A new machine-learning model makes more accurate predictions about ocean currents, which could help with tracking plastic pollution and oil spills, and aid in search and rescue.

SoftZoo is a soft robot co-design platform that can test optimal shapes and sizes for robotic performance in different environments.

Associate Professor Tamara Broderick and colleagues build a “taxonomy of trust” to identify where in data analysis processes confidence in its results might break down.

Researchers are turning to computer models, drones and other methods to improve tornado forecasting.

Computational chemists design better ways of discovering and designing materials for energy applications.

New modeling tool enables rapid design of effective and equitable policy combinations.

Analyses show stakeholders of all levels must get involved in decarbonizing pavements to reach climate goals.

A new tool brings the benefits of AI programming to a much broader class of problems.

A method for quickly predicting the forces needed to push objects through soft, granular materials could help engineers drive robots or anchor ships.

Comparing models of working memory with real-world data, MIT researchers find information resides not in persistent neural activity, but in the pattern of its connections.