Abstract
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.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
Data will be available upon reasonable request to the corresponding authors.
Code availability
Code will be available upon reasonable request to the corresponding authors.
References
ADB (2021) Bangladesh Climate and Disaster Risk Atlas. Asian Development Bank. Mandaluyong City, Philippines. https://www.adb.org/sites/default/files/publication/760776/bangladesh-climate-disaster-risk-atlas-volume1-cover-pg29.pdf.Accessed 2 Dec 2021
Ahmed MM, Hoque ME, Rahman S et al (2022) Prediction of COVID-19 cases from the nexus of air quality and meteorological phenomena: Bangladesh perspective. Earth Syst Environ 6:307–325. https://doi.org/10.1007/s41748-021-00278-7
Alali Y, Harrou F, Sun Y (2022) A proficient approach to forecast COVID-19 spread via optimized dynamic machine learning models. Sci Rep 12:2467. https://doi.org/10.1038/s41598-022-06218-3
Al-Hasib A, Argha DBP (2021) Covid-19: Lack of coronavirus wastes management- an upcoming threat for the megacity Dhaka. 6th International Conference on Engineering Research, Innovation and Education. Sylhet, Bangladesh, pp 642–648
Ali M, Talha A, Berkouk EM (2020) New M5P model tree-based control for doubly fed induction generator in wind energy conversion system. Wind Energy 23(9):1831–1845. https://doi.org/10.1002/we.2519
Al-qaness MAA, Ewees AA, Fan H, Abd El Aziz M (2020) Optimization method for forecasting confirmed cases of COVID-19 in China. J Clin Med 9:674. https://doi.org/10.3390/jcm9030674
Al-Zaman MS (2020) Healthcare crisis in Bangladesh during the COVID-19 pandemic. Am J Trop Med Hyg 103(4):1357–1359. https://doi.org/10.4269/ajtmh.20-0826
Argha DBP, Al-Hasib A. Rahman MM (2021) A comparative study on the variation of air quality index of Dhaka City before and after the nationwide lockdown due to COVID-19. In 6th International Conference on Engineering Research, Innovation and Education (2021). Sylhet, Bangladesh.
Auler AC, Cássaro FAM, da Silva VO, Pires LF (2020) Evidence that high temperatures and intermediate relative humidity might favor the spread of COVID-19 in tropical climate: a case study for the most affected Brazilian cities. Sci Total Environ 729:139090. https://doi.org/10.1016/j.scitotenv.2020.139090
Bashir MF, Maa B, Bilal Komal B, Bashir MA, Tan D, Bashir M (2020) Correlation between climate indicators and COVID-19 pandemic in New York, USA. Sci Total Environ. 728:138835. https://doi.org/10.1016/j.scitotenv.2020.138835
Breiman L, Friedman JH (1985) Estimating optimal transformations for multiple regression and correlation. J Am Stat Assoc 80:580–598. https://doi.org/10.1080/01621459.1985.10478157
Chakraborty T, Ghosh I (2020) Real-time forecasts and risk assessment of novel coronavirus (COVID-19) cases: a data-driven analysis. Chaos Solitons Fractals 135:109850. https://doi.org/10.1016/j.chaos.2020.109850
Deif MA, Solyman AAA, Alsharif MH, Jung S, Hwang EA (2022) hybrid multi-objective optimizer-based SVM model for enhancing numerical weather prediction: a study for the Seoul Metropolitan Area. Sustainability 14(1):296. https://doi.org/10.3390/su14010296
Faisal AA, Kafy A, Fattah MA, Jahir DMA, Rakib AA, Rahman ZA, Ferdousi J, Huang X (2022) Assessment of temporal shifting of PM2.5, lockdown effect, and influences of seasonal meteorological factors over the fastest-growing megacity. Dhaka Spat Inf Res 30(3):441–453. https://doi.org/10.1007/s41324-022-00441-w
Gautam S (2020) COVID-19: air pollution remains low as people stay at home. Air Qual Atmos Health 13:7. https://doi.org/10.1007/s11869-020-00842-6
Geyman J (2021) COVID-19 has revealed America’s broken health care system: what can we learn? Int J Health Serv 51(2):188–194. https://doi.org/10.1177/0020731420985640
Gholami R, Fakhari N (2017) Chapter 27 – Support vector machine: principles, parameters, and applications. In P. Samui, S. Sekhar & V.E. Balas (Eds.), Handbook of Neural Computation. 515–535 . https://doi.org/10.1016/B978-0-12-811318-9.00027-2
Gupta A, Jain V, Singh A (2021) Stacking ensemble-based intelligent machine learning model for predicting post-COVID-19 complications. New Gener Comput 40:987–1007. https://doi.org/10.1007/s00354-021-00144-0
Ho TK (1998) The random subspace method for constructing decision forests. IEEE Trans. Pattern Anal Mach Intell 20(8):832–844
