Real-time Pollutant Identification through Optical PM Micro-Sensor

TL;DR

This work addresses real-time pollutant identification using low-cost optical micro-sensors by framing the problem as a four-class sequence classification among Background Pollution, Ash, Sand, and Candle. It evaluates three models—XGBoost, LSTM, and Hidden Markov Chain—on 10 ratio-based features derived from five PM channels, finding that the Hidden Markov Chain offers the best accuracy (~82.4%) and robust ash/sand detection, while LSTM underperforms due to limited data. The study demonstrates the feasibility of real-time pollutant source attribution in outdoor environments, suggesting practical implications for urban air-quality management and rapid response. Limitations include a small dataset and lack of mixed-pollution testing, with future work pointing to larger, more diverse datasets and advanced HMC variants to enhance robustness and coverage.

Abstract

Air pollution remains one of the most pressing environmental challenges of the modern era, significantly impacting human health, ecosystems, and climate. While traditional air quality monitoring systems provide critical data, their high costs and limited spatial coverage hinder effective real-time pollutant identification. Recent advancements in micro-sensor technology have improved data collection but still lack efficient methods for source identification. This paper explores the innovative application of machine learning (ML) models to classify pollutants in real-time using only data from optical micro-sensors. We propose a novel classification framework capable of distinguishing between four pollutant scenarios: Background Pollution, Ash, Sand, and Candle. Three Machine Learning (ML) approaches - XGBoost, Long Short-Term Memory networks, and Hidden Markov Chains - are evaluated for their effectiveness in sequence modeling and pollutant identification. Our results demonstrate the potential of leveraging micro-sensors and ML techniques to enhance air quality monitoring, offering actionable insights for urban planning and environmental protection.

Figures (4)

• Figure 1: Example of data collection with sand as pollutant
• Figure 2: Representation of the channels for each scenario - different scales per scenario are used for clarity.
• Figure 3: Confusion Matrix of the HMC model
• Figure 4: Confusion matrices of the XGBoost and the LSTM models, respectively