Monitoring and estimation of urban emissions with low-cost sensor networks and deep learning

• Published in: Ecological informatics Vol. 82; p. 102750
• Main Authors: Nguyen, Huynh A.D., Le, Trung H., Azzi, Merched, Ha, Quang P.
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.09.2024; Elsevier
• Subjects: air pollution; air quality; Bayesian optimization; Data constraint; Deep learning; development projects; infrastructure; prediction; Prediction interval; sustainable development; time series analysis; Urban emissions; Deep learning; Urban emissions; Bayesian optimization; Data constraint; Prediction interval
• ISSN: 1574-9541
• DOI: 10.1016/j.ecoinf.2024.102750

Sustainable development in cities requires advanced technologies for monitoring and estimating air pollution emissions, which directly affect the health of local inhabitants and residents in the neighborhoods. For this, low-cost sensors and information technologies are increasingly used to provide accurate air quality forecasts. They are, however, subject to data constraints. This paper presents new techniques for accurate, reliable monitoring and forecasting of air pollution at various scales using data from IoT-enabled sensors along with state-run air-quality monitoring stations. Here, we develop an extended deep-learning model based on neural networks and algorithms for optimization of the model hyperparameters and network dropout rates. These can yield a significant improvement of over 31% in prediction accuracy while maintaining a prediction coverage of approximately 80% for forecasting air-particle levels over a 24-h period. The advantages and effectiveness of our model are validated and verified in two real-world scenarios, a suburban construction site and a civil infrastructure development project. Comparison analysis is conducted to indicate the outperformance of the proposed method over two recent techniques for probabilistic time series forecasting used for air pollution estimation on regular days and extreme events. •Urban emissions monitored with low-cost wireless sensor networks and estimated from air quality monitoring stations.•Novel extended learning model with CNN-LSTM-BNN developed for multi-scale particle forecasts.•Improving forecast coverage with Bayesian optimization-based technique developed for model hyperparameter selection.•Performance validation and verification with data from two real-world urban sites.