Islam S, Islam R, Mannan F, Rahman S, Islam T (2020) COVID-19 pandemic: an analysis of the healthcare, social and economic challenges in Bangladesh. Prog Dis Sci 8:100135. https://doi.org/10.1016/j.pdisas.2020.100135
Islam ARMT, Hasanuzzaman M, Azad MAK, Salam R, Toshi FZ, Khan MSI, Alam GMM, Ibrahim SM (2021) Effect of meteorological factors on COVID-19 cases in Bangladesh. Environ Dev Sustain 23:9139–9162. https://doi.org/10.1007/s10668-020-01016-1
Islam ARMT, Al Awadh M, Mallick J et al (2023) Estimating ground-level PM2.5 using subset regression model and machine learning algorithms in Asian megacity, Dhaka. Bangladesh. Air Qual Atmos Health 6(6):1117–1139. https://doi.org/10.1007/s11869-023-01329-w
Kafieh R, Arian R, Saeedizadeh N, Amini Z, Serej ND, Minaee S, Yadav SK, Vaezi A, Rezaei N, Javanmard SH (2021) COVID-19 in Iran: forecasting pandemic using deep learning. Comput Math Methods Med 2021:1–16. https://doi.org/10.1155/2021/6927985
Kaur H, Mohanty MN (2022) Chapter 4 – COVID-19 outbreak analysis and prediction using statistical learning. In S. De, S. Bhattacharyya, S. Dey, S. Bhatia (Eds.), Advanced Data Mining Tools and Methods for Social Computing. 67–84 . https://doi.org/10.1016/B978-0-32-385708-6.00011-4
Karmokar J, Islam M, Uddin M et al (2022) An assessment of meteorological parameters effects on COVID-19 pandemic in Bangladesh using machine learning models. Environ Sci Pollut Res 29:67103–67114. https://doi.org/10.1007/s11356-022-20196-z
Kong JD, Tekwa EW, Gignoux-Wolfsohn SA (2021) Social, economic, and environmental factors influencing the basic reproduction number of COVID-19 across countries. PlosONE 16(6):e0252373. https://doi.org/10.1371/journal.pone.0252373
Li L, Yang Z, Dang Z, Meng C, Huang J, Meng H, Wang D, Chen G, Zhang J, Peng H, Shao Y (2020) Propagation analysis and prediction of the COVID-19. Infect Dis Model 5:282–292. https://doi.org/10.1016/j.idm.2020.03.002
Lupu D, Tiganasu R (2022) COVID-19 and the efficiency of health systems in Europe. Health Econ Rev 12:14. https://doi.org/10.1186/s13561-022-00358-y
Martelletti L, Martelletti P (2020) Air pollution and the novel COVID-19 disease: a putative disease risk factor. SN Compr Clin Med 2(4):383–387. https://doi.org/10.1007/s42399-020-00274-4
Masum AK, Khushbu SA, Keya M, Abujar S, Hossain SA (2020) COVID-19 in Bangladesh: a deeper outlook into the forecast with prediction of upcoming per day cases using time series. Procedia Comput Sci 178:291–300. https://doi.org/10.1016/j.procs.2020.11.031
Migriño J, Batangan ARU (2020) Using machine learning to create a decision tree model to predict outcomes of COVID-19 cases in the Philippines: decision tree for COVID-19 cases. Western Pac Surveill Response J 12(3):56–64. https://doi.org/10.5365/wpsar.2021.12.3.831
Moftakhar L, Seif M, Safe MS (2020) Exponentially increasing trend of infected patients with covid-19 in Iran: a comparison of neural network and ARIMA forecasting models. Iranian Journal of Public Health 49. https://doi.org/10.18502/ijph.v49is1.3675
Nadakinamani NG, Reyana A, Kautish S, Vibith AS, Gupta Y, Abdelwabhab SF, Mohamed AW (2022) Clinical data analysis for prediction of cardiovascular disease using machine learning techniques. Comput Intell Neurosci 2022:2973324. https://doi.org/10.1155/2022/2973324
Omran NF, Ghany SFA, Saleh H, Ali AA, Gumaei A, Al-Rakhami M (2021) Applying deep learning methods on time-series data for forecasting covid-19 in Egypt, Kuwait, and Saudi Arabia. Complexity, 2021. https://doi.org/10.1155/2021/6686745
Pavel MRS, Zaman SU, Jeba F, Islam MS, Salam A (2021) Long-term (2003–2019) air quality, climate variables, and human health consequences in Dhaka, Bangladesh. Frontiers in Sustainable Cities. 3. https://doi.org/10.3389/frsc.2021.681759
Perc M, Miksić GN, Slavinec M, Stozer A (2020) Forecasting COVID-19. Front Phys 8:127. https://doi.org/10.3389/fphy.2020.00127
Perone G (2020) An ARIMA model to forecast the spread and the final size of COVID-2019 epidemic in Italy. SSRN Electron J. https://doi.org/10.1101/2020.04.27.20081539
Pisner DA, Schnyer DM (2020) Chapter 6 – Support vector machine. In A. Mechelli & S. Vieira (Eds.), Machine Learning Methods and Applications to Brain Disorders. 101–121. https://doi.org/10.1016/B978-0-12-815739-8.00006-7
