AI4CH4: An End-to-End AI Framework for Methane Plume Detection and Quantification using Satellite Imagery

AI4CH4 is using the power of Artificial Intelligence and Earth Observation data to detect and quantify methane emission. 

 

EO & AI for Global Transparency

 

Methane is amongst the most significant contributors to global warming and timely and accurate identification and quantification of methane emissions remains challenging.

 

Working in collaboration with FluxLab and Harvard University with support from GHGSat, AI4CH4 will address a critical gap in the current methane monitoring landscape and provide Advanced AI model for an end-to-end plume detection and quantification, addressing the limitations of conventional techniques.

AI4CH4 Project Objectives

Benchmark dataset
Benchmark dataset

Create a comprehensive benchmark dataset of methane plumes using satellite and field data.

Satellite emission monitoring
Satellite emission monitoring

Advance the understanding of methane emission and atmospheric processes using cutting edge remote sensing techniques and AI models.

AI development
AI development

Improve the accuracy of methane detection and quantification by developing deep learning models for different satellite missions with different sensitivities to methane emission.

AI4CH4 Project Partners

PUBLICATIONS

Mahdianpari, M., Radman, A., Varon, D.J., Mohammadimanesh, F., 2026. SAM4CH4: Zero-Shot Methane Plume Mapping With Segment Anything and Vision-Language Models. IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing 19, 2273–2284. https://doi.org/10.1109/JSTARS.2025.3642040

Marjani, M., Mahdianpari, M., Varon, D.J., Mohammadimanesh, F., 2025. The integration of vision transformers and SAM for automated methane super-emitter detection using TROPOMI data. Journal of Environmental Management 393, 127034. https://doi.org/10.1016/j.jenvman.2025.127034

Mohammadimanesh, F., Mahdianpari, M., Radman, A., Varon, D., Hemati, M., Marjani, M., 2025. Advancements in satellite-based methane point source monitoring: A systematic review. ISPRS Journal of Photogrammetry and Remote Sensing 224, 94–112. https://doi.org/10.1016/j.isprsjprs.2025.03.020

Radman, A., Mahdianpari, M., Varon, D.J., Mohammadimanesh, F., 2023. S2MetNet: A novel dataset and deep learning benchmark for methane point source quantification using Sentinel-2 satellite imagery. Remote Sensing of Environment 295, 113708. https://doi.org/10.1016/j.rse.2023.113708

AI4CH4 Project Progress

Engagement & Collaboration Opportunities

We actively participate in and organize events to foster collaboration and knowledge exchange. Join us at the following upcoming events:

Upcoming Events:

  • Methane Emission Monitoring Session ISPRS and the CRS 2026, June 2026

Past Events:

  • C-CORE – AI4CH4 – Final Review Meeting, January 2026
  • Northwest Territories (NWT) Landscape Carbon Workshop, February 2025
  • 40th International Symposium on Remote Sensing of Environment (ISRSE-40), March 2025
  • SMART-CH4 Meeting, April 2025
  • CSA EO in Orbit: Scientific Workshop, April 2025
  • CSA smartEarth Workshop, May 2025
  • ESA Living Planet Symposium 2025, June 2025
  • Arctic Development Expo, June 2025
  • 46th Canadian Symposium on Remote Sensing, June 2025
  • ESA 3rd Cluster Coordination Meeting, November 2025
  • Investigating Methane for Climate Action (IM4CA) Meeting, December 2025