发表机构
Yale University; Yale School of Public Health（耶鲁大学; 耶鲁公共卫生学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对环境场景中需从污染数据学习暴露映射的因果推断问题，对比PDE、PINO等传输模型，发现预测精度相近的模型溢出估计差异大，仅预测一致无法保证可靠因果推断。
AI 中文摘要
在因果溢出分析中，通常假设暴露映射是已知的。然而在环境场景中，暴露映射通常由未直接观测到的传输过程诱导，必须从污染数据中学习得到。我们研究了学习到的传输过程的不确定性如何在干扰下传播到暴露映射及下游的溢出因果推断中。我们将机理传输模型与现代算子学习方法（包括PDE、PINO、FNO和GeoPT）进行比较，结合模拟研究和加利福尼亚州PM₂.₅数据的实证分析开展实验。模拟研究中，这四种传输模型均达到了几乎相同的污染预测精度，但估计的溢出效应介于1.78至2.27之间；更准确恢复诱导暴露映射的模型，其溢出估计值更接近真实效应。区域干预的分歧较小，但局部点源干预的分歧显著更大。加利福尼亚州的分析呈现出相同模式：不同传输模型对观测到的PM₂.₅浓度的预测相似，但在假设的污染控制干预下隐含不同的溢出效应。我们的研究结果表明，当暴露映射是学习得到而非直接观测时，仅预测一致性不足以支持可靠的因果推断。
英文摘要
Exposure mappings are often assumed to be known in causal spillover analyses. In environmental settings, however, they are typically induced by transport processes that are not directly observed and must instead be learned from pollution data. We study how uncertainty in learned transport processes propagates into exposure mappings and downstream spillover inference under interference. We compare mechanistic transport models with modern operator-learning approaches, including PDE, PINO, FNO, and GeoPT, using both simulation studies and an empirical analysis of California PM$_{2.5}$ data. In simulations, all four transport models achieved nearly identical pollution prediction accuracy, yet estimated spillover effects ranged from 1.78 to 2.27. Models that more accurately recovered the induced exposure mapping also produced spillover estimates closer to the true effect. Disagreement was modest for regional interventions but substantially larger for localized point-source interventions. The California analysis showed the same pattern: competing transport models produced similar predictions of observed PM${2.5}$ concentrations while implying different spillover effects under hypothetical pollution-control interventions. Our findings suggest that predictive agreement alone is insufficient for reliable causal inference when exposure mappings are learned rather than directly observed.
Comments20 pages, 6 figures
