发表机构
LMU Munich; TU Munich; Munich Center for Machine Learning (MCML)（慕尼黑大学; 慕尼黑工业大学; 慕尼黑机器学习中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对TreeUQ基准数据集，采用融合多模态卫星输入的U-Net架构，提出掩码证据损失函数，应用深度证据回归实现了树高与不确定性的联合预测，性能优于确定性模型。
AI 中文摘要
从卫星图像准确估算林高对于碳核算、生物多样性监测和生态系统管理等应用至关重要。尽管近期深度学习方法能提供准确预测，但通常无法量化预测不确定性，这一局限在监督稀疏且存在地理分布偏移的地理空间场景中尤为突出。本研究针对TreeUQ基准数据集开展林高估算研究，该数据集是为联合估算10米分辨率下的树木数量和平均树高而设计的大规模数据集，基于德国巴伐利亚州的Sentinel-1、Sentinel-2数据以及树木清查数据构建。为解决树木清查数据的极端标签稀疏问题，我们提出了一种用于密集地理空间预测的掩码证据损失函数。采用融合Sentinel-1和Sentinel-2多模态输入的U-Net架构，所提方法可在单次前向传播中联合预测树高及相关不确定性估计。实验结果表明，深度证据回归（DER）的预测性能可与确定性U-Net相媲美，同时还能提供校准良好的不确定性估计。这些发现证明了证据学习作为一种高效框架，在基于地球观测数据开展不确定性感知的森林结构估算方面具有潜力。
英文摘要
Accurate estimation of forest height from satellite imagery is essential for applications such as carbon accounting, biodiversity monitoring, and ecosystem management. While recent deep learning approaches provide accurate predictions, they typically do not quantify predictive uncertainty. This limitation is particularly relevant in geospatial settings characterized by sparse supervision and geographic distribution shift. In this work, we investigate Deep Evidential Regression (DER) for forest height estimation on the TreeUQ benchmark, a large-scale dataset designed for the joint estimation of tree count and average tree height at 10 m resolution, based on Sentinel-1/-2 data as well as tree inventory data over the federal state of Bavaria. To account for the extreme label sparsity of the tree inventory data, we introduce a masked evidential loss for dense geospatial prediction. Using a U-Net architecture with multimodal Sentinel-1 and Sentinel-2 inputs, the proposed approach jointly predicts tree height and associated uncertainty estimates in a single forward pass. Experimental results show that DER achieves predictive performance comparable to a deterministic U-Net while additionally providing well-calibrated uncertainty estimates. These findings demonstrate the potential of evidential learning as an efficient framework for uncertainty-aware forest structure estimation from Earth observation data.
