Unified calibration and spatial mapping of fine particulate matter data from multiple low-cost air pollution sensor networks in Baltimore, Maryland

2024-12-17

AI Summary

To address prediction conflicts and sampling bias arising from independent calibration of low-cost, multi-source PM₂.₅ sensor networks, this paper proposes a Bayesian spatial filtering framework for cross-network unified calibration and dynamic spatial mapping in Baltimore City. Methodologically, it jointly models network-specific observation processes and a Gaussian process-based state-space model, integrating sparse reference station measurements with heterogeneous sensor observations across multiple networks. It introduces the first multi-network collaborative calibration paradigm, eliminating single-network preference bias. Experimental results during the June–July 2023 wildfire smoke event demonstrate significant improvements: PM₂.₅ prediction accuracy increases (RMSE reduced by 21%), uncertainty quantification tightens (95% credible intervals narrowed by 34%), and regional-scale air quality characterization achieves greater consistency and robustness across networks.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services

Abstract

Low-cost air pollution sensor networks are increasingly being deployed globally, supplementing sparse regulatory monitoring with localized air quality data. In some areas, like Baltimore, Maryland, there are only few regulatory (reference) devices but multiple low-cost networks. While there are many available methods to calibrate data from each network individually, separate calibration of each network leads to conflicting air quality predictions. We develop a general Bayesian spatial filtering model combining data from multiple networks and reference devices, providing dynamic calibrations (informed by the latest reference data) and unified predictions (combining information from all available sensors) for the entire region. This method accounts for network-specific bias and noise (observation models), as different networks can use different types of sensors, and uses a Gaussian process (state-space model) to capture spatial correlations. We apply the method to calibrate PM$_{2.5}$ data from Baltimore in June and July 2023 -- a period including days of hazardous concentrations due to wildfire smoke. Our method helps mitigate the effects of preferential sampling of one network in Baltimore, results in better predictions and narrower confidence intervals. Our approach can be used to calibrate low-cost air pollution sensor data in Baltimore and any other areas with multiple low-cost networks.

Problem

• Unifying calibration for multiple low-cost air pollution networks
• Resolving conflicting air quality predictions from separate calibrations
• Mapping PM2.5 concentrations across Baltimore with spatial correlations

Innovation

• Bayesian spatial model combining multiple sensor networks
• Dynamic calibration using latest reference data
• Gaussian process capturing spatial correlations