IPB University Logo

SCIENTIFIC REPOSITORY

IPB University Scientific Repository collects, disseminates, and provides persistent and reliable access to the research and scholarship of faculty, staff, and students at IPB University

AI Repository
 
Building and Categories


      View Item 
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - School of Data Science, Mathematic and Informatics
      • UF - Statistics and Data Sciences
      • View Item
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - School of Data Science, Mathematic and Informatics
      • UF - Statistics and Data Sciences
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Penerapan Algoritma Self Organizing Maps (SOM) dan K-Medoids dalam Penggerombolan Kabupaten/Kota Terdampak Banjir di Sumatra

      Thumbnail
      Date
      2026
      Jenis/Type
      Skripsi
      Subtype
      Undergraduate Theses
      Author
      HESTY
      Silvianti, Pika
      Susetyo, Budi
      Metadata
      Show full item record
      Abstract
      Banjir merupakan salah satu bencana hidrometeorologi yang dominan di Indonesia yang menyebabkan kerugian besar pada korban jiwa dan infrastruktur. Pada akhir November 2025, banjir bandang melanda Provinsi Aceh, Sumatra Utara, dan Sumatra Barat dengan dampak yang beragam antarkabupaten/kota. Penelitian ini bertujuan mengelompokkan 53 kabupaten/kota terdampak berdasarkan karakteristik dampak banjir menggunakan metode Self Organizing Maps (SOM) dan K-Medoids. Data yang digunakan mencakup sembilan indikator dampak banjir yang bersumber dari Badan Nasional Penanggulangan Bencana (BNPB) periode November 2025 hingga Februari 2026. Evaluasi kinerja model dilakukan menggunakan Silhouette Index (SI), Davies-Bouldin Index (DBI), dan rasio simpangan baku. Hasil menunjukkan bahwa SOM dengan k = 4 memberikan performa terbaik dengan SI sebesar 0,408, DBI sebesar 1,001, dan rasio simpangan baku sebesar 0,176, dibandingkan K-Medoids. Penggerombolan menghasilkan empat gerombol dengan karakteristik yang berbeda, yaitu gerombol dengan dampak paling ekstrem, gerombol dengan korban jiwa tinggi, gerombol dengan kerusakan infrastruktur transportasi yang dominan, dan gerombol dengan dampak relatif rendah pada seluruh indikator. Temuan ini diharapkan menjadi dasar dalam perumusan kebijakan penanggulangan bencana yang lebih efektif dan tepat sasaran sesuai dengan karakteristik dampak masing-masing wilayah.
       
      Floods are one of the most prevalent hydrometeorological disasters in Indonesia, causing significant losses in terms of human lives and infrastructure. In late November 2025, flash floods struck the provinces of Aceh, North Sumatra, and West Sumatra, with varying impacts across districts and cities. This study aims to cluster the 53 affected districts and cities based on flood impact characteristics using the Self Organizing Maps (SOM) and K-Medoids methods. The data used included nine flood impact indicators sourced from the National Disaster Management Agency (BNPB) for the period from November 2025 to February 2026. Model performance was evaluated using the Silhouette Index (SI), the Davies-Bouldin Index (DBI), and the standard deviation ratio. The results show that SOM with k = 4 delivers the best performance, with an SI of 0,408, a DBI of 1,001, and the standard deviation ratio of 0.176, compared to K-Medoids. The clustering yielded four clusters with distinct characteristics, a cluster with the most extreme impacts, a cluster with high fatalities, a cluster with dominant damage to transportation infrastructure, and a cluster with relatively low impacts across all indicators. These findings are expected to serve as a basis for formulating more effective and targeted disaster management policies tailored to the specific impact characteristics of each region.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/178654
      Collections
      • UF - Statistics and Data Sciences [171]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository