In recent years, air pollution has become an important public health concern. The high concentration of fine particulate matter with diameter less than 2.5 µm (PM2.5) is known to be associated with lung cancer, cardiovascular disease, respiratory disease, and metabolic disease. Predicting PM2.5 concentrations can help governments warn people at high risk, thus mitigating the complications. Although attempts have been made to predict PM2.5 concentrations, the factors influencing PM2.5 prediction have not been investigated. In this work, we study feature importance for PM2.5 prediction in Tehran’s urban area, implementing random forest, extreme gradient boosting, and deep learning machine learning (ML) approaches. We use 23 features, including satellite and meteorological data, ground-measured PM2.5, and geographical data, in the modeling. The best model performance obtained was R2 = 0.81 (R = 0.9), MAE = 9.93 µg/m3, and RMSE = 13.58 µg/m3 using the XGBoost approach, incorporating elimination of unimportant features. However, all three ML methods performed similarly and R2 varied from 0.63 to 0.67, when Aerosol Optical Depth (AOD) at 3 km resolution was included, and 0.77 to 0.81, when AOD at 3 km resolution was excluded. Contrary to the PM2.5 lag data, satellite-derived AODs did not improve model performance.

Developing a cost-effective and highly efficient electrocatalyst with superior catalytic activity is crucial for clean and green water splitting, including the hydrogen evolution reaction (HER), the oxygen evolution reaction (OER), and the oxygen reduction reaction (ORR). The single-atom catalyst (SAC) is a breakthrough in industrial catalysis because of the advantages of maximum metal atom utilization, single active sites, strong metal−support interactions, and great potential to accomplish high catalytic performance and selectivity. Herein, we investigate the electrocatalytic performance of a series of SACs supported on a phosphomolybdic acid (PMA) cluster for the HER, OER, and ORR by using first-principles-based calculations. It has been found that the most plausible binding site for the single-metal adatoms is the 4-fold hollow (4H) site over the PMA cluster. Due to the higher stability and catalytic activity of single-metal adatoms, fast electron transfer kinetics is permissible through catalysis. Mainly, Pt 1 /PMA, Ru 1 /PMA, V 1 /PMA, and Ti 1 /PMA realized decent catalytic performance toward the HER due to nearly ideal (ΔG H* = 0) ΔG H* values via the Volmer−Heyrovsky pathway. The Co 1 /PMA (0.45 V) and Pt 1 /PMA (0.49 V) can be active and selective catalysts for the OER with their overpotentials comparable those of to MoC 2 , IrO 2 , and RuO 2 . Among the considered candidates, a non-noble metal Fe 1 /PMA SAC is a promising electrocatalyst for the ORR with an overpotential of 0.42 V, which is lower than that for the most favorable Pt (0.45 V) catalyst. Furthermore, Pt 1 /PMA is an auspicious multifunctional electrocatalyst for overall water splitting (−0.02 V for the HER and 0.49 V for the OER) and a metal-air battery (0.79 V for the ORR) catalyst. The current study is further extended to calculate the kinetic potential energy barrier for the excellent catalytic performance of Co 1 for the OER and Fe 1 for the ORR. The results suggest that the kinetic activation barrier values in all proton-coupled electron transfer steps are in good agreement with the thermodynamic results. It was revealed that the PMA cluster is a promising single-atom support for the HER, OER, and ORR and provides low-cost and highly efficient electrocatalytic activity under normal reaction conditions.