发表机构
Adams State University（亚当斯州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对物理因子受损时土壤流失变化估计困难的问题，提出物理结构化潜在因子恢复框架PhyRestore，通过恢复受损因子并利用RUSLE物理关系重建变化，在流域尺度评估中优于退化估计及多种模型，但联合损坏下优势减弱。
AI 中文摘要
当具有物理意义的输入因子受到噪声或损坏时，估算时间尺度上的土壤流失变化具有挑战性，尤其是因为相对于大量变化很小的位置，显著变化较为罕见。我们通过修订通用土壤流失方程（RUSLE）研究该问题，并引入PhyRestore，一种物理结构化的潜在因子恢复框架。PhyRestore并非直接预测土壤流失变化或修正退化的物理估计，而是恢复受损的物理因子，并通过已知的物理关系重建时间变化。我们在流域尺度的双时相栅格设置中评估PhyRestore，在降雨侵蚀力和覆盖管理因子单独及同时损坏的情况下，将其与退化的RUSLE估计以及直接RF、XGBoost、MLP和CNN模型进行比较。当受损因子仍可识别时，因子恢复提高了高幅度恢复能力，但在联合损坏、稀疏的正极端值以及因子值超出训练支持范围的情况下，其优势减弱。
英文摘要
Estimating temporal soil-loss change is challenging when physically meaningful input factors are noisy or corrupted, particularly because substantial changes are rare relative to the large number of locations exhibiting little change. We study this problem through the Revised Universal Soil Loss Equation (RUSLE) and introduce PhyRestore, a physics-structured latent-factor restoration framework. Rather than directly predicting soil-loss change or correcting a degraded physical estimate, PhyRestore restores corrupted physical factors and reconstructs temporal change through the known physical relationship. We evaluate PhyRestore in a watershed-scale bitemporal raster setting under isolated and simultaneous corruption of rainfall erosivity and cover management, comparing it with the degraded RUSLE estimate and Direct RF, XGBoost, MLP, and CNN models. Factor restoration improves high-magnitude recovery when the corrupted factors remain identifiable, but its advantage weakens under joint corruption, sparse positive extremes, and factor values outside the training support.
Comments12 pages, 2 figures, 2 tables
