show it millions of labeled molecular structures — a process known as training. Due to the expense of discovering molecules and the challenges of hand-labeling millions of structures, large training datasets are often hard to come by, which limits the effectiveness of machine-learning approaches.

    By contrast, the system created by the MIT researchers can effectively predict molecular properties using only a small amount of data. Their system has an underlying understanding of the rules that dictate how building blocks combine to produce valid molecules. These rules capture the similarities between molecular structures, which helps the system generate new molecules and predict their properties in a data-efficient manner.

    This method outperformed other machine-learning approaches on both small and large datasets, and was able to accurately predict molecular properties and generate viable molecules when given a dataset with fewer than 100 samples.

    “Our goal with this project is to use some data-driven methods to speed up the discovery of new molecules, so you can train a model to do the prediction without all of these cost-heavy experiments,” says lead author Minghao Guo, a computer science and electrical engineering (EECS) graduate student.

    Guo’s co-authors include MIT-IBM Watson AI Lab research staff members Veronika Thost, Payel Das, and Jie Chen; recent MIT graduates Samuel Song ’23 and Adithya Balachandran ’23; and senior author Wojciech Matusik, a professor of electrical engineering and computer science and a member of the MIT-IBM Watson AI Lab, who leads the Computational Design and Fabrication Group within the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL). The research will be presented at the International Conference for Machine Learning.

    Learning the language of molecules

    To achieve the best results with machine-learning models, scientists need training datasets with millions of molecules that have similar properties to those they hope to discover. In reality, these domain-specific datasets are usually very small. So, researchers use models that have been pretrained on large datasets of general molecules, which they apply to a much smaller, targeted dataset. However, because these models haven’t acquired much domain-specific knowledge, they tend to perform poorly.

    The MIT team took a different approach. They created a machine-learning system that automatically learns the “language” of molecules — what is known as a molecular grammar — using only a small, domain-specific dataset. It uses this grammar to construct viable molecules and predict their properties.

    In language theory, one generates words, sentences, or paragraphs based on a set of grammar rules. You can think of a molecular grammar the same way. It is a set of production rules that dictate how to generate molecules or polymers by combining atoms and substructures.

    Just like a language grammar, which can generate a plethora of sentences using the same rules, one molecular grammar can represent a vast number of molecules. Molecules with similar structures use the same grammar production rules, and the system learns to understand these similarities.

    Since structurally similar molecules often have similar properties, the system uses its underlying knowledge of molecular similarity to predict properties of new molecules more efficiently. 

    “Once we have this grammar as a representation for all the different molecules, we can use it to boost the process of property prediction,” Guo says.

    The system learns the production rules for a molecular grammar using reinforcement learning — a trial-and-error process where the model is rewarded for behavior that gets it closer to achieving a goal.

    But because there could be billions of ways to combine atoms and substructures, the process to learn grammar production rules would be too computationally expensive for anything but the tiniest dataset.

    The researchers decoupled the molecular grammar into two parts. The first part, called a metagrammar, is a general, widely applicable grammar they design manually and give the system at the outset. Then it only needs to learn a much smaller, molecule-specific grammar from the domain dataset. This hierarchical approach speeds up the learning process.

    Big results, small datasets

    In experiments, the researchers’ new system simultaneously generated viable molecules and polymers, and predicted their properties more accurately than several popular machine-learning approaches, even when the domain-specific datasets had only a few hundred samples. Some other methods also required a costly pretraining step that the new system avoids.

    The technique was especially effective at predicting physical properties of polymers, such as the glass transition temperature, which is the temperature required for a material to transition from solid to liquid. Obtaining this information manually is often extremely costly because the experiments require extremely high temperatures and pressures.

    To push their approach further, the researchers cut one training set down by more than half — to just 94 samples. Their model still achieved results that were on par with methods trained using the entire dataset.

    “This grammar-based representation is very powerful. And because the grammar itself is a very general representation, it can be deployed to different kinds of graph-form data. We are trying to identify other applications beyond chemistry or material science,” Guo says.

    In the future, they also want to extend their current molecular grammar to include the 3D geometry of molecules and polymers, which is key to understanding the interactions between polymer chains. They are also developing an interface that would show a user the learned grammar production rules and solicit feedback to correct rules that may be wrong, boosting the accuracy of the system.

    This work is funded, in part, by the MIT-IBM Watson AI Lab and its member company, Evonik. More

  • in

    A better way to study ocean currents

    To study ocean currents, scientists release GPS-tagged buoys in the ocean and record their velocities to reconstruct the currents that transport them. These buoy data are also used to identify “divergences,” which are areas where water rises up from below the surface or sinks beneath it.

