Prediction of Monthly PM2.5 Concentration in Liaocheng in China Employing Artificial Neural Network

Fine particulate matter (PM2.5) affects climate change and human health. Therefore, the prediction of PM2.5 level is particularly important for regulatory planning. The main objective study to predict concentration employing an artificial neural network (ANN). annual in Liaocheng from 2014 2021 shows a gradual decreasing trend. air quality during lockdown after periods 2020 was obviously improved compared with same 2019. ANN employed contains hidden layer 6 neurons, input 11 parameters, output layer. First, used 80% data training, then 10% verification. value correlation coefficient (R) training validation 0.9472 0.9834, respectively. In forecast period, it demonstrated that model Bayesian regularization (BR) algorithm (trainbr) obtained best forecasting performance terms R (0.9570), mean absolute error (4.6 ?g/m3), root square (6.6 has produced accurate results. These results prove effective monthly predicting due fact can identify nonlinear relationships between variables.