The Working Group on Machine Learning Applications in Remote Sensing (MLRS) to foster international collaboration, to exchange knowledge, methodologies, and to share high-quality dataset of machine learning techniques applied to satellite remote sensing and radiative transfer physics.

Leads/Contacts

Co-Chairs: 
Feng Zheng (Fudan University), fengzhang@fudan.edu.cn
Hironobu Iwabuchi (Tohoku University), hiroiwa@tohoku.ac.jp
Jérôme Riedi (University of Lille), jerome.riedi@univ-lille.fr
Sebastian Schmidt (University of Colorado Boulder) Sebastian.Schmidt@lasp.colorado.edu

Mission Statement

Machine Learning (ML) and Artificial Intelligence (AI) has brought significant changes to remote sensing. The main objective of this working group is to promote the development of machine learning methods in areas such as satellite remote sensing retrieval methods, and to share ideas, techniques, and high-quality datasets for machine learning in radiative transfer and remote sensing.

Key Activities

1) ML & Physics Integration: Accelerating radiative transfer computations and hybrid physics-AI retrieval algorithms.
2) Satellite Remote Sensing: Advanced ML applications for cloud detection, atmospheric property retrieval, and surface-atmosphere characterization.
3) Validation & Benchmarking: Developing standardized evaluation datasets and uncertainty quantification methods.