结合稀疏地面校准的多传感器可迁移地上生物量（AGB）估算模型
Transferable Above-Ground Biomass (AGB) Estimation Model from Multi-Sensor Data with Sparse Field Calibration
中文总结 AI 辅助
该研究提出结合稀疏地面校准的多传感器可迁移AGB估算框架，以全局训练CNN为核心，经GEDI数据训练后用少量样地校准，提升了AGB估算精度，优于现有产品。
中文摘要 AI 辅助
森林地上生物量（AGB）的空间连续量化是碳核算可信性和减缓策略可实施性的基础。地面清查虽具备高局部精度，但空间分布稀疏；而全球生态系统动力学调查（GEDI）的星载激光雷达（LiDAR）虽能提供大范围生物量样本，却缺乏空间连续性，且对高生物量森林存在系统性低估。本文提出一种以单全局训练卷积神经网络（CNN）为核心的可操作框架，通过轻量经验性地面校准工作流，可无缝适配每个新研究区域。该全局模型结合光学数据（哨兵2号，Sentinel-2）、C波段合成孔径雷达（SAR，哨兵1号，Sentinel-1）、L波段SAR（ALOS-2 PALSAR-2）及地形数据（数字高程模型，DEM），针对覆盖多区域、干湿季的GEDI Level-4A生物量参考数据仅训练一次，以学习持久的木质结构特征而非单期表观特征。为避免对每个区域重新训练，该框架利用少量本地地面样地拟合尺度与偏差校正项，使全局预测结果与各区域地面真值对齐。该流程将传感器数据统一到10米网格，提取植被指数与极化比值，计算各波段归一化统计量，采用混合对数域的平滑L1损失函数结合均方根误差（RMSE）训练CNN，以应对生物量分布的偏斜特性。在预留验证集上，基于GEDI的全局模型获得约0.78的决定系数（R²）和约22 Mg/公顷的RMSE。后续结合10折交叉验证下的随机森林（Random Forest）微调的地面校准，可消除局部区域偏差，使局部验证性能提升至约0.82的R²，RMSE降至约15 Mg/公顷，在地面样地基准上优于未校准的全局模型与欧空局气候变化倡议生物量产品（ESA CCI Biomass）。
英文摘要
Spatially continuous quantification of forest above-ground biomass (AGB) is what makes carbon accounting credible and mitigation strategies actionable. While field inventories provide high localized accuracy, they are spatially sparse; conversely, spaceborne LiDAR from the Global Ecosystem Dynamics Investigation (GEDI) offers broad biomass samples but lacks spatial continuity and systematic underestimation of high-biomass forests. This paper presents an operational framework centered on a single globally trained convolutional neural network (CNN) that is seamlessly adapted to each new landscape through a lightweight empirical field-calibration workflow. The global model combines optical (Sentinel-2), C-band SAR (Sentinel-1), L-band SAR (ALOS-2 PALSAR-2), and terrain (DEM) data. It is trained once against GEDI Level-4A biomass reference data spanning multiple regions and both wet and dry seasons so that it learns the persistent woody-structure rather than a single-date appearance. To avoid retraining for every landscape, the framework applies a small number of local field plots to fit a scale-and-bias correction that aligns the global prediction with ground truth in each region. The pipeline harmonizes sensor data onto a shared 10 m grid, derives vegetation indices and polarimetric ratios, computes per-band normalization stats, and trains the CNN with a hybrid log-domain SmoothL1 with RMSE loss for skewed biomass distribution. On held-out validation the global GEDI-based model achieved R^2 approximately 0.78 and RMSE approximately 22 Mg/ha. A subsequent field calibration combining Random Forest fine-tuning under a 10-fold cross-validation eliminates localized regional biases. This improves local validation performance to R^2 approximately 0.82 and reduces RMSE to approximately 15 Mg/ha, outperforming both the uncalibrated global model and the ESA CCI Biomass product against field plots.
