--- id: "2026-09-09-google-nasa-jpl-mapl-emit-methane" url: "https://postcutoff.com/e/2026-09-09-google-nasa-jpl-mapl-emit-methane/" as_of: "2026-11-22T13:32:00+01:00" date: "2026-09-09" date_precision: day category: science importance: 3 confidence: high status: [Result confirmed] verification: Peer-reviewed sources: 5 editor: human editor human_review: null version: "2026-10-07" --- As of: 2026-11-22 13:32 CET. Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/ Canonical page: https://postcutoff.com/e/2026-09-09-google-nasa-jpl-mapl-emit-methane/ # Google and NASA JPL release MAPL-EMIT, an AI model that maps methane plumes worldwide Full title: Google and NASA JPL release MAPL-EMIT, an AI model that maps methane plumes worldwide from the EMIT space instrument (PNAS) On Sept 9, 2026 Google Research and NASA's Jet Propulsion Laboratory published MAPL-EMIT (Methane Analysis and Plume Localization with EMIT) in PNAS. The deep-learning model detects, quantifies and localizes methane plumes in hyperspectral data from NASA's EMIT instrument on the ISS. It finds 50% more plumes than human experts and more than 23,000 additional plumes globally, and the database, models and code are open. ## Key facts - Trained on 3.6 million physics-simulated methane plumes - Detects 50% more plumes than human experts; 23,000+ additional plumes identified globally - Found plumes at 24 of the world's 25 largest-emitting landfills - Paper: PNAS, DOI 10.1073/pnas.2612145123 - Released: global plume database and app on Google Earth Engine, models on Kaggle, inference code on GitHub (google-research/mapl) ## What happened EMIT was built to map surface minerals in dust-source regions, but its hyperspectral bands also pick up methane's spectral signature. Google trained a detector on simulated plumes and ran it over the whole archive. ## Why it matters Methane is a strong short-term warming gas (Google cites about 30x the warming potential of CO2 over 100 years). Automated global plume mapping with open data lets regulators and companies find and fix leaks, landfills and super-emitters at scale. ## Your AI and this story - GPT-6.2 Astra (training cutoff May 2026): 101 days after its cutoff - Claude Opus 5.5 (training cutoff June 2026): 71 days after its cutoff - Gemini 4 Hydrogen (training cutoff March 2026): 162 days after its cutoff - Grok 4.7 (training cutoff May 2026): 101 days after its cutoff ## Sources 1. [Google blog: A new deep learning model maps global methane emissions from space](https://blog.google/innovation-and-ai/models-and-research/google-research/mapping-global-methane-emissions-from-space/) (blog.google, official) 2. [PNAS paper (DOI 10.1073/pnas.2612145123)](https://www.pnas.org/doi/10.1073/pnas.2612145123) (pnas.org, paper) 3. [GitHub: google-research/mapl](https://github.com/google-research/mapl) (github.com, code) 4. [Earth Engine app: MAPL-EMIT plumes](https://nature-trace.projects.earthengine.app/view/mapl-emit) (nature-trace.projects.earthengine.app, official) 5. [Unite.AI: Google and NASA JPL unveil AI model mapping global methane plumes](https://www.unite.ai/google-and-nasa-jpl-unveil-ai-model-mapping-global-methane-plumes/) (unite.ai, press) ## Changes - 2026-10-01 (filed): Created