SpecBPP: A Self-Supervised Learning Approach for Hyperspectral Representation and Soil Organic Carbon Estimation

TL;DR

This paper introduces SpecBPP, a self-supervised learning method for hyperspectral imagery that predicts spectral band order to improve soil organic carbon estimation, achieving state-of-the-art results.

Contribution

The paper presents a novel spectral permutation prediction framework with curriculum learning for hyperspectral data, enhancing representation learning and soil carbon estimation accuracy.

Findings

Achieves R^2 of 0.9456 in SOC estimation.

Outperforms masked autoencoder and JEPA baselines.

Demonstrates spectral order prediction as effective pretext task.

Abstract

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.