Using Machine Learning in Analyzing Air Quality Discrepancies of Environmental Impact

2025-06-18

AI Summary

This study investigates the association between contemporary air pollution disparities (NO₂/PM₂.₅) in Baltimore, USA, and historical institutional discrimination. Method: Integrating 20th-century redlining maps with modern demographic data and satellite-derived pollution measurements, we construct a novel multisource, heterogeneous spatial dataset. We apply supervised learning models augmented with fairness-aware feature engineering and complement them with spatial statistical analysis to quantify the persistent impact of institutional legacies on environmental injustice. Contribution/Results: We find significantly higher PM₂.₅ exposure in Black neighborhoods compared to White neighborhoods (+37%, p<0.001), and statistically significant NO₂ concentration differences between high- and low-income census tracts. Critically, the study uncovers an intergenerational transmission mechanism whereby structural racism—operationalized through historic housing policy—continues to shape present-day environmental health inequities. Our work establishes a reproducible, transdisciplinary analytical framework bridging historical, geographical, and technical dimensions for environmental justice research.

Technology Category

• Machine Learning: Ethics, Bias, and Fairness
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Bridging structured and unstructured data
• Social Networks and Social Media: Fairness and bias in social network and social media analysis

Abstract

In this study, we apply machine learning and software engineering in analyzing air pollution levels in City of Baltimore. The data model was fed with three primary data sources: 1) a biased method of estimating insurance risk used by homeowners loan corporation, 2) demographics of Baltimore residents, and 3) census data estimate of NO2 and PM2.5 concentrations. The dataset covers 650,643 Baltimore residents in 44.7 million residents in 202 major cities in US. The results show that air pollution levels have a clear association with the biased insurance estimating method. Great disparities present in NO2 level between more desirable and low income blocks. Similar disparities exist in air pollution level between residents' ethnicity. As Baltimore population consists of a greater proportion of people of color, the finding reveals how decades old policies has continued to discriminate and affect quality of life of Baltimore citizens today.

Problem

• Analyzing air pollution disparities using machine learning
• Linking biased insurance methods to pollution levels
• Examining ethnic and income-based air quality inequalities

Innovation

• Machine learning analyzes air pollution disparities
• Combines biased insurance data with demographics
• Links historical policies to current pollution levels