    By accurately predicting currents and pinpointing divergences, scientists can more precisely forecast the weather, approximate how oil will spread after a spill, or measure energy transfer in the ocean. A new model that incorporates machine learning makes more accurate predictions than conventional models do, a new study reports.

    A multidisciplinary research team including computer scientists at MIT and oceanographers has found that a standard statistical model typically used on buoy data can struggle to accurately reconstruct currents or identify divergences because it makes unrealistic assumptions about the behavior of water.

    The researchers developed a new model that incorporates knowledge from fluid dynamics to better reflect the physics at work in ocean currents. They show that their method, which only requires a small amount of additional computational expense, is more accurate at predicting currents and identifying divergences than the traditional model.

    This new model could help oceanographers make more accurate estimates from buoy data, which would enable them to more effectively monitor the transportation of biomass (such as Sargassum seaweed), carbon, plastics, oil, and nutrients in the ocean. This information is also important for understanding and tracking climate change.

    “Our method captures the physical assumptions more appropriately and more accurately. In this case, we know a lot of the physics already. We are giving the model a little bit of that information so it can focus on learning the things that are important to us, like what are the currents away from the buoys, or what is this divergence and where is it happening?” says senior author Tamara Broderick, an associate professor in MIT’s Department of Electrical Engineering and Computer Science (EECS) and a member of the Laboratory for Information and Decision Systems and the Institute for Data, Systems, and Society.

    Broderick’s co-authors include lead author Renato Berlinghieri, an electrical engineering and computer science graduate student; Brian L. Trippe, a postdoc at Columbia University; David R. Burt and Ryan Giordano, MIT postdocs; Kaushik Srinivasan, an assistant researcher in atmospheric and ocean sciences at the University of California at Los Angeles; Tamay Özgökmen, professor in the Department of Ocean Sciences at the University of Miami; and Junfei Xia, a graduate student at the University of Miami. The research will be presented at the International Conference on Machine Learning.

    Diving into the data

    Oceanographers use data on buoy velocity to predict ocean currents and identify “divergences” where water rises to the surface or sinks deeper.

    To estimate currents and find divergences, oceanographers have used a machine-learning technique known as a Gaussian process, which can make predictions even when data are sparse. To work well in this case, the Gaussian process must make assumptions about the data to generate a prediction.

    A standard way of applying a Gaussian process to oceans data assumes the latitude and longitude components of the current are unrelated. But this assumption isn’t physically accurate. For instance, this existing model implies that a current’s divergence and its vorticity (a whirling motion of fluid) operate on the same magnitude and length scales. Ocean scientists know this is not true, Broderick says. The previous model also assumes the frame of reference matters, which means fluid would behave differently in the latitude versus the longitude direction.

    “We were thinking we could address these problems with a model that incorporates the physics,” she says.

    They built a new model that uses what is known as a Helmholtz decomposition to accurately represent the principles of fluid dynamics. This method models an ocean current by breaking it down into a vorticity component (which captures the whirling motion) and a divergence component (which captures water rising or sinking).

    In this way, they give the model some basic physics knowledge that it uses to make more accurate predictions.

    This new model utilizes the same data as the old model. And while their method can be more computationally intensive, the researchers show that the additional cost is relatively small.

    Buoyant performance

    They evaluated the new model using synthetic and real ocean buoy data. Because the synthetic data were fabricated by the researchers, they could compare the model’s predictions to ground-truth currents and divergences. But simulation involves assumptions that may not reflect real life, so the researchers also tested their model using data captured by real buoys released in the Gulf of Mexico.

    This shows the trajectories of approximately 300 buoys released during the Grand LAgrangian Deployment (GLAD) in the Gulf of Mexico in the summer of 2013, to learn about ocean surface currents around the Deepwater Horizon oil spill site. The small, regular clockwise rotations are due to Earth’s rotation.Credit: Consortium of Advanced Research for Transport of Hydrocarbons in the Environment

    In each case, their method demonstrated superior performance for both tasks, predicting currents and identifying divergences, when compared to the standard Gaussian process and another machine-learning approach that used a neural network. For example, in one simulation that included a vortex adjacent to an ocean current, the new method correctly predicted no divergence while the previous Gaussian process method and the neural network method both predicted a divergence with very high confidence.

    The technique is also good at identifying vortices from a small set of buoys, Broderick adds.

    Now that they have demonstrated the effectiveness of using a Helmholtz decomposition, the researchers want to incorporate a time element into their model, since currents can vary over time as well as space. In addition, they want to better capture how noise impacts the data, such as winds that sometimes affect buoy velocity. Separating that noise from the data could make their approach more accurate.

    “Our hope is to take this noisily observed field of velocities from the buoys, and then say what is the actual divergence and actual vorticity, and predict away from those buoys, and we think that our new technique will be helpful for this,” she says.

