Atmospheric particulate matter (PM) has major threats to global health, especially in urban regions around the world. Dhaka, Narayanganj and Gazipur of Bangladesh are positioned as top ranking polluted metropolitan cities in the world. This study assessed the performance of the application of hybrid models, that is, Autoregressive Integrated Moving Average (ARIMA)-Artificial Neural Network (ANN), ARIMA-Support Vector Machine (SVM) and Principle Component Regression (PCR) along with Decision Tree (DT) and CatBoost deep learning model to predict the ambient PM2.5 concentrations. The data from January 2013 to May 2019 with 2342 observations were utilized in this study. Eighty percent of the data was used as training and the rest of the dataset was employed as testing. The performance of the models was evaluated by R2, RMSE and MAE value. Among the models, CatBoost performed best for predicting PM2.5 for all the stations. The RMSE values during the test period were 12.39 µg m−3, 13.06 µg m−3 and 12.97 µg m−3 for Dhaka, Narayanganj and Gazipur, respectively. Nonetheless, the ARIMA-ANN and DT methods also provided acceptable results. The study suggests adopting deep learning models for predicting atmospheric PM2.5 in Bangladesh.
Drought is a widespread hazard that can tremendously affect the biodiversity, habitat of wild species, and ecosystem functioning and stability, especially in the dry region. Due to its geographic location, the north-western region of Bangladesh has a comparatively arid climate which is very much susceptible to drought occurrence and is marked as a red zone. Despite the growing evidence of the impact of drought on food security and ecosystem functioning, little effort has been paid to mitigate the drought in this region. The present study aimed to assess the drought condition of the north-western region of Bangladesh using earth observation techniques. For this purpose, Landsat data from 1990 to 2020 was used to determine various vegetation indices such as Normalized Difference Vegetation Index (NDVI), Water Index (NDWI), Moisture Index (NDMI) and Soil Adjusted Vegetation Index (SAVI), along with Land Surface Temperature (LST). Results show that the depletion of forests (2832 km2) and water bodies (6773 km2) resulted from the expansion of settlement (6563 km2) and agricultural land (1802 km2) for the period 1990-2020. Examination of the temporal changes of vegetation indices and LST showed that the values of all indices decreased while the LST increased. The negative correlation between NDVI value and LST indicates that the vegetation in our study was subject to drought-induced shocks. This study reveals the current situation of the vegetation health in the north-western region of Bangladesh in relation to the drought conditions. The findings of this study have practical implications for the policymakers in implementing necessary measures for agriculture, forests, water development, and economic zone planning.