AI-Powered Methane Detection Models

Google and NASA's Jet Propulsion Laboratory introduced MAPL-EMIT, an AI model that tracks methane emissions globally from space using data from NASA's EMIT instrument. Trained on 3.6 million physics-simulated methane plumes, the model detects 50% more plumes than human experts, identifying more than 23,000 additional plumes worldwide, including 24 of the 25 largest-emitting landfills.

Methane has 30 times the warming potential of carbon dioxide over a 100-year period, making faster detection critical for targeted climate mitigation. Google released the global plume database on Earth Engine alongside a visualization app, with open-source models on Kaggle and inference tools on GitHub to support researchers, policymakers, and operators.

MAPL-EMIT signals how AI-powered satellite analysis could accelerate the identification and addressing of major emission sources at scale.