High-Resolution Forest Mapping from L-Band Interferometric SAR Time Series using Deep Learning over Northern Spain

In this study, we examine the potential of high-resolution forest mapping using L-band interferometric time series datasets and deep learning modeling. Our SAR data are represented by a time series of nine ALOS-2 PALSAR-2 dual-pol SAR images acquired at near-zero spatial baseline over a study site in Asturias, Northern Spain. Reference data are collected using airborne laser scanning. We examine the performance of several candidate deep learning models from UNet-family with various combinations of input polarimetric and interferometric features. In addition to basic Vanilla UNet, attention reinforced UNet model with squeeze-excitation blocks (SeU-Net) and advanced UNet model with nested structure and skip pathways are used. Studied features include dual pol interferometric observables additionally incorporating model-based derived measures. Results show that adding model-based inverted InSAR features or InSAR coherence layers improves retrieval accuracy compared to using backscatter intensity only. Use of attention mechanisms and nested connection fusion provides better predictions than using Vanilla UNet or traditional machine learning methods. Forest height retrieval accuracies range between 3.1-3.8 m (R2 = 0.45--0.55) at 20 m resolution when only intensity data are used, and improve to less than 2.8 m when both intensity and interferometric coherence features are included. At 40 m and 60 m resolution, retrieval performance further improves, primarily due to higher SNR in both the intensity and interferometric layers. When using intensity at 60 m resolution, best achieved RMSE is 2.2 m, while when using all suitable input features the achieved error is 1.95 m. We recommend this hybrid approach for L-band SAR retrievals also suitable for NISAR and future ROSE-L missions.

A Novel Semisupervised Contrastive Regression Framework for Forest Inventory Mapping with Multisensor Satellite Data

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.