2023

Ge, Shaojia; Gu, Hong; Su, Weimin; Lönnqvist, Anne; Antropov, Oleg

Accurate mapping of forests is critical for forest management and carbon stocks monitoring. Deep learning (DL) is becoming more popular in Earth observation (EO), however, the availability of reference data limits its potential in wide-area forest mapping. To overcome those limitations, here we introduce contrastive regression into EO-based forest mapping and develop a novel semisupervised regression framework for wall-to-wall mapping of continuous forest variables. It combines supervised contrastive regression loss (CtRL) and semi-supervised cross-pseudo regression (CPR) loss. The framework is demonstrated over a boreal forest site using Copernicus Sentinel-1 and Sentinel-2 imagery for mapping forest tree height. Achieved prediction accuracies are strongly better compared to using vanilla UNet or traditional regression models, with relative root mean square error (rRMSE) of 15.1% on stand level. We expect that the developed framework can be used for modeling other forest variables and EO datasets.