Comparison of K-Means and K-Medoids Algorithms for Clustering of Potential Flood-Prone Areas in Bengkulu Province

This research investigates the likelihood of flooding in Bengkulu Province, an area prone to flood events. Key factors such as heavy rainfall, mountainous terrain, changes in land use, insufficient drainage infrastructure, and the impact of climate change contribute significantly to the occurrence of floods in this region. Utilizing Quantum GIS, this study incorporates rainfall data and river distances from district centers to analyze the potential flood susceptibility of different areas. Employing clustering techniques, specifically K-means and Kmedoids, the research identifies areas at higher risk of flooding. The findings indicate that employing K-means with five clusters yields superior outcomes, while K-medoids with two clusters also provide valuable insights. By leveraging Geographic Information Systems (GIS), flood-prone areas can be effectively mapped, enhancing the comprehension and mitigation of flood risks. Recommendations stemming from this study include prioritizing common and pertinent factors related to flood disasters, enhancing website user experience through UI/UX enhancements, and improving online accessibility measures.