SpectralEarth: Training Hyperspectral Foundation Models at Scale

TL;DR

SpectralEarth introduces a large-scale, multitemporal hyperspectral dataset and pretrained foundation models, enabling improved remote sensing analysis across diverse tasks and sensors.

Contribution

The paper presents SpectralEarth, a comprehensive hyperspectral dataset and pretrained models, filling a gap in HSI research and enabling scalable, generalizable remote sensing applications.

Findings

Models trained on SpectralEarth generalize well across tasks.

Pretrained models show high accuracy in land-cover and crop classification.

Efficient fine-tuning reduces computational costs.

Abstract

Foundation models have triggered a paradigm shift in computer vision and are increasingly being adopted in remote sensing, particularly for multispectral imagery. Yet, their potential in hyperspectral imaging (HSI) remains untapped due to the absence of comprehensive and globally representative hyperspectral datasets. To close this gap, we introduce SpectralEarth, a large-scale multitemporal dataset designed to pretrain hyperspectral foundation models leveraging data from the environmental mapping and analysis program (EnMAP). SpectralEarth comprises 538 974 image patches covering 415 153 unique locations from 11 636 globally distributed EnMAP scenes spanning two years of archive. In addition, 17.5% of these locations include multiple timestamps, enabling multitemporal HSI analysis. Utilizing state-of-the-art self-supervised learning algorithms, we pretrain a series of foundation models on SpectralEarth, integrating a spectral adapter into classical vision backbones to accommodate the unique characteristics of HSI. In tandem, we construct nine downstream datasets for land-cover, crop-type mapping, and tree-species classification, providing benchmarks for model evaluation. Experimental results support the versatility of our models and their generalizability across different tasks and sensors. We also highlight computational efficiency during model fine-tuning.