Sains Malaysiana 53(11)(2024): 3831-3843

http://doi.org/10.17576/jsm-2024-5311-24

 

The Effect of Meteorology and Air Quality to the COVID-19 Cases in Malaysia: A Multivariate Deep Learning Approach

(Kesan Meteorologi dan Kualiti Udara kepada Kes COVID-19 di Malaysia: Suatu Pendekatan Pembelajaran Mendalam Multivariat)

 

PEGGY YEO¹, AZURALIZA ABU BAKAR^1,*, ZALINDA OTHMAN¹, MAZRURA SAHANI², SUHAILA ZAINUDIN¹ & ZAILIZA SULI³

 

¹Center for Artificial Intelligence Technology, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, 43600 UKM Bangi, Selangor, Malaysia
²Center for Toxicology and Health Risk Studies (CORE), Faculty of Heath Sciences, Universiti Kebangsaan Malaysia, Jalan Raja Muda Abdul Aziz, 50300 Kuala Lumpur, Malaysia
³Hulu Langat District Health Office, 43000 Kajang, Selangor, Malaysia

 

Received: 7 December 2023/Accepted: 4 October 2024

 

Abstract

In October 2022, the World Health Organization (WHO) reported that over six hundred million people globally had been infected by the COVID-19 pandemic, leading to six million deaths. Malaysia, like many other countries, has experienced significant economic and societal impacts due to COVID-19. Previous research has identified meteorological conditions and air quality as critical factors influencing the spread of infectious diseases like influenza. In this study, we explore the impact of meteorological and air quality factors on COVID-19 case numbers in Malaysia, focusing on a case study in the Hulu Langat district of Selangor state, utilizing a deep learning approach. Our model, which employs a neural network architecture incorporating both Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN), was trained using multivariate time-series data. This data included meteorological and air quality metrics from the Department of Environment, Malaysia, and COVID-19 case data collected from the Hulu Langat Health Office. We prepared three datasets for predictive modeling: one combining all features, one including only meteorological data, and another with only air quality data. Our results indicate that the CNN model outperformed the LSTM model in terms of prediction accuracy. Furthermore, the dataset incorporating all features resulted in the lowest prediction error, compared to datasets with only meteorological or air quality features. Feature importance analysis showed that air quality factors were the most significant predictors, suggesting that air quality has a greater impact on COVID-19 case numbers than meteorological factors.

 

Keywords: Air quality; COVID-19 cases; feature ranking; meteorology; multivariate LSTM and CNN

 

Abstrak

Pada Oktober 2022, Pertubuhan Kesihatan Sedunia (WHO) melaporkan bahawa lebih enam ratus juta orang di seluruh dunia telah dijangkiti oleh pandemik COVID-19, yang membawa kepada enam juta kematian. Malaysia, seperti kebanyakan negara lain, telah mengalami kesan ekonomi dan sosial yang ketara akibat COVID-19. Penyelidikan sebelum ini telah mengenal pasti keadaan meteorologi dan kualiti udara sebagai faktor kritikal yang mempengaruhi penyebaran penyakit berjangkit seperti influenza. Dalam kajian ini, kami meneroka kesan faktor meteorologi dan kualiti udara terhadap bilangan kes COVID-19 di Malaysia, memfokuskan kepada kajian kes di daerah Hulu Langat, Selangor menggunakan pendekatan pembelajaran mendalam. Model kami yang menggunakan seni bina rangkaian saraf yang menggabungkan Memori Jangka Pendek Panjang (LSTM) dan Rangkaian Neural Konvolusi (CNN) telah dilatih menggunakan data siri masa multivariat. Data ini termasuk metriks meteorologi dan kualiti udara daripada Jabatan Alam Sekitar, Malaysia dan data kes COVID-19 yang dikumpul daripada Pejabat Kesihatan Hulu Langat. Kami menyediakan tiga set data untuk pemodelan ramalan: satu menggabungkan semua ciri, satu hanya data meteorologi dan satu lagi dengan hanya data kualiti udara. Keputusan kami menunjukkan bahawa model CNN mengatasi model LSTM dari segi ketepatan ramalan. Tambahan pula, set data yang menggabungkan semua ciri menghasilkan ralat ramalan yang paling rendah, berbanding set data dengan hanya ciri meteorologi atau kualiti udara. Analisis kepentingan ciri mendedahkan bahawa faktor kualiti udara adalah peramal yang paling penting, menunjukkan bahawa kualiti udara mempunyai kesan yang lebih besar terhadap bilangan kes COVID-19 berbanding faktor meteorologi.

 

Kata kunci: Kedudukan ciri; kes COVID-19; kualiti udara; meteorologi; multivariat LSTM dan CNN

 

REFERENCES

Adhikari, A. & Yin, J. 2021. Lag effects of ozone, PM_2.5, and meteorological factors on COVID-19 new cases at the disease epicenter in queens, New York. Atmosphere 12(3): 357.

