Comprehensive Monitoring of Air Pollution Hotspots Using Sparse Sensor Networks

2024-10-05

AI Summary

To address insufficient spatial coverage of sparse public sensor networks in urban air pollution hotspot monitoring, this paper proposes a synergistic approach integrating data-driven prediction with physics-based modeling. Leveraging 30 months of PM₂.₅ measurements from 28 low-cost sensors in New Delhi, we pioneer the joint application of spatiotemporal kriging and a Gaussian plume dispersion model coupled with a localized emissions inventory for hotspot identification and attribution. Under 50% sensor failure or missing data, the method achieves 98% precision and 95% recall in hotspot detection, successfully identifying 189 previously undetected hotspots outside the public network’s coverage and validating 660 known hotspots. The mechanistic model explains 65% of transient hotspot occurrences. These results enable actionable, high-resolution pollution mitigation policies grounded in both empirical observation and physical causality.

Technology Category

• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Web data integration and cleaning

Abstract

Urban air pollution hotspots pose significant health risks, yet their detection and analysis remain limited by the sparsity of public sensor networks. This paper addresses this challenge by combining predictive modeling and mechanistic approaches to comprehensively monitor pollution hotspots. We enhanced New Delhi's existing sensor network with 28 low-cost sensors, collecting PM2.5 data over 30 months from May 1, 2018, to Nov 1, 2020. Applying established definitions of hotspots to this data, we found the existence of additional 189 hidden hotspots apart from confirming 660 hotspots detected by the public network. Using predictive techniques like Space-Time Kriging, we identified hidden hotspots with 95% precision and 88% recall with 50% sensor failure rate, and with 98% precision and 95% recall with 50% missing sensors. The projected results of our predictive models were further compiled into policy recommendations for public authorities. Additionally, we developed a Gaussian Plume Dispersion Model to understand the mechanistic underpinnings of hotspot formation, incorporating an emissions inventory derived from local sources. Our mechanistic model is able to explain 65% of observed transient hotspots. Our findings underscore the importance of integrating data-driven predictive models with physics-based mechanistic models for scalable and robust air pollution management in resource-constrained settings.

Problem

• Enhancing urban air pollution monitoring
• Identifying hidden pollution hotspots effectively
• Integrating predictive and mechanistic modeling approaches

Innovation

• Combined predictive and mechanistic modeling
• Enhanced sensor network with low-cost sensors
• Gaussian Plume Dispersion Model usage