Skip to main content Skip to main navigation


Feature Attributation Methods for Multivariate Time-Series Explainability in Remote Sensing

Hiba Najjar; Patrick Helber; Benjamin Bischke; Peter Habelitz; Cristhian Sanchez; Francisco Mena; Miro Miranda Lorenz; Deepak Kumar Pathak; Jayanth Siddamsetty; Diego Arenas; Michaela Vollmer; Marcela Charfuelan Oliva; Marlon Nuske; Andreas Dengel
In: IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium. IEEE International Geoscience and Remote Sensing Symposium (IGARSS-2023), July 16-21, Pasadena, California, USA, Pages 5014-5017, IEEE Xplore, 10/2023.


Numerous remote sensing applications rely on temporal satellite data, and Deep learning models are increasingly being used for such tasks. Nevertheless, these models operate as black boxes, lacking transparency and understandability. We address this gap by using explainable AI on an agricultural task. Specifically, we trained a recurrent neural network on individual pixels from multispectral time-series of Sentinel-2 satellite images to predict crop yield. We then applied nine feature attribution methods on a sample of the dataset and computed the spectral and temporal contributions to the final individual predictions.The aggregated results were evaluated qualitatively and quantitatively. Results suggest that LIME and Shapley sampling value methods performed best on the quantitative scores, followed by GradientShap. Most backpropagation-based techniques had highly inconsistent scores across the explained data points.Finally, to guide remote sensing practitioners in using Explainable AI on similar datasets, we further discuss some selection criteria to be considered.