Comparative Analysis of Statistical, Machine Learning, and Deep Learning Models for PM_2.5 Prediction in Almaty

Accurate prediction of PM<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</inf> concentrations is essential for public health protection in heavily polluted urban areas such as Almaty, Kazakhstan. This study presents a novel comparative assessment of statistical, machine learning (ML), deep learning (DL), and hybrid models for PM<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2.5</inf> forecasting, addressing a gap in the literature concerning model performance under different data preprocessing scenarios. Using a comprehensive dataset spanning 2020–2024, nine models—including SARIMA, Random Forest, SVM, LSTM, CNN, CNN-ELM, and CNN-LSTM—were evaluated across three imputation techniques: mean imputation, time-based mean, and Multiple Imputation by Chained Equations (MICE). The methodology emphasizes how the quality of missing value treatment influences model accuracy. Results demonstrate that Random Forest performed best with mean imputation (R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> = 0.7277), CNN-ELM achieved optimal performance under time-based imputation (R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> = 0.8279), and LSTM yielded the highest accuracy when applied to MICE-imputed data (R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> = 0.9570). The findings contribute to the development of robust air quality forecasting systems by highlighting the interplay between preprocessing strategies and model selection.