# Causal Inference under Interference with Learned Exposure Mappings

arXiv: https://arxiv.org/abs/2608.19224 · HTML: https://mlsanity.com/paper/2608.19224/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 10 references that are in the map.
- First posted on arXiv 26 Jul 2026.

## Builds on (most cited first, 3 of 3)

- [Factorized Fourier Neural Operators](https://mlsanity.com/paper/2111.13802/) (2021)
- [Causal Diagrams for Interference](https://mlsanity.com/paper/1403.1239/) (2014)
- [Causal health impacts of power plant emission controls under modeled and uncertain physical process interference](https://mlsanity.com/paper/2306.05665/) (2023)

## Abstract (arXiv)

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 PM2.5 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 PM2.5 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.