Advances in machine learning for big Earth observation data analysis

ABSTRACT: This special session will explore recent advancements in analysing big Earth observation data,  focusing on the critical role of training data in achieving high classification accuracy. Given the substantial  effort required to select and acquire quality training samples for big data, this session will explore advanced  learning methods designed to optimise this process. Topics will include self-supervised and semi-supervised  learning, transfer learning, deep continual learning, and domain adaptation. Our speakers will present  ongoing research that showcases state-of-the-art approaches in these areas.