Implementation of DBSCAN and K-MEANS++ Methods for Flood Vulnerability Cluster Mapping in East Java Province, 2024

Zalfa Zaliana Nugrahanto, A'yunin Sofro

Abstract


Flood vulnerability in East Java varies across districts due to differences in hydrometeorological pressure and exposure levels. This study compares two clustering algorithms—DBSCAN and K-Means++—for identifying patterns in eleven flood-impact indicators. DBSCAN parameter selection was conducted using a k-distance graph, resulting in ε = 0.8 and MinPts = 3, which produced five clusters and three noise points. The Silhouette Index for DBSCAN was 0.3266, calculated including noise points to ensure fair evaluation against K-Means++, which obtained a Silhouette Index of 0.2453 for five clusters. The findings indicate that DBSCAN produced higher internal cohesion under the given dataset. However, the resulting clusters are not interpreted as validated flood risk zones or as physically causal patterns, due to the absence of external validation layers such as historical flood maps, hydrological data, or topographic information. The results therefore provide a methodological comparison between density-based and centroid-based clustering for flood-impact variables without making geographical or causal inferences.

Keywords


Flood vulnerability; DBSCAN, K-Means++; Clustering; East Java Province; Silhouette Index.

Full Text:

PDF

References


[1] Zhiyong Yuan et al. “Dynamic evolution and scenario-based prediction of urban flood resilience: A system dynamics modeling approach in Kunming, China”. In: Journal of Environmental Management 395 (2025), p. 127740. doi: 10.1016/j.jenvman.2025.127740.

[2] Muhammad Fadillah Ghifari, Komeyni Rusba, and Muhamad Ramdan. “Kebijakan Penanggulangan Bencana Banjir Dan Kebakaran Di Kota Balikpapan”. In: Identifikasi 10.1 (2024), pp. 156–160.

[3] James Lewi Duykers et al. “Identifying factors for supporting early warning flood using clustering approach and geo-spatial analysis”. In: Procedia Computer Science 227 (2023), pp. 540–547. doi: 10.1016/j.procs.2023.10.556.

[4] Emeka Austin Okoli et al. “Integrated flood susceptibility mapping using machine learning and geospatial techniques: A case study of Imo State, Southeastern Nigeria”. In: Journal of African Earth Sciences 233 (2026), p. 105872. doi: 10.1016/j.jafrearsci.2025.105872.

[5] Hongshi Xu et al. “Urban flooding risk assessment based on an integrated K-Means cluster algorithm and improved entropy weight method in the region of Haikou, China”. In: Journal of Hydrology 563 (2018), pp. 975–986. doi: 10.1016/j.jhydrol.2018.06.060.

[6] A. A. Abdulnassar and Latha R. Nair. “Performance analysis of K-Means with modified initial centroid selection algorithms and developed K-Means9+ model”. In: Measurement: Sensors 25 (2023), p. 100666. doi: 10.1016/j.measen.2023.100666.

[7] Santosh Kumar Majhi and Shubhra Biswal. “Optimal cluster analysis using hybrid K-Means and Ant Lion Optimizer”. In: Karbala International Journal of Modern Science 4.4 (2018), pp. 347–360. doi: 10.1016/j.kijoms.2018.09.001.

[8] Yan Tu, Zhenxing Tang, and Benjamin Lev. “Regional flood risk grading assessment considering indicator interactions among hazard, exposure, and vulnerability: A novel FlowSort with DBSCAN”. In: Journal of Hydrology 639 (2024), p. 131587. doi: 10.1016/j.jhydrol.2024.131587.

[9] Abdulhayat M. Jibrin et al. “New perspective on density-based spatial clustering of applications with noise for groundwater assessment”. In: Journal of Hydrology 661 (2025), p. 133566. doi: 10.1016/j.jhydrol.2025.133566.

[10] Omkaresh Kulkarni and Adnan Burhanpurwala. “A survey of advancements in DBSCAN clustering algorithms for big data”. In: 2024 3rd International Conference on Power Electronics and IoT Applications in Renewable Energy and its Control (PARC). IEEE. 2024, pp. 106–111. doi: 10.1109/PARC59193.2024.10486339.

[11] F. M. Martínez-García et al. “Distillation anomaly and fault detection based on clustering algorithms”. In: Journal of Industrial Information Integration 48 (2025), p. 100970. doi: 10.1016/j.jii.2025.100970.

[12] Suma Srinath and Nagaraju Baydeti. “Behavioral pattern clustering for thematic user segmentation in web interaction environments”. In: Information Sciences 724 (2026), p. 122745. doi: 10.1016/j.ins.2025.122745.

[13] Bowo Eko Cahyono et al. “Mapping flooded risk area in East Java Indonesia using remote sensing data”. In: Journal of Physics: Conference Series. Vol. 1825. 1. Bristol, UK: IOP Publishing, 2021, p. 012081. doi: 10.1088/1742-6596/1825/1/012081.

[14] Yoga Satria Iswandaru, Amien Widodo, and Moh. Singgih Purwanto. “Analysis of Flood Disaster Areas, Jombang Regency, East Java Using ArcGIS Remote Sensing”. In: Journal of Marine-Earth Science and Technology 2.3 (2021), pp. 78–82. doi: 10.12962/j27745449.v2i3.100.

[15] Petronilia Palinggik Allorerung et al. “Analisis Performa Normalisasi Data untuk Klasifikasi K-Nearest Neighbor pada Dataset Penyakit”. In: JISKA (Jurnal Informatika Sunan Kalijaga) 9.3 (2024), pp. 178–191. doi: 10.14421/jiska.2024.9.3.178-191.

[16] In-Kyoung Hong et al. “Investigating standardized criteria to evaluate the impact of agro-healing programs on psychological and interpersonal outcomes: Utilizing normalization methods”. In: Acta Psychologica 261 (2025), p. 105727. doi: 10.1016/j.actpsy.2025.105727.

[17] Friansyah Gani et al. “Implementation of K-Nearest Neighbor Algorithm on Density-Based Spatial Clustering Application with Noise Method on Stunting Clustering”. In: Jurnal Diferensial 6.2 (2024), pp. 170–178. doi: 10.35508/jd.v6i2.16278.

[18] Jiaxin Qian et al. “MDBSCAN: A multi-density DBSCAN based on relative density”. In: Neurocomputing 576 (2024), p. 127329. doi: 10.1016/j.neucom.2024.127329.

[19] Ying Liu et al. “An indoor thermal comfort model for group thermal comfort prediction based on K-means++ algorithm”. In: Energy and Buildings 327 (2025), p. 115000. doi: 10.1016/j.enbuild.2024.115000.

[20] Ponuku Sarah et al. “A novel approach to brain tumor detection using K-Means++, SGLDM, ResNet50, and synthetic data augmentation”. In: Frontiers in Physiology 15 (2024), pp. 1–14. doi: 10.3389/fphys.2024.1342572.

[21] Arwin Putra, Dahlan Abdullah, and Muhammad Daud. “Klasterisasi Kualitas Biji Kopi Berdasarkan Taraf Penyusutan Menggunakan Metode K-Harmonic Means dengan Validasi Silhouette Index dan C-index”. In: Jurnal Janitra Informatika dan Sistem Informasi 4.2 (2024), pp. 74–86. doi: 10.59395/f1jg3b72.




DOI: https://doi.org/10.18860/cauchy.v11i1.37410

Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 Zalfa Zaliana Nugrahanto, A’yunin Sofro

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Editorial Office
Mathematics Department,
Universitas Islam Negeri Maulana Malik Ibrahim Malang
Gajayana Street 50 Malang, East Java, Indonesia 65144
Faximile (+62) 341 558933
e-mail: cauchy@uin-malang.ac.id

Creative Commons License
CAUCHY: Jurnal Matematika Murni dan Aplikasi is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.