In prediction of forest parameters with data from remote sensing (RS), regression models have traditionally been trained on a small sample of ground reference data. This paper proposes to impute this sample of true prediction targets with data from an existing RS-based prediction map that we consider as pseudo-targets. This substantially increases the amount of target training data and leverages the use of deep learning (DL) for semi-supervised regression modelling. We use prediction maps constructed from airborne laser scanning (ALS) data to provide accurate pseudo-targets and free data from Sentinel-1's C-band synthetic aperture radar (SAR) as regressors. A modified U-Net architecture is adapted with a selection of different training objectives. We demonstrate that when a judicious combination of loss functions is used, the semi-supervised imputation strategy produces results that surpass traditional ALS-based regression models, even though \sen data are considered as inferior for forest monitoring. These results are consistent for experiments on above-ground biomass prediction in Tanzania and stem volume prediction in Norway, representing a diversity in parameters and forest types that emphasises the robustness of the approach.

翻译：在基于遥感数据预测森林参数时，回归模型传统上依赖小样本的地面参考数据进行训练。本文提出利用现有遥感预测地图中的数据作为伪目标，对真实预测目标样本进行插补。该方法显著增加了目标训练数据量，并推动了深度学习在半监督回归建模中的应用。我们使用基于机载激光扫描数据构建的预测地图提供准确的伪目标，同时采用Sentinel-1 C波段合成孔径雷达的免费数据作为回归变量。通过改进U-Net架构并选取不同训练目标，我们证明：当采用精心设计的损失函数组合时，半监督插补策略能生成超越传统基于ALS回归模型的结果——即便Sentinel-1数据通常被认为在森林监测中性能较弱。该结论在坦桑尼亚地上生物量预测与挪威树干材积预测实验中保持一致性，涵盖不同参数与森林类型，充分彰显了该方法的稳健性。