GreenHyperSpectra: A multi-source hyperspectral dataset for global vegetation trait prediction

TL;DR

GreenHyperSpectra is a new hyperspectral dataset designed to improve plant trait prediction across different sensors and ecosystems using semi- and self-supervised learning methods, addressing domain shifts and label scarcity.

Contribution

The paper introduces GreenHyperSpectra, a comprehensive dataset for benchmarking cross-domain plant trait prediction and demonstrates the effectiveness of pretraining models with semi- and self-supervised learning techniques.

Findings

Pretrained models outperform supervised baselines in trait prediction.

GreenHyperSpectra enables robust cross-sensor and cross-ecosystem trait prediction.

Substantial improvements in spectral representation learning for plant traits.

Abstract

Plant traits such as leaf carbon content and leaf mass are essential variables in the study of biodiversity and climate change. However, conventional field sampling cannot feasibly cover trait variation at ecologically meaningful spatial scales. Machine learning represents a valuable solution for plant trait prediction across ecosystems, leveraging hyperspectral data from remote sensing. Nevertheless, trait prediction from hyperspectral data is challenged by label scarcity and substantial domain shifts (\eg across sensors, ecological distributions), requiring robust cross-domain methods. Here, we present GreenHyperSpectra, a pretraining dataset encompassing real-world cross-sensor and cross-ecosystem samples designed to benchmark trait prediction with semi- and self-supervised methods. We adopt an evaluation framework encompassing in-distribution and out-of-distribution scenarios. We successfully leverage GreenHyperSpectra to pretrain label-efficient multi-output regression models that outperform the state-of-the-art supervised baseline. Our empirical analyses demonstrate substantial improvements in learning spectral representations for trait prediction, establishing a comprehensive methodological framework to catalyze research at the intersection of representation learning and plant functional traits assessment. All code and data are available at: https://github.com/echerif18/HyspectraSSL.