Explainable AI for Earth Observation: Current Methods, Open Challenges, and Opportunities
It reviews existing techniques for improving explainability in remote sensing, which is an incremental contribution aimed at researchers and practitioners in Earth observation.
The paper surveys the current state of explainable AI methods applied to Earth observation, addressing the lack of interpretability in deep learning for remote sensing, but does not present new experimental results or concrete numbers.
Deep learning has taken by storm all fields involved in data analysis, including remote sensing for Earth observation. However, despite significant advances in terms of performance, its lack of explainability and interpretability, inherent to neural networks in general since their inception, remains a major source of criticism. Hence it comes as no surprise that the expansion of deep learning methods in remote sensing is being accompanied by increasingly intensive efforts oriented towards addressing this drawback through the exploration of a wide spectrum of Explainable Artificial Intelligence techniques. This chapter, organized according to prominent Earth observation application fields, presents a panorama of the state-of-the-art in explainable remote sensing image analysis.