Rahman MS, Azad MAK, Hasanuzzaman N, Salam R, Islam ARMT, Rahman MM, Hoque MMM (2021) How air quality and COVID-19 transmission change under different lockdown scenarios? A case from Dhaka city. Bangladesh. Sci Total Environ 762:143161. https://doi.org/10.1016/j.scitotenv.2020.143161
Sakib SN, Islam ARMT, Azad MAZ, Mallick J, Ahmed M, Pal SC, Islam MS, Hu Z, Alam E, Malafaia G (2023) Seasonality of meteorological factors influencing the COVID-19 era in coastal and inland regions of bangladesh. Geocarto Int 38:1. https://doi.org/10.1080/10106049.2023.2203115
Satu MS, Howlader KC, Mahmud M., Kaiser, M.S., Islam, SMSM, Quinn JMW, Alyami SA, Moni MA (2021) Short-term prediction of covid-19 cases using machine learning models. Applied Sciences 11. https://doi.org/10.3390/app11094266
Shakhovska N, Yakovyna V, Chopyak V (2022) A new hybrid ensemble machine-learning model for severity risk assessment and post-COVID prediction system. Math Biosci Eng 19(6):6102–6123. https://doi.org/10.3934/mbe.2022285
Shams SA, Haleem A, Javaid M (2020) Analyzing COVID-19 pandemic for unequal distribution of tests, identified cases, deaths, and fatality rates in the top 18 countries. Diabetes and Metabolic Syndrome: Clinical Research and Reviews 14. https://doi.org/10.1016/j.dsx.2020.06.051
Tosepu R, Gunawan J, Effendy DS, Ahmad LOAI, Lestari H, Bahar H, Asfian P (2020) Correlation between weather and COVID-19 pandemic in Jakarta. Indonesia Sci Total Environ 725:1384369. https://doi.org/10.1016/j.scitotenv
WHO (2021) COVID-19 weekly epidemiological update, edition 47. World Health Organization. https://apps.who.int/iris/handle/10665/342524. Accessed 6 July 2021
Witten IH, Frank E., Hall MA., Pal CJ (2017) Chapter 12 – Ensemble learning. In Ian H. Witten, Eibe Frank, Mark A. Hall, Christopher J. Pal (Eds.) Data Mining (Fourth Edition). 479–501. https://doi.org/10.1016/B978-0-12-804291-5.00012-X
Wu Y, **g W, Liu J, Ma Q, Yuan J, Wang Y, Du M, Liu M (2020) Effects of temperature and humidity on the daily new cases and new deaths of COVID-19 in166 countries. Sci Total Environ 729:139051. https://doi.org/10.1016/j.scitotenv.2020.139051
Yang L, Liu S, Tsoka S, Papageorgiou LG (2022) A regression tree approach using mathematical programming. Expert Syst Appl 78:347–357. https://doi.org/10.1016/j.eswa.2017.02.013
Yang D, Hakkarainen J, Liu Y, Ialongo I, Cai Z, Tamminen J (2023) Detection of anthropogenic CO2 emission signatures with TanSat CO2 and with Copernicus Sentinel-5 precursor (S5P) NO2 measurements: first results. Adv Atmos Sci 40:1–5. https://doi.org/10.1007/s00376-022-2237-5
Zhang T, Geng G, Liu Y, Chang HH (2020) Application of Bayesian additive regression trees for estimating daily concentrations of PM2.5 components. Atmosphere. 11(11):1233. https://doi.org/10.3390/atmos11111233
Acknowledgements
We acknowledge the anonymous reviewer to improve the quality of the manuscript. The authors would like to thank the Bangladesh Meteorological Department (BMD), and the Department of Environment (DOE) for providing the related datasets for this research.
Funding
Authors thankfully acknowledge the Deanship of Scientific Research providing administrative and financial supports. Funding for this research was given under award numbers RGP2/363/44 by the Deanship of Scientific Research; King Khalid University, Ministry of Education, Kingdom of Saudi Arabia.
Author information
Authors and Affiliations
Contributions
A. R. M. T. I. designed, conceptualized, and drafted the original manuscript and planned the documents; M. A. F. and S. C. P. were involved in the literature review, software, map**, statistical analysis, interpretation of the analysis, and discussion; M. S. and M. C. R. contributed to instrumental setup, data analysis, and validation; M. M. M. contributed to data collection and extraction; Islam, A. R. M. T., J. M., A. E., and M. A. P. had done the internal review and proofreading during the manuscript drafting stage.
Corresponding author
Ethics declarations
Ethics approval
Not applicable.
Consent to participate
Not applicable.
Consent for publication
Not applicable.
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Islam, A.R.M.T., Elbeltagi, A., Mallick, J. et al. Application of optimal subset regression and stacking hybrid models to estimate COVID-19 cases in Dhaka, Bangladesh. Theor Appl Climatol 154, 797–814 (2023). https://doi.org/10.1007/s00704-023-04589-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00704-023-04589-9