Please use this identifier to cite or link to this item:
https://repository.uksw.edu//handle/123456789/32366
Title: | Klasifikasi Daerah Rawan Banjir menggunakan 10-Fold Cross Validation dan K-Nearest Neighbors |
Other Titles: | Classification of Flood-Prone Areas Using 10-Fold Cross Validation and K-Nearest Neighbors |
Authors: | Bagaskara, Adyatma Andhika |
Keywords: | Banjir;K-NN;QGIS;Pemetaan;10-fold cross-validation;Mapping |
Issue Date: | 6-Nov-2023 |
Abstract: | Banjir terjadi ketika volume air melebihi kapasitas penampungan atau aliran normal saluran air, seperti sungai, danau, kanal, atau sistem drainase. Pada tahun 2021 dan 2022, terjadi 88 bencana banjir di Semarang. Faktor-faktor yang memengaruhi terjadinya bencana banjir termasuk curah hujan, kemiringan lahan, dan indeks tutupan vegetasi (NDVI). Tujuan utama penelitian ini adalah untuk mengidentifikasi dan mengklasifikasi daerah-daerah di Semarang yang rentan terhadap banjir dengan memetapkannya berdasarkan curah hujan, indeks vegetasi, dan kemiringan lahan. Status yang diklasifikasikan adalah daerah rawan banjir dan daerah tidak rawan banjir. Evaluasi spasial daerah rawan banjir berdasarkan GIS dilakukan dengan menggunakan algoritma klasifikasi K-Nearest Neighbor (K-NN) dengan bahasa pemrograman R untuk mencapai tujuan ini. Pengujian k optimal menggunakan metode 10-Fold Cross Validation mengungkapkan bahwa akurasi tertinggi sistem tercapai dengan metode K-NN pada k=7, mencapai 86%. Temuan dari penelitian ini menunjukkan bahwa delapan kecamatan di Semarang rentan terhadap banjir, sedangkan 167 daerah di Semarang tidak menunjukkan kerentanan terhadap banjir. Potensi daerah rawan banjir direpresentasikan dengan pembuatan peta kerawanan banjir Semarang menggunakan perangkat lunak Quantum GIS. Floods occur when the volume of water exceeds the capacity of containment or the normal flow of water channels, such as rivers, lakes, canals, or drainage systems. In 2021 and 2022, there were 88 flood disasters in Semarang. Factors influencing the occurrence of flood disasters include rainfall, land slope, and the vegetation cover index (NDVI). The main objective of this research is to identify and classify areas in Semarang that are susceptible to flooding by mapping them based on rainfall, vegetation index, and land slope. The classified statuses are flood-prone areas and non-flood-prone areas. A spatial assessment of areas prone to flooding based on GIS is performed using the K-Nearest Neighbor (K-NN) classification algorithm with the R programming language to accomplish this objective. Optimal k testing using the 10-fold cross-validation method reveals that the highest accuracy of the system is achieved with the K-NN method at k=7, reaching 86%. The findings from this study suggest that eight sub-district areas within Semarang are susceptible to flooding, whereas 167 areas in Semarang do not exhibit susceptibility to floods. The potential areas prone to flooding are represented by making a Semarang flood susceptibility map using Quantum GIS software. |
URI: | https://repository.uksw.edu//handle/123456789/32366 |
Appears in Collections: | T1 - Information Systems |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
T1_682019079_Judul.pdf | 899.85 kB | Adobe PDF | View/Open | |
T1_682019079_Isi.pdf Until 9999-01-01 | 1.28 MB | Adobe PDF | View/Open | |
T1_682019079_Daftar Pustaka.pdf | 868.17 kB | Adobe PDF | View/Open | |
T1_682019079_ Formulir Pernyataan Persetujuan Penyerahan Lisensi Tugas Akhir dan Pilihan Embargo.pdf Restricted Access | 910.4 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.