The COVID-19 outbreaks revealed a severe healthcare crisis with many loopholes in the global healthcare system. It is more crucial to quantify COVID-19 cases when COVID-19 occurs in humid to semi-humid climatic conditions. There are issues with a lack of meteorological and air pollution data and future information on COVID-19 mortality, as is the case in Bangladesh. To deal with this issue, the present research aims to apply four single artificial intelligence models, including additive regression (AR), M5P tree (M5P), random subspace (RSS), and support vector machine (SVM), and construct their stacking hybrid ensemble models for predicting COVID-19 mortality cases at five sites in greater Dhaka City, Bangladesh. The proposed methods were developed using a total of eight input datasets that included climatic factors such as relative humidity, temperature, precipitation, wind speed, and air pollutants including sulfur dioxide (SO2), ozone (O3), carbon monoxide (CO), and nitrate oxide (NO2). Various input data combinations are appraised according to predictive performance, utilizing statistical tests and graphical presentation. The datasets were categorized into two classes (68:32) for model generation (training data) and model validation (testing data) with a fivefold cross-validation technique. Results show that SVM is superior to other AR, M5P, and RSS models (R² testing = 0.86–0.91, MAE = 1.33–2.02, RMSE = 3.12–3.85, RAE% = 19.68–29.86, and RRSE% = 40.58–41.01). The sensitivity analysis findings reveal a higher sensitivity for all input parameters selected except CO in the predictive results. Relative humidity, wind speed, and SO2 were the three input parameters that most influenced the results of subset regression and sensitivity analysis. The SVM is a promising method because it can predict COVID-19 mortality in greater Dhaka City with fewer input parameters. The suggested model developed in this research produced satisfactory outcomes in COVID-19 mortality prediction. It will be a new method for future COVID-19 prevention for policymakers and health experts. Serious social concern and robust public health measures may lessen the environmental impact of COVID-19 cases.