Classification of Flood Impact Levels in North Sumatra Province Using the K-Nearest Neighbor (KNN) Algorithm
DOI:
https://doi.org/10.64803/juikti.v2i1.103Keywords:
Banjir, Dampak Banjir, Klasifikasi, Data Mining, K-Nearest NeighborAbstract
Floods are one of the natural disasters that need to be anticipated because they can cause significant impacts on society, including infrastructure damage and loss of life. The National Disaster Management Agency (BNPB) and the Regional Disaster Management Agency (BPBD) play an important role in collecting and providing flood-related data as a basis for decision-making in disaster management. This study aims to classify the level of flood impact in North Sumatra Province using a data mining approach with classification techniques. The dataset used in this study consists of flood impact data obtained from BNPB and BPBD of North Sumatra Province, including the number of damaged houses, the number of evacuees, the number of fatalities, the number of missing persons, and the number of damaged public facilities. The data mining process follows the Knowledge Discovery in Databases (KDD) stages, which include data selection, preprocessing, normalization, classification, and evaluation. The algorithm applied in this study is the K-Nearest Neighbor (KNN) algorithm. Data processing and testing were conducted using RapidMiner software. The experimental results show that the KNN algorithm is able to classify flood impact levels into three classes, namely low, medium, and high, with the best accuracy of 89.47%. These results indicate that the KNN algorithm is sufficiently effective for classifying flood impact levels in North Sumatra Province based on disaster impact data.
References
[1] F. Seftiani and R. Handawati, “Pemetaan Tingkat Bahaya Banjir Menggunakan Metode Penginderaan Jauh Di Kecamatan Jatinegara Kota Administrasi Jakarta Timur,” vol. 2, no. 2, pp. 48–55, 2023.
[2] B. Mufarida, “BNPB Catat 74 Bencana Landa Tanah Air di Awal 2025, Banjir Mendominasi.” Accessed: Jan. 19, 2026. [Online]. Available: https://nasional.sindonews.com/read/1516047/15/bnpb-catat-74-bencana-landa-tanah-air-di-awal-2025-banjir-mendominasi-1736820077?
[3] Z. Sembiring et al., “Didaktik : Jurnal Ilmiah PGSD FKIP UNIVERSITAS MANDIRI ISSN Cetak : 2477-5673 ISSN Online : 2614-722X Volume 11 Nomor 02 , Juni 2025 Didaktik : Jurnal Ilmiah PGSD FKIP UNIVERSITAS MANDIRI ISSN Cetak : 2477-5673 ISSN Online : 2614-722X Volume 11 Nomor 02 , Juni 2025,” vol. 11, pp. 366–371, 2025.
[4] A. Penyebab, D. A. N. Dampak, B. Di, and K. Anggrung, “terjadi di Indonesia, termasuk di Kelurahan Anggrung,” vol. 5, no. 6, 2024.
[5] Elfa Harahap, “Kabupaten-Kota yang Terdampak Banjir Longsor di Sumut Bertambah,” Mistar.ID. Accessed: Jan. 19, 2026. [Online]. Available: https://mistar.id/news/medan/kabupatenkota-yang-terdampak-banjir-longsor-di-sumut-bertambah
[6] N. Anggraini, B. Pangaribuan, A. P. Siregar, and G. Sintampalam, “ANALISIS PEMETAAN DAERAH RAWAN BANJIR DI KOTA MEDAN TAHUN 2020,” vol. 4, no. 2, pp. 27–33, 2021.
[7] N. Bayes et al., “Pеrbаndіngаn Tеknіk Klаsifikаsi Dаtа Mining untuk Pеnеntuаn Jеnіѕ Jаmur Bеrаcun,” vol. 5, no. 3, pp. 23–31, 2024.
[8] S. Setyaningtyas, B. I. Nugroho, and Z. Arif, “TINJAUAN PUSTAKA SISTEMATIS PADA DATA MINING : STUDI KASUS ALGORITMA K-MEANS CLUSTERING,” vol. 10, no. 2, pp. 52–61, 2022.
[9] N. A. Ramadhani and H. A. Rosyid, “Algoritma – Algoritma Data Mining untuk Klasifikasi Data,” vol. 2, no. 12, pp. 550–556, 2022, doi: 10.17977/um068v2i122022pxxx-xxx.
[10] J. M. Informatika, S. I. Misi, C. P. Inayati, S. Lestanti, and S. Budiman, “RANCANG BANGUN APLIKASI PENGENALAN WAJAH,” vol. 8, pp. 1–12, 2025.
[11] P. Data et al., “Jurnal PIPA: Pendidikan Ilmu Pengetahuan Alam,” vol. 05, no. 01, pp. 42–45, 2024.
[12] A. Naïve, “Comparison of Data Mining Methods for Predition of Floods with Naïve Bayes and KNN Algorithm Perbandingan Metode Data Mining untuk Prediksi Banjir Dengan,” pp. 40–48, 2022.
[13] P. E. Putra, M. A. Amrullah, Y. H. Fauzi, and R. F. Saputri, “Penerapan Algoritma C4 . 5 untuk Klasifikasi Tingkat Korban Banjir di Indonesia,” vol. 3, no. c, pp. 1–7, 2025.
[14] S. M. Natzir, “Perbandingan Kinerja Model Pembelajaran Mesin dalam Prediksi Banjir menggunakan KNN , Naive Bayes , dan Random Forest,” vol. 14, no. c, pp. 59–64, 2023.
[15] J. Akbar, M. Ali, and S. Yudono, “Water Level Classification for Detect Flood Disaster Status using KNN and SVM,” vol. 13, pp. 298–302, 2024.
[16] A. Khusaeri, S. Ilham, D. Nurhasanah, D. Delpidat, and B. N. Sari, “Algoritma c4.5 untuk pemodelan daerah rawan banjir studi kasus kabupaten karawang jawa barat,” vol. 9, pp. 132–136, 2017.
[17] M. W. Martadiansyah, A. Ghufron, R. A. Hidayah, and D. Salzabila, “Perbandingan Algoritma C4 . 5 dengan Naive Bayes Untuk Klasifikasi Curah Hujan,” vol. 3, no. c, pp. 8–17, 2025.
[18] P. P. Haryoto, H. Okprana, and I. S. Saragih, “Algoritma C4 . 5 Dalam Data Mining Untuk Menentukan Klasifikasi Penerimaan Calon Mahasiswa Baru,” vol. 2, no. 5, pp. 358–364, 2021.
[19] E. Pitaloka et al., “Penerapan Machine Learning untuk Prediksi Bencana Banjir,” vol. 01, 2024, doi: 10.21456/vol14iss1pp62-76.
[20] A. Rizky, S. Achmadi, A. F. Setiawan, and T. Informatika, “PENERAPAN DATA MINING DENGAN ALGORITMA KNN UNTUK MENENTUKAN TINGKAT KERUSAKAN DRAINASE KOTA JOMBANG,” vol. 8, no. 5, pp. 8471–8478, 2024.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Maria Afri Yani, Dia Alemisa br Sembiiring, Sardo Pardingotan Sipayung (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
