{"slug": "predicting-spatiotemporal-mobile-sensing-based-pm2-5-concentrations-using-low", "title": "Predicting Spatiotemporal Mobile Sensing-Based PM2.5 Concentrations Using Low-Rank Adapted Spatially Attentive Graph Neural Network", "summary": "Researchers introduced SA-GNN, a low-rank adapted spatially attentive graph neural network, achieving R² = 0.95, RMSE = 6.8, and MAE = 4.2 µg/m³ for fine-grained PM2.5 forecasting on a new mobile-sensing dataset from Surat, Gujarat, India, outperforming LSTM, RNN, GRU, and ANN baselines. The model combines cluster-specific GRUs and graph attention to capture rapid urban air quality fluctuations, enabling real-time hotspot identification and personalized exposure tracking.", "body_md": "arXiv:2609.04693v1 Announce Type: new \nAbstract: Urban air quality can vary significantly along transit corridors, necessitating high-resolution monitoring. This work introduces a novel mobile-sensing dataset from Surat, Gujarat, India, comprising PM$*{2.5}$ concentrations, meteorological variables (temperature, humidity, wind speed, wind direction), and land-use features. To represent the spatiotemporal data as a graph, two node-definition strategies were used: (i) uniform segmentation (200--400~m intervals) and (ii) DBSCAN clustering to adaptively group dense observations. For each node, rolling mean and standard deviation of meteorological variables were computed. To model this high-dimensional data, we propose a SA-GNN for fine-grained, short-term PM$*{2.5}$ forecasting and hotspot identification. We compared SA-GNN with LSTM, RNN, GRU, and ANN models. These models performed well on low-resolution data but had difficulty capturing rapidly changing patterns in urban air quality. SA-GNN employs cluster-specific GRUs to capture localized temporal dependencies and a Graph Attention Network to learn spatial heterogeneity. This hybrid architecture effectively models rapid fluctuations and complex spatial interactions. On our dataset, SA-GNN achieved $R^2 = 0.95$, RMSE $= 6.8$, and MAE $= 4.2~\\si{\\micro\\gram\\per\\meter\\cubed}$, outperforming all baseline models. Combining spatial clustering with adaptive attention significantly improves forecasting, enabling real-time, fine-grained monitoring and supporting personalized exposure tracking and timely alerts for healthier cities.", "url": "https://wpnews.pro/news/predicting-spatiotemporal-mobile-sensing-based-pm2-5-concentrations-using-low", "canonical_source": "https://www.machinebrief.com/news/predicting-spatiotemporal-mobile-sensing-based-pm25-concentr-qw5x", "published_at": "2026-09-07 04:00:00+00:00", "updated_at": "2026-09-07 04:56:23.017050+00:00", "lang": "en", "topics": ["machine-learning", "artificial-intelligence"], "entities": ["SA-GNN", "Surat", "Gujarat", "India"], "alternates": {"html": "https://wpnews.pro/news/predicting-spatiotemporal-mobile-sensing-based-pm2-5-concentrations-using-low", "markdown": "https://wpnews.pro/news/predicting-spatiotemporal-mobile-sensing-based-pm2-5-concentrations-using-low.md", "text": "https://wpnews.pro/news/predicting-spatiotemporal-mobile-sensing-based-pm2-5-concentrations-using-low.txt", "jsonld": "https://wpnews.pro/news/predicting-spatiotemporal-mobile-sensing-based-pm2-5-concentrations-using-low.jsonld"}}