Predicting Public Health Impacts of Electricity Usage

2025-11-26

AI Summary

The power sector is a major source of air pollution and associated public health risks, with high fossil-fuel dependency constraining health co-benefit realization. To address this, we propose HealthPredictor—the first end-to-end, domain-specific AI framework integrating electricity source attribution, atmospheric pollutant dispersion simulation, and monetized health impact quantification. It employs a three-stage technical pipeline: (1) dynamic fuel-mix forecasting, (2) meteorology- and geography-constrained air quality transformation modeling, and (3) exposure–dose–response–monetization assessment of population-level health impacts. Empirical evaluation across multiple U.S. regions demonstrates significantly lower health impact prediction error compared to conventional fuel-mix baselines. In an electric vehicle smart charging dispatch scenario, HealthPredictor enables quantifiable public health gains. The framework establishes a novel, interpretable, and deployable decision-support paradigm for health-aware demand-side management.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Hardware-aware ML

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Systems and Infrastructure for Web, Mobile and WoT: Web applications in cross-disciplinary domains and verticals such as mixed reality, smart cities, and digital health
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

The electric power sector is a leading source of air pollutant emissions, impacting the public health of nearly every community. Although regulatory measures have reduced air pollutants, fossil fuels remain a significant component of the energy supply, highlighting the need for more advanced demand-side approaches to reduce the public health impacts. To enable health-informed demand-side management, we introduce HealthPredictor, a domain-specific AI model that provides an end-to-end pipeline linking electricity use to public health outcomes. The model comprises three components: a fuel mix predictor that estimates the contribution of different generation sources, an air quality converter that models pollutant emissions and atmospheric dispersion, and a health impact assessor that translates resulting pollutant changes into monetized health damages. Across multiple regions in the United States, our health-driven optimization framework yields substantially lower prediction errors in terms of public health impacts than fuel mix-driven baselines. A case study on electric vehicle charging schedules illustrates the public health gains enabled by our method and the actionable guidance it can offer for health-informed energy management. Overall, this work shows how AI models can be explicitly designed to enable health-informed energy management for advancing public health and broader societal well-being. Our datasets and code are released at: https://github.com/Ren-Research/Health-Impact-Predictor.

Problem

• Predicts public health impacts from electricity usage
• Links electricity demand to monetized health damages
• Enables health-informed energy management optimization

Innovation

• AI model linking electricity use to health outcomes
• Three-component pipeline: fuel mix, air quality, health assessor
• Health-driven optimization reduces prediction errors vs. baselines