Google and NASA’s Jet Propulsion Laboratory (JPL) have introduced MAPL-EMIT, a deep-learning model designed to detect, quantify, and localize methane plumes across the globe using data from NASA’s EMIT satellite instrument. The announcement was made on September 9, 2026, according to Google.
How MAPL-EMIT Works
The model was trained on 3.6 million physics-simulated methane plumes. According to Google, MAPL-EMIT detects 50% more plumes than human experts and identifies more than 23,000 additional plumes globally. This includes plumes at 24 of the world’s 25 largest-emitting sites.
Significance for Global Methane Monitoring
By leveraging deep learning and satellite data, MAPL-EMIT offers a new tool for tracking methane emissions worldwide. The ability to detect, quantify, and localize plumes at this scale could enhance understanding of methane sources and support efforts to address them.
