Spatial interference (SI) occurs when the treatment at one location affects
the outcomes at other locations. Accounting for spatial interference in
spatiotemporal settings poses further challenges as interference violates the
stable unit treatment value assumption, making it infeasible for standard
causal inference methods to quantify the effects of time-varying treatment at
spatially varying outcomes. In this paper, we first formalize the concept of
spatial interference in case of time-varying treatment assignments by extending
the potential outcome framework under the assumption of no unmeasured
confounding. We then propose our deep learning based potential outcome model
for spatiotemporal causal inference. We utilize latent factor modeling to
reduce the bias due to time-varying confounding while leveraging the power of
U-Net architecture to capture global and local spatial interference in data
over time. Our causal estimators are an extension of average treatment effect
(ATE) for estimating direct (DATE) and indirect effects (IATE) of spatial
interference on treated and untreated data. Being the first of its kind deep
learning based spatiotemporal causal inference technique, our approach shows
advantages over several baseline methods based on the experiment results on two
synthetic datasets, with and without spatial interference. Our results on
real-world climate dataset also align with domain knowledge, further
demonstrating the effectiveness of our proposed method.

基于深度学习的潜在结果模型及其在时空因果推断中的应用：通过扩展潜在结果框架，在无未测混淆的情况下对时变治疗分配中的空间干扰进行形式化，并利用潜在因子建模来减少因时变混淆引起的偏差，同时利用 U-Net 架构捕捉数据随时间的全局和局部空间干扰，从而推断空间干扰对受治疗和未受治疗数据的直接和间接效应。