Machine Learning-driven Optimization of a Sensor Network for Accurate Pollutant Source Identification
Résumé
Optimizing sensor networks for localizing atmospheric pollution sources and enhancing estimation accuracy remains a significant challenge in air pollution studies. To address this, various techniques have been recently developed. Among them, machine learning has demonstrated its ability to model and optimize complex problems, including sensor network optimization.To improve the localization of atmospheric pollution sources in air quality research activities, we propose in this paper, a Machine Learning-driven Optimization of Sensor Networks method (ML-OSN). The method introduces a new combination of Hierarchical Agglomerative Clustering and Siamese Neural Networks, thereby improving the prediction of similarities in pollutant concentrations across different wind directions and leading to an optimized sensor network.The proposed ML-OSN method was evaluated and compared to a standard clustering approach based on the Pearson correlation coefficient, using the augmented Indianapolis dataset. The resulting optimal sensor network configuration achieved broader spatial coverage and improved source estimation accuracy, reducing the error score to 1.34 compared to 1.44 obtained with the Pearson-based approach.