mlsanityData to 14 Oct 2026

Evaluating the Alignment Between GeoAI Explanations and Domain Knowledge in Satellite-Based Flood Mapping

arXiv 2604.26051 ↗First posted 28 Apr 2026cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The increasing number of satellites has improved the temporal resolution of Earth observation, making satellite-based flood mapping a promising approach for operational flood monitoring. Deep learning-based approaches for flood mapping using satellite imagery, an important application within Geospatial Artificial Intelligence (GeoAI), have shown improved predictive performance by learning complex spatial and spectral patterns from large volumes of remote sensing data. However, the opaque decision-making processes of deep learning models remain a major barrier to their integration into critical scientific and operational workflows. This highlights the need for a systematic assessment of whether model explanations align with established domain knowledge in remote sensing. To address this research gap, this study introduces the ADAGE (Alignment between Domain Knowledge and GeoAI Explanation Evaluation) framework. The proposed framework is designed to systematically evaluate how well explanations of deep learning models align with established remote sensing knowledge, particularly regarding the distinctive spectral properties of the Earth's surface. The ADAGE framework employs Channel-Group SHAP (SHapley Additive exPlanations) method to estimate the contributions of grouped input channels to pixel-level predictions. Experiments on two satellite-based flood mapping tasks demonstrate that the ADAGE framework can (1) quantitatively assess the alignment between model explanations and reference explanations derived from domain knowledge, and (2) help domain experts identify misaligned explanations through the proposed alignment scores. This study contributes to bridging the gap between explainability and domain knowledge in GeoAI for Earth observation, enhancing the applicability of GeoAI models in scientific and operational workflows.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 80 references that are in the map. First posted on arXiv 28 Apr 2026.

Builds on

22 of 80 references.

References · 22

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  4. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  5. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  6. 2020Shortcut Learning in Deep Neural Networkscited by 1,969
  7. 2019UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentationcited by 586
  8. 2021Evaluating explainable artificial intelligence methods for multi-label deep learning classification tasks in remote sensingcited by 26
  9. 2021groupShapley: Efficient prediction explanation with Shapley values for feature groupscited by 21
  10. 2023Kuro Siwo: 33 billion m2 under the water. A global multi-temporal satellite dataset for rapid flood mappingcited by 16
  11. 2023Explainable GeoAI: Can saliency maps help interpret artificial intelligence's learning process? An empirical study on natural feature detectioncited by 14
  12. 2023Assessment of a new GeoAI foundation model for flood inundation mappingcited by 14
10 more
  1. 2020H2O-Net: Self-Supervised Flood Segmentation via Adversarial Domain Adaptation and Label Refinementcited by 12
  2. 2024Explainable AI (XAI) in Image Segmentation in Medicine, Industry, and Beyond: A Surveycited by 11
  3. 2024UrbanSARFloods: Sentinel-1 SLC-Based Benchmark Dataset for Urban and Open-Area Flood Mappingcited by 11
  4. 2024Mapping Global Floods with 10 Years of Satellite Radar Datacited by 8
  5. 2017Exploiting ConvNet Diversity for Flooding Identificationcited by 7
  6. 2024Improving Interpretability of Deep Active Learning for Flood Inundation Mapping Through Class Ambiguity Indices Using Multi-spectral Satellite Imagerycited by 6
  7. 2023GeoShapley: A Game Theory Approach to Measuring Spatial Effects in Machine Learning Modelscited by 5
  8. 2024Urban Flood Mapping Using Satellite Synthetic Aperture Radar Data: A Review of Characteristics, Approaches and Datasetscited by 3
  9. 2023Grouping Shapley Value Feature Importances of Random Forests for explainable Yield Predictioncited by 1
  10. 2025A Spatially Masked Adaptive Gated Network for multimodal post-flood water extent mapping using SAR and incomplete multispectral datacited by 1

Built on by

Not cited yet.