    “The authors cleverly integrate known behaviors from fluid dynamics to model ocean currents in a flexible model,” says Massimiliano Russo, an associate biostatistician at Brigham and Women’s Hospital and instructor at Harvard Medical School, who was not involved with this work. “The resulting approach retains the flexibility to model the nonlinearity in the currents but can also characterize phenomena such as vortices and connected currents that would only be noticed if the fluid dynamic structure is integrated into the model. This is an excellent example of where a flexible model can be substantially improved with a well thought and scientifically sound specification.”

    This research is supported, in part, by the Office of Naval Research, a National Science Foundation (NSF) CAREER Award, and the Rosenstiel School of Marine, Atmospheric, and Earth Science at the University of Miami. More

  • in

    Strengthening trust in machine-learning models

    Probabilistic machine learning methods are becoming increasingly powerful tools in data analysis, informing a range of critical decisions across disciplines and applications, from forecasting election results to predicting the impact of microloans on addressing poverty.

    This class of methods uses sophisticated concepts from probability theory to handle uncertainty in decision-making. But the math is only one piece of the puzzle in determining their accuracy and effectiveness. In a typical data analysis, researchers make many subjective choices, or potentially introduce human error, that must also be assessed in order to cultivate users’ trust in the quality of decisions based on these methods.

    To address this issue, MIT computer scientist Tamara Broderick, associate professor in the Department of Electrical Engineering and Computer Science (EECS) and a member of the Laboratory for Information and Decision Systems (LIDS), and a team of researchers have developed a classification system — a “taxonomy of trust” — that defines where trust might break down in a data analysis and identifies strategies to strengthen trust at each step. The other researchers on the project are Professor Anna Smith at the University of Kentucky, professors Tian Zheng and Andrew Gelman at Columbia University, and Professor Rachael Meager at the London School of Economics. The team’s hope is to highlight concerns that are already well-studied and those that need more attention.

    In their paper, published in February in Science Advances, the researchers begin by detailing the steps in the data analysis process where trust might break down: Analysts make choices about what data to collect and which models, or mathematical representations, most closely mirror the real-life problem or question they are aiming to answer. They select algorithms to fit the model and use code to run those algorithms. Each of these steps poses unique challenges around building trust. Some components can be checked for accuracy in measurable ways. “Does my code have bugs?”, for example, is a question that can be tested against objective criteria. Other times, problems are more subjective, with no clear-cut answers; analysts are confronted with numerous strategies to gather data and decide whether a model reflects the real world.

    “What I think is nice about making this taxonomy, is that it really highlights where people are focusing. I think a lot of research naturally focuses on this level of ‘are my algorithms solving a particular mathematical problem?’ in part because it’s very objective, even if it’s a hard problem,” Broderick says.

    “I think it’s really hard to answer ‘is it reasonable to mathematize an important applied problem in a certain way?’ because it’s somehow getting into a harder space, it’s not just a mathematical problem anymore.”

    Capturing real life in a model

    The researchers’ work in categorizing where trust breaks down, though it may seem abstract, is rooted in real-world application.

    Meager, a co-author on the paper, analyzed whether microfinances can have a positive effect in a community. The project became a case study for where trust could break down, and ways to reduce this risk.

    At first look, measuring the impact of microfinancing might seem like a straightforward endeavor. But like any analysis, researchers meet challenges at each step in the process that can affect trust in the outcome. Microfinancing — in which individuals or small businesses receive small loans and other financial services in lieu of conventional banking — can offer different services, depending on the program. For the analysis, Meager gathered datasets from microfinance programs in countries across the globe, including in Mexico, Mongolia, Bosnia, and the Philippines.

    When combining conspicuously distinct datasets, in this case from multiple countries and across different cultures and geographies, researchers must evaluate whether specific case studies can reflect broader trends. It is also important to contextualize the data on hand. For example, in rural Mexico, owning goats may be counted as an investment.

    “It’s hard to measure the quality of life of an individual. People measure things like, ‘What’s the business profit of the small business?’ Or ‘What’s the consumption level of a household?’ There’s this potential for mismatch between what you ultimately really care about, and what you’re measuring,” Broderick says. “Before we get to the mathematical level, what data and what assumptions are we leaning on?”

    With data on hand, analysts must define the real-world questions they seek to answer. In the case of evaluating the benefits of microfinancing, analysts must define what they consider a positive outcome. It is standard in economics, for example, to measure the average financial gain per business in communities where a microfinance program is introduced. But reporting an average might suggest a net positive effect even if only a few (or even one) person benefited, instead of the community as a whole.

