Multi-Spectral Band Selection and Spatial Explanations Using XAI Algorithms in Remote Sensing Applications

This work proposes an interpretable Deep Learning framework utilizing Vision Transformers (ViT) for the classification of remote sensing images into land use and land cover (LULC) classes. It uses the Shapley Additive Explanations (SHAP) values to achieve two-stage explanations: 1) bandwise feature...

Full description

Saved in:
Bibliographic Details
Published inIGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium pp. 6093 - 6396
Main Authors Temenos, Anastasios, Temenos, Nikos, Kaselimi, Maria, Doulamis, Anastasios, Doulamis, Nikolaos
Format Conference Proceeding
LanguageEnglish
Published IEEE 16.07.2023
Subjects
Correlation
Deep learning
EuroSAT
Heating systems
Land Cover
Land Use
Remote Sensing
Rivers
Satellite images
Sensors
Sentinel-2
SHAP
Transformers
ViT
XAI
Online AccessGet full text

Cover

More Information
Summary:This work proposes an interpretable Deep Learning framework utilizing Vision Transformers (ViT) for the classification of remote sensing images into land use and land cover (LULC) classes. It uses the Shapley Additive Explanations (SHAP) values to achieve two-stage explanations: 1) bandwise feature importance per class, showing which band assists the prediction of each class and 2) spatial-wise feature understanding, explaining which embedded patches per band affected the network's performance. Experimental results on the EuroSAT dataset demonstrate the ViT's accurate classification with an overall accuracy 96.86 %, offering improved results when compared to popular CNN models. Heatmaps in each one of the dataset's existing classes highlight the effectiveness of the proposed framework in the band explanation and the feature importance.
ISSN:2153-7003
DOI:10.1109/IGARSS52108.2023.10282565