Explainable AI for Earth Observation: Current Methods, Open Challenges, and Opportunities
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 38 of its 149 references that are in the map. First posted on arXiv 8 Nov 2023.
Builds on
38 of 149 references.
References · 38
- 2017Mask R-CNNcited by 7,259
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
- 2017Squeeze-and-Excitation Networkscited by 4,763
- 2017Axiomatic Attribution for Deep Networkscited by 3,350
- 2018YOLOv3: An Incremental Improvementcited by 2,652
- 2015Learning Deep Features for Discriminative Localizationcited by 2,430
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
- 2017Deep Image Priorcited by 1,097
- 2014Striving for Simplicity: The All Convolutional Netcited by 983
26 more
- 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
- 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
- 2017Counterfactual Fairnesscited by 802
- 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 622
- 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
- 2017Methods for Interpreting and Understanding Deep Neural Networkscited by 342
- 2019Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmarkcited by 339
- 2016Top-down Neural Attention by Excitation Backpropcited by 318
- 2016Model-Agnostic Interpretability of Machine Learningcited by 219
- 2019Explainable Machine Learning for Scientific Insights and Discoveriescited by 165
- 2017Interpretable Convolutional Neural Networkscited by 161
- 2017Deep learning in remote sensing: a reviewcited by 128
- 2019CARAFE: Content-Aware ReAssembly of FEaturescited by 119
- 2016A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learningcited by 86
- 2018Multi-Temporal Land Cover Classification with Sequential Recurrent Encoderscited by 61
- 2021Deep Gradient Projection Networks for Pan-sharpeningcited by 44
- 2019Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Netcited by 35
- 2021CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Imagescited by 29
- 2021Endmember-Guided Unmixing Network (EGU-Net): A General Deep Learning Framework for Self-Supervised Hyperspectral Unmixingcited by 29
- 2021Towards a Collective Agenda on AI for Earth Science Data Analysiscited by 27
- 2021Evaluating explainable artificial intelligence methods for multi-label deep learning classification tasks in remote sensingcited by 26
- 2020Spectral Response Function Guided Deep Optimization-driven Network for Spectral Super-resolutioncited by 12
- 2021Coupling Model-Driven and Data-Driven Methods for Remote Sensing Image Restoration and Fusioncited by 11
- 2021Embedded Self-Distillation in Compact Multi-Branch Ensemble Network for Remote Sensing Scene Classificationcited by 8
- 2021Explainable Systematic Analysis for Synthetic Aperture Sonar Imagerycited by 3
- 2022Unmixing based PAN guided fusion network for hyperspectral imagerycited by 2
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.