International Journal on Advanced Science, Engineering and Information Technology, Vol. 13 (2023) No. 2, pages: 632-637, DOI:10.18517/ijaseit.13.2.18292

Transformer-based Deep Learning for COVID-19 Prediction Based on Climate Variables in Indonesia

- Kurnianingsih, Anindya Wirasatriya, Lutfan Lazuardi, Adi Wibowo, Nurseno Bayu Aji, Beno Kunto Pradekso, Sigit Prasetyo, Eri Sato-Shimokawara


Recent research on the effect of climate variables on coronavirus (COVID-19) transmission has emerged. Climate change has the potential to cause new viral outbreaks, illness, and death. This study contributes to COVID-19 disease prevention efforts. This study makes two contributions: (1) we investigated the impact of climate variables on the number of COVID-19 cases in 34 Indonesian provinces; and (2) we developed a transformer-based deep learning model for time series forecasting for the number of positive COVID-19 cases the following day based on climate variables in 34 Indonesian provinces. We obtained data from March 15, 2020 to July 22, 2021 on the number of positive COVID-19 cases and climate change variables (wind, temperature, humidity) in Indonesia. To examine the effect of climate change on the number of positive COVID-19 cases, we employed 15 scenarios for training. The experiment results of the proposed model show that the combination of wind speed and humidity has a weakly positive correlation with positive COVID-19 incidence. However, temperature has a considerably negative association with positive COVID-19 incidences. Compared to the other testing scenarios, the transformer-based deep learning model produced the lowest MAE of 175.96 and the lowest RMSE of 375.81. This study demonstrates that the transformer model works well in several provinces, such as Sumatra, Java, Papua, Bali, West Nusa Tenggara, East Nusa Tenggara, East Kalimantan, and Sulawesi, but not in Central Kalimantan, West Sulawesi, South Sulawesi, and North Sulawesi.


COVID-19 prediction; climate variables; transformer-based deep learning

Viewed: 140 times (since abstract online)

cite this paper     download