Ali, N. & Islam, F. 2020. The effects of air pollution on COVID-19 infection and mortality - A review on recent evidence. Frontiers in Public Health 8: 580057.

Felix Gers, FA., Schraudolph, NN., & Schmidhuber, J. 2002. Learning precise timing with LSTM recurrent networks. Journal of machine learning research. 115-143

Ghobakhloo, S., Miranzadeh, M.B., Ghaffari, Y., Ghobakhloo, Z. & Mostafaii, G.R. 2022. Association between air pollution, climate change, and COVID-19 pandemic: A review of recent scientific evidence. Health Scope 11(4): e122412. https://doi.org/10.5812/jhealthscope-122412

Goodfellow, I., Bengio, Y. & Courville, A. 2016. Deep Learning. Massachusetts: MIT Press. http://www.deeplearningbook.org   

Hasan, R.A. & Jamaludin, J.E. 2023. Prediction of COVID-19 cases for Malaysia, Egypt, and USA using deep learning models. Malaysian Journal of Fundamental and Applied Sciences 19: 417-428.

Jalaludin, J., Wan Mansor, W.N., Abidin, N.A., Suhaimi, N.F. & Chao, H-R. 2023. The impact of air quality and meteorology on COVID-19 cases at Kuala Lumpur and Selangor, Malaysia and prediction using machine learning. Atmosphere 14(6): 973. https://doi.org/10.3390/atmos14060973

Kelleher, J.D., Namee, B.M. & D’Arcy, A. 2020. Fundamentals of Machine Learning for Predictive Data Analytics Algorithms, Worked Examples, and Case Studies. 2nd ed. Massachusetts: MIT Press.

Khan, Z., Ualiyeva, D., Khan, A., Zaman, N., Sapkota, S., Khan, A., Ali, B. & Ghafoor, D. 2021. A correlation among the COVID-19 spread, particulate matters, and angiotensin-converting enzyme 2: A review. Journal of Environmental and Public Health 2021: 5524098.

Lloyd, B.N. & Viswanathan, P.M. 2022. A long term observation of meteorological influence on COVID-19 pandemic spread in Malaysia - A case study. Journal of Climate Change 8(1): 67-96.

Madini, O.A., Mutasem, J. & Reem, A. 2022. Time series predicting of COVID-19 based on deep learning. Neurocomputing 468: 335-344. https://doi.org/10.1016/j.neucom.2021.10.035

Mohan Viswanathan, P., Sabarathinam, C., Karuppannan, S. & Gopalakrishnan, G. 2022. Determination of vulnerable regions of SARS-CoV-2 in Malaysia using meteorology and air quality data. Environment, Development and Sustainability 24(6): 8856-8882. https://doi.org/10.1007/s10668-021-01719-z

Mohd Halim, N.F., Mohd Zahid, A.Z., Salleh, M.Z.M. & Abu Bakar, A.A. 2022. Air quality status during pandemic COVID 19 in urban and sub-urban area in Malaysia. IOP Conf. Ser.: Earth Environ. Sci. 1019: 012044.

Nielsen, M.A. 2015. Neural Networks and Deep Learning. Determination Press.

Ogunjo, S.T., Fuwape, I.A. & Rabiu, A.B. 2022. Predicting COVID-19 cases from atmospheric parameters using machine learning approach. GeoHealth 6(4): e2021GH000509. https://doi.org/10.1029/2021GH000509

Ramirez-Alcocer, U.M., Tello-Leal, E., Macías-Hernández, B.A. & Hernandez-Resendiz, J.D. 2022. Data-driven prediction of COVID-19 daily new cases through a hybrid approach of machine learning unsupervised and deep learning. Atmosphere 13(8): 1205. https://doi.org/10.3390/atmos13081205

Shen, N.W., Bakar, A.A. & Mohamad, H. 2023. Univariate and multivariate long short term memory (LSTM) model to predict COVID-19 cases in Malaysia using integrated meteorological data. Malaysian Journal of Fundamental and Applied Sciences 19: 653-667.

Valsamatzi-Panagiotou, A. & Penchovsky, R. 2022. Environmental factors influencing the transmission of the coronavirus 2019: A review. Environmental Chemistry Letters 20(3): 1603-1610.

WHO. 2022. WHO Coronavirus (COVID-19) Dashboard | WHO Coronavirus (COVID-19) dashboard with vaccination data. https://covid19.who.int/ (Accessed on 4 December 2022).

Yu, Z., Abdel-Salam, A.S.G., Sohail, A. & Alam, F. 2021. Forecasting the impact of environmental stresses on the frequent waves of COVID19. Nonlinear Dynamics 106(2): 1509-1523.

Zhou, N., Dai, H., Zha, W. & Lv, Y. 2022. The impact of meteorological factors and PM_2.5 on COVID-19 transmission. Epidemiology and Infection 150: e38. https://doi.org/10.1017/S0950268821002570

 

*Corresponding author; email: azuraliza@ukm.edu.my