GST-UNet: A Neural Framework for Spatiotemporal Causal Inference with Time-Varying Confounding

Miruna Oprescu, David Keetae Park, Xihaier Luo, Shinjae Yoo, Nathan Kallus

Keywords: spatiotemporal causal inference, time-varying confounding, G-computation, observational studies, neural networks, treatment effects, observational data

TL;DR: We introduce GST-UNet, a neural framework for valid causal inference from spatiotemporal observational data with time-varying confounding and complex spatiotemporal dependencies.

Abstract: Estimating causal effects from spatiotemporal observational data is essential in public health, environmental science, and policy evaluation, where randomized experiments are often infeasible. Existing approaches, however, either rely on strong structural assumptions or fail to handle key challenges such as interference, spatial confounding, temporal carryover, and *time-varying confounding*—where covariates are influenced by past treatments and, in turn, affect future ones. We introduce the **GST-UNet** (**G**-computation **S**patio-**T**emporal **UNet**), a theoretically grounded neural framework that combines a U-Net-based spatiotemporal encoder with regression-based iterative G-computation to estimate location-specific potential outcomes under complex intervention sequences. GST-UNet explicitly adjusts for time-varying confounders and captures non-linear spatial and temporal dependencies, enabling valid causal inference from a *single* observed trajectory in data-scarce settings. We validate its effectiveness in synthetic experiments and in a real-world analysis of wildfire smoke exposure and respiratory hospitalizations during the 2018 California Camp Fire. Together, these results position GST-UNet as a **principled and ready-to-use framework** for spatiotemporal causal inference, advancing reliable estimation in policy-relevant and scientific domains.

Primary Area: Probabilistic methods (e.g., variational inference, causal inference, Gaussian processes)

Submission Number: 18755