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.

Land degradation reflected by vegetation is a commonly used practice to monitor desertification. To retrieve important information for ecosystem management accurate assessment of desertification is necessary. The major factors that drive vegetation dynamics in arid and semi-arid regions are climate and anthropogenic activities. Progression of desertification is expected to exacerbate under future climate change scenarios, through precipitation variability, increased drought frequency and persistence of dry conditions. This study examined spatiotemporal vegetation dynamics in arid regions of Sindh, Pakistan, using annual and growing season Normalized Difference Vegetation Index (NDVI) data from 2000 to 2017, and explored the climatic and anthropogenic effects on vegetation. Results showed an overall upward trend (annual 86.71% and growing season 82.7%) and partial downward trend (annual 13.28% and growing season 17.3%) in the study area. NDVI showed the highest significant increase in cropland region during annual, whereas during growing season the highest significant increase was observed in savannas. Overall high consistency in future vegetation trends in arid regions of Sindh province is observed. Stable and steady development region (annual 48.45% and growing 42.80%) dominates the future vegetation trends. Based on the Hurst exponent and vegetation dynamics of the past, improvement in vegetation cover is predicted for a large area (annual 44.49% and growing 30.77%), and a small area is predicted to have decline in vegetation activity (annual 0.09% and growing 3.04%). Results revealed that vegetation growth in the study area is a combined result of climatic and anthropogenic factors; however, in the future multi-controls are expected to have a slightly larger impact on annual positive development than climate whereas positive development in growing season is more likely to continue in future under the control of climate variability.