Comparative Analysis of Machine Learning-Based Imputation Techniques for Air Quality Datasets with High Missing Data Rates

2026-04-11

AI Summary

Dublin’s air quality dataset exhibits an exceptionally high missingness rate of 82.42%, severely impeding reliable PM₂.₅ monitoring and analysis. Method: This study proposes a fine-grained spatiotemporal imputation and classification framework for PM₂.₅, integrating heterogeneous multi-source data—including mobile sensors, fixed monitoring stations, traffic flow, and meteorological variables. It introduces, for the first time, diffusion models for imputation under extreme missingness, enhanced by an external-feature-driven conditional generation mechanism and robust multi-source data alignment and feature fusion strategies. Contribution/Results: Experimental results demonstrate that the diffusion model achieves an F₁-score of 0.9486 (accuracy: 94.26%), while an XGBoost/LightGBM ensemble attains 94.82% accuracy—both significantly outperforming conventional deep learning (e.g., LSTM) and classical imputation methods. The approach validates high-accuracy PM₂.₅ concentration state classification even under extreme data scarcity, offering a robust, practical solution for intelligent urban environmental management.

Technology Category

Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal DataMachine Learning: Calibration & Uncertainty QuantificationComputer Vision: Diffusion Models for Vision

Application Category

Web Mining and Content Analysis: Web data integration and cleaningSystems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applicationsSearch and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Urban pollution poses serious health risks, particularly in relation to traffic-related air pollution, which remains a major concern in many cities. Vehicle emissions contribute to respiratory and cardiovascular issues, especially for vulnerable and exposed road users like pedestrians and cyclists. Therefore, accurate air quality monitoring with high spatial resolution is vital for good urban environmental management. This study aims to provide insights for processing spatiotemporal datasets with high missing data rates. In this study, the challenge of high missing data rates is a result of the limited data available and the fine granularity required for precise classification of PM2.5 levels. The data used for analysis and imputation were collected from both mobile sensors and fixed stations by Dynamic Parcel Distribution, the Environmental Protection Agency, and Google in Dublin, Ireland, where the missing data rate was approximately 82.42%, making accurate Particulate Matter 2.5 level predictions particularly difficult. Various imputation and prediction approaches were evaluated and compared, including ensemble methods, deep learning models, and diffusion models. External features such as traffic flow, weather conditions, and data from the nearest stations were incorporated to enhance model performance. The results indicate that diffusion methods with external features achieved the highest F1 score, reaching 0.9486 (Accuracy: 94.26%, Precision: 94.42%, Recall: 94.82%), with ensemble models achieving the highest accuracy of 94.82%, illustrating that good performance can be obtained despite a high missing data rate.

Problem

• Air Quality Data
• PM2.5 Concentration Prediction
• Incomplete Data Handling

Innovation

• Diffusion Model
• Environmental Information Integration
• Deep Learning for Air Quality Prediction