When Treatments Spill Over: A Neural Framework for Spatiotemporal Causal Effect Estimation
Abstract
Real-world public health policies are often enacted by local jurisdictions, but their effects can ripple through connected populations. For causal evaluation, this creates a difficult spatiotemporal problem: intermittent policy updates create path-level treatments, and because spillover depends on neighboring treatment paths along with the focal-unit's own history, controlling time-varying confounding requires high-dimensional, multimodal information from both sources. To address this challenge, we develop a neural spatiotemporal spillover framework that extends potential-outcome causal analysis to networked policy-systems with unit-level effects and structured interference. The framework indexes each unit's potential outcomes through own-treatment and neighborhood spillover-exposure paths, yielding direct, spillover, and total effects. We introduce an LSTM-based representation-learning encoder that integrates each unit's own and neighborhood histories into compact sequential summaries for downstream modeling and causal estimation. These summaries feed a self-normalized kernel inverse-probability-weighting estimator for continuous spillover exposure. Beyond theoretical guarantees, simulations show improved performance over outcome-regression baselines; in a practically motivated county-level COVID-19 policy study, the framework finds both business-and-economic restrictions and education-and-childcare policies associated with lower subsequent case burden, with larger estimates for business-and-economic restrictions. Overall, it provides a scalable, policy-interpretable framework for evaluating unit-level effects in high-dimensional, multimodal spatiotemporal systems when interventions spill over across space and time.
Related
- Divide-and-Conquer Neural Bayes Estimation for Spatial and Spatiotemporal Point Process Models
- Causal adaptive intensity estimation for non-stationary point processes: a Kalman-kernel duality framework
- Causal Inference with Generative Artificial Intelligence: Application to Texts as Treatments
- Nonlinear Sufficient Dimension Reduction for Causal Inference with Continuous Treatments
- Identifying Causal Effects in Experiments with Latent Treatments: An Instrumental Variable Approach
BibTeX
@misc{zhang2026when,
title = {{When Treatments Spill Over: A Neural Framework for Spatiotemporal Causal Effect Estimation}},
author = {Shaohui Zhang and Jiasheng Shi and Jing Huang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.16086},
eprint = {2610.16086},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.16086},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - When Treatments Spill Over: A Neural Framework for Spatiotemporal Causal Effect Estimation
AU - Shaohui Zhang
AU - Jiasheng Shi
AU - Jing Huang
PY - 2026
DA - 2026/10/14
PB - arXiv
DO - 10.48550/arxiv.2610.16086
UR - https://arxiv.org/abs/2610.16086
AB - Real-world public health policies are often enacted by local jurisdictions, but their effects can ripple through connected populations. For causal evaluation, this creates a difficult spatiotemporal problem: intermittent policy updates create path-level treatments, and because spillover depends on neighboring treatment paths along with the focal-unit's own history, controlling time-varying confounding requires high-dimensional, multimodal information from both sources. To address this challenge, we develop a neural spatiotemporal spillover framework that extends potential-outcome causal analysis to networked policy-systems with unit-level effects and structured interference. The framework indexes each unit's potential outcomes through own-treatment and neighborhood spillover-exposure paths, yielding direct, spillover, and total effects. We introduce an LSTM-based representation-learning encoder that integrates each unit's own and neighborhood histories into compact sequential summaries for downstream modeling and causal estimation. These summaries feed a self-normalized kernel inverse-probability-weighting estimator for continuous spillover exposure. Beyond theoretical guarantees, simulations show improved performance over outcome-regression baselines; in a practically motivated county-level COVID-19 policy study, the framework finds both business-and-economic restrictions and education-and-childcare policies associated with lower subsequent case burden, with larger estimates for business-and-economic restrictions. Overall, it provides a scalable, policy-interpretable framework for evaluating unit-level effects in high-dimensional, multimodal spatiotemporal systems when interventions spill over across space and time.
ER -