A Novel Semisupervised Contrastive Regression Framework for Forest Inventory Mapping with Multisensor Satellite Data
This work addresses forest management and carbon monitoring by improving mapping accuracy in Earth Observation, though it is incremental as it adapts existing contrastive and semi-supervised techniques to a specific domain.
The paper tackled the problem of limited reference data for wide-area forest mapping by introducing a novel semisupervised contrastive regression framework, achieving a relative RMSE of 15.1% on stand level for forest tree height prediction, which is strongly better than baseline methods.
Accurate mapping of forests is critical for forest management and carbon stocks monitoring. Deep learning 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 and semi-supervised Cross-Pseudo Regression 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 RMSE of 15.1% on stand level. We expect that developed framework can be used for modeling other forest variables and EO datasets.