Towards Optimal Environmental Policies: Policy Learning under Arbitrary Bipartite Network Interference

2024-10-10

arXiv.org

AI Summary

This study addresses causal decision-making for scrubber deployment in coal-fired power plants—particularly wet flue gas desulfurization (WFGD) systems—under budget constraints, aiming to minimize ischemic heart disease (IHD) hospitalization rates in distant communities while accounting for bipartite network interference (BNI) between plants and communities. Method: We propose the first Q/A-Learning policy learning framework adaptable to arbitrary BNI structures, integrating pollution transport network embedding, causal modeling of multi-source data (EPA emissions + Medicare health records), and reinforcement learning–based optimization. Contribution/Results: We establish asymptotic optimality theory, resolving the fundamental identifiability barrier for cross-unit causal effects under BNI. Empirical evaluation on real-world data demonstrates that our policy reduces IHD hospitalizations by 20.66–44.51 cases per 10,000 person-years, significantly outperforming benchmarks while ensuring cost-effectiveness and policy interpretability.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

The substantial effect of air pollution on cardiovascular disease and mortality burdens is well-established. Emissions-reducing interventions on coal-fired power plants -- a major source of hazardous air pollution -- have proven to be an effective, but costly, strategy for reducing pollution-related health burdens. Targeting the power plants that achieve maximum health benefits while satisfying realistic cost constraints is challenging. The primary difficulty lies in quantifying the health benefits of intervening at particular plants. This is further complicated because interventions are applied on power plants, while health impacts occur in potentially distant communities, a setting known as bipartite network interference (BNI). In this paper, we introduce novel policy learning methods based on Q- and A-Learning to determine the optimal policy under arbitrary BNI. We derive asymptotic properties and demonstrate finite sample efficacy in simulations. We apply our novel methods to a comprehensive dataset of Medicare claims, power plant data, and pollution transport networks. Our goal is to determine the optimal strategy for installing power plant scrubbers to minimize ischemic heart disease (IHD) hospitalizations under various cost constraints. We find that annual IHD hospitalization rates could be reduced in a range from 20.66-44.51 per 10,000 person-years through optimal policies under different cost constraints.

Problem

• Optimizing scrubber installation on power plants
• Minimizing ischemic heart disease hospitalizations cost-effectively
• Addressing bipartite network interference in policy evaluation

Innovation

• Policy learning methods using Q- and A-Learning
• Addressing bipartite network interference in policy optimization
• Optimal scrubber installation under cost constraints