Welcome to the Climate Change AI Wiki

The aim of this wiki is to help foster impactful research to tackle the climate crisis, by identifying problems where ML can be useful. This wiki is maintained and moderated by members of CCAI.

The scope of solutions to address the climate crisis goes far beyond the intersection we address here; the problems of climate change require cooperation between diverse stakeholders, and action in many forms. But whether you are machine learning researcher looking to apply your skills to combat climate change, a young researcher aiming to have impact in your career, a practitioner in one of these areas looking to apply ML to your problem, or for any other reason are interested in the intersection of climate change and ML, we hope these pages can help inform and facilitate your research!

We welcome your contributions and feedback! See editing guidelines here.

General Resources

 * General Resources page
 * Tackling Climate Change with Machine Learning review paper

Topics by Application Area
The pages below provide overviews and resources on topics at the intersection of climate change and machine learning. Mitigation refers to reducing emissions in order to lessen the extent of climate change, while adaptation refers to preparing for the effects of climate change. We also provide overviews of various tools for action -- such as policy, economics, education, and finance -- that can help enable mitigation and adaptation strategies.

Mitigation

 * Electricity systems
 * Transportation
 * Buildings and cities
 * Industry
 * Agriculture
 * Forestry and other land use
 * CO2 removal and negative emissions technologies

Adaptation

 * Climate science
 * Climate change adaptation
 * Biodiversity
 * Solar geoengineering

Tools for Action

 * Public policy and decision science
 * Economics
 * Education
 * Climate finance
 * Tools for individuals

Topics by Cross-cutting Theme
There are several cross-cutting themes and research problems that recur across the topic areas above.


 * Accelerated science
 * Remote sensing
 * Predictive maintenance
 * Efficient sensing
 * Surrogate modeling