Optimized Three Deep Learning Models Based-PSO Hyperparameters for Beijing PM2.5 Prediction

M-1 with three hidden layers produces the best results of RMSE and MAPE compared to the proposed M-2, M-3, and all the baselines. A recommendation for air pollution management could be generated by using these optimized models. This is an open access article under the CC BY-SA license (https://creativecommons.org/licenses/by-sa/4.0/). I. Introduction In air quality monitoring systems, PM2.5 concentration is a crucial measure. As public awareness rises, analyzing and anticipating pollution levels is vital. Monitoring stations can only perform a small role in PM2.5 pollution control due to the nonlinear character of PM2.5 concentrations in both time and space. As a result, improving PM2.5 concentrations prediction accuracy is crucial for preventing and controlling air pollution. Several studies have been conducted using machine learning techniques, such as neural networks, applied to environmental science issues. As a part of a neural network, deep learning is a technique that achieves high performance for various applications such as natural language processing, visual recognition, and forecasting has recently gained attention in the machine learning field.