Future Air Quality Prediction Using Long Short-Term Memory Based on Hyper Heuristic Multi-Chain Model
Kalyan Chatterjee, Samla Suraj Kumar, Ramagiri Praveen Kumar, Anjan Bandyopadhyay, Sujata Swain, Saurav Mallik, Amal Al‐Rasheed, Mohamed Abbas, Ben Othman Soufiene
Abstract
Air pollution is a critical global concern, demanding precise air quality forecasting to mitigate its severe consequences. Our study introduces Future Air Quality Prediction using Long Short-Term Memory based on <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">H</u>yper <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">H</u>euristic <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">M</u>ulti-<underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</u>hain <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">M</u>odel (H<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>MCM) to project future air quality, considering various meteorological factors (MFs) and pollution-related variables like atmospheric pressure, temperature, humidity, and wind patterns. Leveraging 12 units of Long Short-Term Memory neural networks (LSTMs), H<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>MCM accurately predicts forthcoming air pollutants (APs) concentrations such as particulate matter with diameter <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$2.5 \; \mu $ </tex-math></inline-formula>m (PM<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</sub>), carbon monoxide (CO), and nitrogen dioxide (NO<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub>). Additionally, it accounts for spatiotemporal correlations between these APs and MFs, which significantly influence the air quality prediction for the next immediate time interval. H<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>MCM utilizes a multi-chain mechanism, employing <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1-hour prediction model</i>s to forecast air quality hourly, enabling approximations for the next 12 hours. Also, for an efficient model selection, Akaike Information Criterion (AIC), Schwarz Bayesian Information Criterion (SBIC), Hannan-Quinn Information Criterion (HQIC), and corrected AIC (AICc) tools are used based on their ability to balance model fit and complexity. Furthermore, it demonstrates the ability to enhance the performance of any predictor. Experimental results substantiate H<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>MCM’s superiority over various models, including the Support Vector Regressor (SVR), Multi-Layer Perceptron (MLP), Recurrent Air Quality Predictor (RAQP), and Valchogianni models. H<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>MCM achieves impressive up to 75% better accuracy and consistency compared to SVR, 60% better than MLP, 38% better than RAQP, and 70% better than Valchogianni models.