{"id":362566,"date":"2025-10-15T15:25:36","date_gmt":"2025-10-15T09:55:36","guid":{"rendered":"https:\/\/www.technologyforyou.org\/?p=362566"},"modified":"2025-10-15T15:25:36","modified_gmt":"2025-10-15T09:55:36","slug":"fighting-for-the-health-of-the-planet-with-ai","status":"publish","type":"post","link":"https:\/\/www.technologyforyou.org\/fighting-for-the-health-of-the-planet-with-ai\/","title":{"rendered":"Fighting for the health of the planet with AI"},"content":{"rendered":"
\n
\n
\"\"
Caption:\u201cMachine learning is already really widely used for things like solar power forecasting, which is a prerequisite to managing and balancing power grids,\u201d says EECS assistant professor and LIDS PI Priya Donti. \u201cMy focus is: How do you improve the algorithms for actually balancing power grids in the face of a range of time-varying renewables?\u201d Credits : Photo : Adam Glanzman<\/figcaption><\/figure>\n

Source: MIT Press News | Michaela Jarvis<\/span>\u00a0|<\/span>\u00a0MIT Laboratory for Information and Decision Systems.<\/span><\/p>\n

Assistant Professor Priya Donti\u2019s research applies machine learning to optimize renewable energy.<\/span><\/strong><\/p>\n<\/div>\n<\/div>\n

\n
\n
For Priya Donti, childhood trips to India were more than an opportunity to visit extended family. The biennial journeys activated in her a motivation that continues to shape her research and her teaching.<\/p>\n

Contrasting her family home in Massachusetts, Donti \u2014 now the Silverman Family Career Development Professor in the MIT Department of Electrical Engineering and Computer Science (EECS) and a principal investigator at the MIT Laboratory for Information and Decision Systems \u2014 was struck by the disparities in how people live.<\/p>\n

\u201cIt was very clear to me the extent to which inequity is a rampant issue around the world,\u201d Donti says. \u201cFrom a young age, I knew that I definitely wanted to address that issue.\u201d<\/p>\n

That motivation was further stoked by a high school biology teacher, who focused his class on climate and sustainability.<\/p>\n

\n
\u201cMachine learning is already really widely used for things like solar power forecasting, which is a prerequisite to managing and balancing power grids,\u201d says EECS assistant professor and LIDS PI Priya Donti. \u201cMy focus is: How do you improve the algorithms for actually balancing power grids in the face of a range of time-varying renewables?\u201d<\/span><\/div>\n<\/div>\n
\n
<\/div>\n<\/div>\n

\u201cWe learned that climate change, this huge, important issue, would exacerbate inequity,\u201d Donti says. \u201cThat really stuck with me and put a fire in my belly.\u201d<\/p>\n

So, when Donti enrolled at Harvey Mudd College, she thought she would direct her energy toward the study of chemistry or materials science to create next-generation solar panels.<\/p>\n

Those plans, however, were jilted. Donti \u201cfell in love\u201d with computer science, and then discovered work by researchers in the United Kingdom who were arguing that artificial intelligence and machine learning would be essential to help integrate renewables into power grids.<\/p>\n

\u201cIt was the first time I\u2019d seen those two interests brought together,\u201d she says. \u201cI got hooked and have been working on that topic ever since.\u201d<\/p>\n

Pursuing a PhD at Carnegie Mellon University, Donti was able to design her degree to include computer science and public policy. In her research, she explored the need for fundamental algorithms and tools that could manage, at scale, power grids relying heavily on renewables.<\/p>\n

\u201cI wanted to have a hand in developing those algorithms and tool kits by creating new machine learning techniques grounded in computer science,\u201d she says. \u201cBut I wanted to make sure that the way I was doing the work was grounded both in the actual energy systems domain and working with people in that domain\u201d to provide what was actually needed.<\/p>\n

While Donti was working on her PhD, she co-founded a nonprofit called Climate Change AI. Her objective, she says, was to help the community of people involved in climate and sustainability \u2014 \u201cbe they computer scientists, academics, practitioners, or policymakers\u201d \u2014 to come together and access resources, connection, and education \u201cto help them along that journey.\u201d<\/p>\n

