SpecBPP: A Self-Supervised Learning Approach for Hyperspectral Representation and Soil Organic Carbon Estimation
This work addresses the underexplored area of self-supervised learning for hyperspectral imagery, offering a novel approach that could benefit remote sensing applications, though it is incremental in advancing existing self-supervised techniques.
The paper tackled the problem of learning representations from hyperspectral imagery for soil organic carbon estimation by proposing a self-supervised learning framework called SpecBPP, which achieved state-of-the-art results with an R² of 0.9456 and RMSE of 1.1053%.
Self-supervised learning has revolutionized representation learning in vision and language, but remains underexplored for hyperspectral imagery (HSI), where the sequential structure of spectral bands offers unique opportunities. In this work, we propose Spectral Band Permutation Prediction (SpecBPP), a novel self-supervised learning framework that leverages the inherent spectral continuity in HSI. Instead of reconstructing masked bands, SpecBPP challenges a model to recover the correct order of shuffled spectral segments, encouraging global spectral understanding. We implement a curriculum-based training strategy that progressively increases permutation difficulty to manage the factorial complexity of the permutation space. Applied to Soil Organic Carbon (SOC) estimation using EnMAP satellite data, our method achieves state-of-the-art results, outperforming both masked autoencoder (MAE) and joint-embedding predictive (JEPA) baselines. Fine-tuned on limited labeled samples, our model yields an $R^2$ of 0.9456, RMSE of 1.1053%, and RPD of 4.19, significantly surpassing traditional and self-supervised benchmarks. Our results demonstrate that spectral order prediction is a powerful pretext task for hyperspectral understanding, opening new avenues for scientific representation learning in remote sensing and beyond.