XAI-Guided Enhancement of Vegetation Indices for Crop Mapping
This work addresses the challenge of optimizing vegetation indices for crop classification using new satellite data, representing an incremental improvement in agricultural remote sensing.
The paper tackles the problem of inefficiently exploiting multi- and hyperspectral satellite data for crop mapping by proposing an explainable-AI method to select and design vegetation indices, resulting in models that achieve comparable or better performance than using all bands, with combinations of two indices surpassing the baseline in some cases.
Vegetation indices allow to efficiently monitor vegetation growth and agricultural activities. Previous generations of satellites were capturing a limited number of spectral bands, and a few expert-designed vegetation indices were sufficient to harness their potential. New generations of multi- and hyperspectral satellites can however capture additional bands, but are not yet efficiently exploited. In this work, we propose an explainable-AI-based method to select and design suitable vegetation indices. We first train a deep neural network using multispectral satellite data, then extract feature importance to identify the most influential bands. We subsequently select suitable existing vegetation indices or modify them to incorporate the identified bands and retrain our model. We validate our approach on a crop classification task. Our results indicate that models trained on individual indices achieve comparable results to the baseline model trained on all bands, while the combination of two indices surpasses the baseline in certain cases.