With increasing levels of air pollution, air quality prediction has attracted more attention. Mathematical models are being developed by researchers to achieve precise predictions. Monitoring and prediction of atmospheric PM_2.5 levels, as a predominant pollutant, is essential in emission mitigation programs. In this study, meteorological datasets from 9 years in Isfahan city, a large metropolis of Iran, were applied to predict the PM_2.5 levels, using four machine learning algorithms including Artificial Neural |Networks (ANNs), K-Nearest-Neighbors (KNN), Support Vector |Machines (SVMs) and ensembles of classification trees Random Forest (RF). The data from 7 air quality monitoring stations located in Isfahan City were taken into consideration. The Confusion Matrix and Cross-Entropy Loss were used to analyze the performance of classification models. Several parameters, including sensitivity, specificity, accuracy, F1 score, precision, and the area under the curve (AUC), are computed to assess model performance. Finally, by introducing the predicted data for 2020 into ArcGIS software and using the IDW (Inverse Distance Weighting) method, interpolation was conducted for the area of Isfahan city and the pollution map was illustrated for each month of the year. The results showed that, based on the accuracy percentage, the ANN model has a better performance (90.1%) in predicting PM_2.5 grades compared to the other models for the applied meteorological dataset, followed by RF (86.1%), SVM (84.6%) and KNN (82.2%) models, respectively. Therefore, ANN modelling provides a feasible procedure for the managerial planning of air pollution control.

Microcystin-leucine arginine (MC-LR) is a carcinogenic toxin, produced by cyanobacteria. The release of this toxin into drinking water sources can threaten public health and environmental safety. Therefore, effective MC-LR removal from water resources is necessary. In the present study, the hydrothermal method was used to synthesize a novel ternary BiVO4/TiO2/NaY-Zeolite (B/T/N-Z) nanocomposite for MC-LR degradation under visible light. FESEM, FTIR, XRD, and DRS were performed for characterizing the nanocomposite structure. Also, the Response Surface Methodology (RSM) was applied to determine the impact of catalyst dosage, pH, and contact time on the MC-LR removal. High-performance liquid chromatography was performed to measure the MC-LR concentration. Based on the results, independent parameters, including contact time, catalyst dosage, and pH, significantly affected the MC-LR removal (P < 0.05). In other words, increasing the contact time, catalyst dosage, and acidic pH had positive effects on MC-LR removal. Among these variables, the catalyst dosage, with the mean square and F-value of 1041.37 and 162.84, respectively, had the greatest effect on the MC-LR removal efficiency. Apart from the interaction between the catalyst dosage and contact time, the interaction effects of other parameters were not significant. Also, the maximum MC-LR removal efficiency was 99.88% under optimal conditions (contact time = 120 min, catalyst dosage = 1 g/L, and pH = 5). According to the results, the B/T/N-Z nanocomposite, as a novel and effective photocatalyst could be used to degrade MC-LR from polluted water.