\u201cIn the climate space,\u201d she says, \u201cyou need experts in particular climate change-related sectors, experts in different technical and social science tool kits, problem owners, affected users, policymakers who know the regulations \u2014 all of those \u2014 to have on-the-ground scalable impact.\u201d<\/p>\n

When Donti came to MIT in September 2023, it was not surprising that she was drawn by its initiatives directing the application of computer science toward society\u2019s biggest problems, especially the current threat to the health of the planet.<\/p>\n

\u201cWe\u2019re really thinking about where technology has a much longer-horizon impact and how technology, society, and policy all have to work together,\u201d Donti says. \u201cTechnology is not just one-and-done and monetizable in the context of a year.\u201d<\/p>\n

Her work uses deep learning models to incorporate the physics and hard constraints of electric power systems that employ renewables for better forecasting, optimization, and control.<\/p>\n

\u201cMachine learning is already really widely used for things like solar power forecasting, which is a prerequisite to managing and balancing power grids,\u201d she says. \u201cMy focus is, how do you improve the algorithms for actually balancing power grids in the face of a range of time-varying renewables?\u201d<\/p>\n

Among Donti\u2019s breakthroughs is a promising solution for power grid operators to be able to optimize for cost, taking into account the actual physical realities\u00a0of the grid, rather than relying on approximations. While the solution is not yet deployed, it appears to work 10 times faster, and far more cheaply, than previous technologies, and has attracted the attention of grid operators.<\/p>\n

Another technology she is developing works to provide data that can be used in training machine learning systems for power system optimization. In general, much data related to the systems is private, either because it is proprietary or because of security concerns. Donti and her research group are working to create synthetic data and benchmarks that, Donti says, \u201ccan help to expose some of the underlying problems\u201d in making power systems more efficient.<\/p>\n

\u201cThe question is,\u201d Donti says, \u201ccan we bring our datasets to a point such that they are just hard enough to drive progress?\u201d<\/p>\n

For her efforts, Donti has been awarded the U.S. Department of Energy Computational Science Graduate Fellowship and the NSF Graduate Research Fellowship. She was recognized as part of\u00a0MIT Technology Review<\/em>\u2019s 2021 list of \u201c35 Innovators Under 35\u201d and Vox\u2019s 2023 \u201cFuture Perfect 50.\u201d<\/p>\n

Next spring, Donti will co-teach a class called AI for Climate Action with Sara Beery, EECS assistant professor, whose focus is AI for biodiversity and ecosystems, and Abigail Bodner, an assistant professor in Earth, Atmospheric and Planetary Sciences, holding an MIT Schwarzman College of Computing shared position with EECS.<\/p>\n

\u201cWe\u2019re all super-excited about it,\u201d Donti says.<\/p>\n

Coming to MIT, Donti says, \u201cI knew that there would be an ecosystem of people who really cared, not just about success metrics like publications and citation counts, but about the impact of our work on society.\u201d<\/p>\n<\/article>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

Source: MIT Press News | Michaela Jarvis\u00a0|\u00a0MIT Laboratory for Information and Decision Systems. Assistant Professor Priya Donti\u2019s research applies machine learning to optimize renewable energy. For Priya Donti, childhood trips to India were more than an opportunity to visit extended family. The biennial journeys activated in her a motivation that continues to shape her research […]<\/p>\n","protected":false},"author":1,"featured_media":362574,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[9231],"tags":[37578],"class_list":{"0":"post-362566","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-top-stories","8":"tag-fighting-for-the-health-of-the-planet-with-ai"},"_links":{"self":[{"href":"https:\/\/www.technologyforyou.org\/wp-json\/wp\/v2\/posts\/362566","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.technologyforyou.org\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.technologyforyou.org\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.technologyforyou.org\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.technologyforyou.org\/wp-json\/wp\/v2\/comments?post=362566"}],"version-history":[{"count":0,"href":"https:\/\/www.technologyforyou.org\/wp-json\/wp\/v2\/posts\/362566\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.technologyforyou.org\/wp-json\/wp\/v2\/media\/362574"}],"wp:attachment":[{"href":"https:\/\/www.technologyforyou.org\/wp-json\/wp\/v2\/media?parent=362566"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.technologyforyou.org\/wp-json\/wp\/v2\/categories?post=362566"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.technologyforyou.org\/wp-json\/wp\/v2\/tags?post=362566"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}