Google Research has developed a deep-learning framework called MAPL-EMIT to automate the detection and quantification of methane plumes from satellite data. This new approach, detailed in a PNAS publication, significantly improves upon existing methods by achieving an 84% recall rate on expert-annotated plumes. To facilitate broader use, Google is releasing the trained model, a global plume database, and an inference library. AI
IMPACT Enables more accurate and scalable tracking of potent greenhouse gas emissions, supporting global climate action efforts.
RANK_REASON Publication of a new deep-learning framework for methane detection in a peer-reviewed journal. [lever_c_demoted from research: ic=1 ai=1.0]
Read on Google AI / Research →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
