Air pollution prediction system using XRSTH-LSTM algorithm

PMFORECAST: leveraging temporal LSTM to deliver in situ air quality predictions

The physical and chemical properties of atmospheric aerosol particles are crucial in influencing global climate and ecosystem processes. Given the numerous studies highlighting adverse health effects from exposure to aerosol particulates, particularly Particulate Matter (PM), effective air quality management strategies are under consideration  (Annesi-Maesano et al. Eur Respir Soc 29(3):428-431. 2007). Herein, we introduce a predictive model-PMFORECAST-employing a self-adaptive long short-term memory (LSTM) architecture to predict PM2.5 values in the real atmosphere. Specifically, we explore adopting a LSTM model to better benefit from temporal dimensions. PMFORECAST is strategically designed with four key phases: preprocessing, temporal attention, prediction horizon, and LSTM layers. By leveraging LSTM's significant predictive ability in time-series data, the inclusion of temporal attention enhances the model's specificity. Temporal dynamics modeling entails generating insights over time, utilizing temporal attention to extract essential characteristics from historical air pollutant concentrations, with the flexibility to adjust the historical data according to the forecasting period. To assess PMFORECAST, we consider measurements collected from the QAMELEO network, a sparse network of air-quality micro-stations deployed in Dijon, France. The self-adaptive capabilities of PMFORECAST allow the model to be dynamically updated, evaluating its performance and continuously tuning hyper-parameters based on the latest data trends. Our empirical evaluation reports that PMFORECAST outperforms the state of the art, achieving notable accuracy in both short-term and long-term predictions. The PMFORECAST deployment at scale can serve as a valuable tool for proactive decision-making and targeted interventions to mitigate the health risks associated with air pollution.

Blockchain and IoT integration for secure short-term and long-term air quality monitoring system using optimized neural network

Accurate air pollution prediction is vital for residents' well-being. This research introduces a secure air quality monitoring system using neural networks and blockchain for robust analysis, precise predictions, and early pollution detection. Blockchain guarantees data integrity, security, and transparency. Goals include real-time air quality data, secure blockchain recording, and enhanced safety through informed decisions. The research integrates blockchain and IoT for short- and long-term air quality monitoring, utilizing an optimized neural network. IoT sensors collect PM2.5, PM10, CO, NO2, and SO2, processed through noise removal and normalization, with feature extraction using N-tuple contrastive learning. Predictions utilize Graph attention-based deep Residual shrinkage Network and Bidirectional long short Term Memory (GRNBTM) categorized into five levels. An adaptive bowerbird algorithm optimizes parameters, reducing computational complexity. Blockchain integration ensures secure, tamper-proof data storage with a lightweight consensus-based algorithm. The GRNBTM model's air quality monitoring performance is extensively simulated and analyzed at 30-min, 2-h, 1-day, and 1-month intervals, demonstrating superior performance over existing techniques.