MIT EECS 6.S891/6.S893/12.S992 AI for Climate Action

Spring 2026

Course Overview

Description: Examines applications of artificial intelligence and machine learning to climate change mitigation, adaptation, and monitoring. Introduces the physical science of climate change, data-driven modeling and observation, and approaches for decision-making in domains such as climate modeling, biodiversity, and energy systems. Includes common (‘merged’) lectures on climate fundamentals followed by domain-specific sections (‘forks’) focusing on advanced methods such as physics-informed learning, data assimilation, and uncertainty quantification. Within each ‘fork’, students present, critique, and lead discussions of current research papers and develop a written research proposal applying machine learning methods to the track’s focus area. ‘Merged’ sessions later in the term synthesize lessons and foster exchange across domains. Both graduate and undergraduate students are encouraged to register.

Pre-requisites: 6.3900 or 6.8300/1 or 6.7960 or equivalent or permission of instructor.

---

Course Information

 

 

---

Class Schedule: AI for Climate Action

** Class schedule is subject to change **

Tracks (Weeks 5-10): 12.S992: Climate Models | 6.S891: Biodiversity and Environment | 6.S893 Power & Energy Systems

Week / Date	Track / Focus	Topic	Instructor
Week 1
Mon 02/02	Merged	Logistics Intro to AI and Climate Change (adaptation, mitigation)	Priya
Wed 02/04	Merged	Application-driven innovation in Machine Learning	Sara
Week 2
Mon 02/09	Merged	Impacts, Adaptation and Vulnerability (IPCC WG2) The natural world	Sara
Wed 02/11	Merged	Mitigation of Climate Change (IPCC WG3) Human impacts and infrastructure	Priya
Week 3
Tue 02/17 (MIT Monday)	Merged	The Physical Science Basis (IPCC WG1) Data methods Models and observations	Abigail
Wed 02/18	Merged	Foundation models for Climate	Abigail
Week 4 - Forked Lessons
Mon 02/23 & Wed 02/25	Climate Models	Introduction to Earth System Models	Abigail
	Biodiversity	Introduction to biodiversity, ecosystems, and evolution	Sara
	Power & Energy	Introduction to power and energy systems	Priya
Week 5 - Forked Lessons
Mon 03/02 & Wed 03/04	Climate Models	Future climate scenarios & multi-model ensembles Guest: Raffaele Ferrari	Abigail
	Biodiversity	Monitoring and Evaluation	Sara
	Power & Energy	State estimation and predictive maintenance (physics-informed ML, anomaly detection)	Priya
Week 6 - Forked Lessons
Mon 03/09 & Wed 03/11	Climate Models	Parameterizing subgrid effects	Abigail
	Biodiversity	Distribution shift and bias	Sara
	Power & Energy	Short-term forecasting (interpretable ML, uncertainty quantification)	Priya
Week 7 - Forked Lessons
Mon 03/16 & Wed 03/18	Climate Models	Synthesising & interpreting data sources; data assimilation	Abigail
	Biodiversity	Long tails and anomalies	Sara
	Power & Energy	Long-term forecasting and scenario generation (physics-informed ML, generative AI)	Priya
Week 8 - Spring Break
Week 9 - Forked Lessons
Mon 03/30 & Wed 04/01	Climate Models	Foundation models and emulators of climate models	Abigail
	Biodiversity	Multimodality	Sara
	Power & Energy	Surrogates for power grid optimization (physics- informed ML, ML for optimization)	Priya
Week 10 - Forked Lessons
Mon 04/06 & Wed 04/08	Climate Models	Uncertainty quantification and estimating extreme events; scenario-dependence of future changes in extremes	Abigail
	Biodiversity	Human-AI participation and integrating knowledge	Sara
	Power & Energy	Power systems control (safe RL, RL + control)	Priya
Week 11 - Forked Lessons
Mon 04/13 & Wed 04/15	All Tracks	Project Presentations	Abigail/Sara/Priya
Week 12 - Forked Lessons
Mon (holiday) Wed 04/22	All Tracks	Project Presentations	Abigail/Sara/Priya
Week 13
Mon 04/27	Merged	Benchmarks & Evaluation	Sara
Wed 04/29	Merged	Data-centric research	Abigail
Week 14
Mon 05/04	Merged	Incorporation of domain knowledge	Priya
Wed 05/06	Merged	Guest Lecture: TBD	(Host: Priya)
Week 15
Mon 05/11	Merged	"Now what?" Opportunities to work on climate-related issues beyond the classroom: Moderated Panel	(Moderator: Sara)

 

Course Project

Details and requirements will be posted soon.

AI assistants policy (honor code)

• You are not allowed to ask AI to generate your project ideas or the content for the project, we hope that by participating in this class you have lots of ideas and context to be able to formulate a proposed project well.
• You are allowed to with with AI to discover relevant literature, and to co-edit prose (with the strong request that you don’t generate a bulleted list, ask AI to expand on it, and submit it without iteration! Because this usually reads really badly and we don’t want to read annoying AI-generated overhyped text 😃 )