Weather2vec: Representation Learning for Causal Inference with Non-local Confounding in Air Pollution and Climate Studies
Mauricio Tec, James G. Scott, Corwin M. Zigler
Abstract
Estimating the causal effects of a spatially-varying intervention on a spatially-varying outcome may be subject to non-local confounding (NLC), a phenomenon that can bias estimates when the treatments and outcomes of a given unit are dictated in part by the covariates of other nearby units. In particular, NLC is a challenge for evaluating the effects of environmental policies and climate events on health-related outcomes such as air pollution exposure. This paper first formalizes NLC using the potential outcomes framework, providing a comparison with the related phenomenon of causal interference. Then, it proposes a broadly applicable framework, termed weather2vec, that uses the theory of balancing scores to learn representations of non-local information into a scalar or vector defined for each observational unit, which is subsequently used to adjust for confounding in conjunction with causal inference methods. The framework is evaluated in a simulation study and two case studies on air pollution where the weather is an (inherently regional) known confounder.
BibTeX
@article{Tec_Scott_Zigler_2023, title={Weather2vec: Representation Learning for Causal Inference with Non-local Confounding in Air Pollution and Climate Studies}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/26696}, DOI={10.1609/aaai.v37i12.26696}, abstractNote={Estimating the causal effects of a spatially-varying intervention on a spatially-varying outcome may be subject to non-local confounding (NLC), a phenomenon that can bias estimates when the treatments and outcomes of a given unit are dictated in part by the covariates of other nearby units. In particular, NLC is a challenge for evaluating the effects of environmental policies and climate events on health-related outcomes such as air pollution exposure. This paper first formalizes NLC using the potential outcomes framework, providing a comparison with the related phenomenon of causal interference. Then, it proposes a broadly applicable framework, termed weather2vec, that uses the theory of balancing scores to learn representations of non-local information into a scalar or vector defined for each observational unit, which is subsequently used to adjust for confounding in conjunction with causal inference methods. The framework is evaluated in a simulation study and two case studies on air pollution where the weather is an (inherently regional) known confounder.}, number={12}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Tec, Mauricio and Scott, James G. and Zigler, Corwin M.}, year={2023}, month={Jun.}, pages={14504-14513} }