    “What you really wanted was that a lot of people are benefiting,” Broderick says. “It sounds simple. Why didn’t we measure the thing that we cared about? But I think it’s really common that practitioners use standard machine learning tools, for a lot of reasons. And these tools might report a proxy that doesn’t always agree with the quantity of interest.”

    Analysts may consciously or subconsciously favor models they are familiar with, especially after investing a great deal of time learning their ins and outs. “Someone might be hesitant to try a nonstandard method because they might be less certain they will use it correctly. Or peer review might favor certain familiar methods, even if a researcher might like to use nonstandard methods,” Broderick says. “There are a lot of reasons, sociologically. But this can be a concern for trust.”

    Final step, checking the code 

    While distilling a real-life problem into a model can be a big-picture, amorphous problem, checking the code that runs an algorithm can feel “prosaic,” Broderick says. But it is another potentially overlooked area where trust can be strengthened.

    In some cases, checking a coding pipeline that executes an algorithm might be considered outside the purview of an analyst’s job, especially when there is the option to use standard software packages.

    One way to catch bugs is to test whether code is reproducible. Depending on the field, however, sharing code alongside published work is not always a requirement or the norm. As models increase in complexity over time, it becomes harder to recreate code from scratch. Reproducing a model becomes difficult or even impossible.

    “Let’s just start with every journal requiring you to release your code. Maybe it doesn’t get totally double-checked, and everything isn’t absolutely perfect, but let’s start there,” Broderick says, as one step toward building trust.

    Paper co-author Gelman worked on an analysis that forecast the 2020 U.S. presidential election using state and national polls in real-time. The team published daily updates in The Economist magazine, while also publishing their code online for anyone to download and run themselves. Throughout the season, outsiders pointed out both bugs and conceptual problems in the model, ultimately contributing to a stronger analysis.

    The researchers acknowledge that while there is no single solution to create a perfect model, analysts and scientists have the opportunity to reinforce trust at nearly every turn.

    “I don’t think we expect any of these things to be perfect,” Broderick says, “but I think we can expect them to be better or to be as good as possible.” More

  • in

    Improving health outcomes by targeting climate and air pollution simultaneously

    Climate policies are typically designed to reduce greenhouse gas emissions that result from human activities and drive climate change. The largest source of these emissions is the combustion of fossil fuels, which increases atmospheric concentrations of ozone, fine particulate matter (PM2.5) and other air pollutants that pose public health risks. While climate policies may result in lower concentrations of health-damaging air pollutants as a “co-benefit” of reducing greenhouse gas emissions-intensive activities, they are most effective at improving health outcomes when deployed in tandem with geographically targeted air-quality regulations.

    Yet the computer models typically used to assess the likely air quality/health impacts of proposed climate/air-quality policy combinations come with drawbacks for decision-makers. Atmospheric chemistry/climate models can produce high-resolution results, but they are expensive and time-consuming to run. Integrated assessment models can produce results for far less time and money, but produce results at global and regional scales, rendering them insufficiently precise to obtain accurate assessments of air quality/health impacts at the subnational level.

    To overcome these drawbacks, a team of researchers at MIT and the University of California at Davis has developed a climate/air-quality policy assessment tool that is both computationally efficient and location-specific. Described in a new study in the journal ACS Environmental Au, the tool could enable users to obtain rapid estimates of combined policy impacts on air quality/health at more than 1,500 locations around the globe — estimates precise enough to reveal the equity implications of proposed policy combinations within a particular region.

    “The modeling approach described in this study may ultimately allow decision-makers to assess the efficacy of multiple combinations of climate and air-quality policies in reducing the health impacts of air pollution, and to design more effective policies,” says Sebastian Eastham, the study’s lead author and a principal research scientist at the MIT Joint Program on the Science and Policy of Global Change. “It may also be used to determine if a given policy combination would result in equitable health outcomes across a geographical area of interest.”

    To demonstrate the efficiency and accuracy of their policy assessment tool, the researchers showed that outcomes projected by the tool within seconds were consistent with region-specific results from detailed chemistry/climate models that took days or even months to run. While continuing to refine and develop their approaches, they are now working to embed the new tool into integrated assessment models for direct use by policymakers.

    “As decision-makers implement climate policies in the context of other sustainability challenges like air pollution, efficient modeling tools are important for assessment — and new computational techniques allow us to build faster and more accurate tools to provide credible, relevant information to a broader range of users,” says Noelle Selin, a professor at MIT’s Institute for Data, Systems and Society and Department of Earth, Atmospheric and Planetary Sciences, and supervising author of the study. “We are looking forward to further developing such approaches, and to working with stakeholders to ensure that they provide timely, targeted and useful assessments.”

    The study was funded, in part, by the U.S. Environmental Protection Agency and the Biogen Foundation. More