Abstract—Changes in global weather patterns are sweeping the world, including Indonesia. One of the causes of this change was the El Niño event, where sea surface temperatures in the central Pacific Ocean experienced an increase. Apart from causing temperatures to increase, it also causes the intensity of rainfall to decrease, causing drought disasters. Anticipating natural disasters and disaster mitigation needs to be carried out to reduce their negative impacts. Efforts can be made by identifying areas with a high potential for drought and clustering areas based on the level of potential drought. This article focuses on extreme data from maximum temperatures in 34 provinces in Indonesia. Clustering was performed using the k-means and k-medoids methods and evaluated using the Davies-Bouldin index. Predict the highest maximum temperature in a specific period using the return level. The result shows that the k-means method is more suitable and better implemented by checking on the Davies-Boulding index, which is 0.9945.

Keywords—clustering, drought, k-means, k-medoids, maximum temperature

[PDF]

Cite: A'yunin Sofro, Elok Rizqi Auliya, Khusnia Nurul Khikmah, Danang Ariyanto, Riska Wahyu Romadhonia, and Hernando Ombao, "Clustering Provinces with Drought Risk Based on Daily Maximum Temperature," International Journal of Environmental Science and Development vol. 15, no. 2, pp. 69-76, 2024.

Copyright © 2024 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).