RAHASIA, BRILLYA FIENTJE BELLA (2023) IMPLEMENTASI ALGORITMA K-MEANS UNTUK CLUSTERING DAERAH RAWAN BANJIR DI DKI JAKARTA. S1 thesis, Universitas Mercu Buana.
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (COVER)
01 COVER.pdf Download (370kB) |
|
Text (ABSTRAK)
02 ABSTRAK.pdf Download (33kB) |
|
Text (BAB I)
03 BAB 1.pdf Restricted to Registered users only Download (119kB) |
|
Text (BAB II)
04 BAB 2.pdf Restricted to Registered users only Download (142kB) |
|
Text (BAB III)
05 BAB 3.pdf Restricted to Registered users only Download (50kB) |
|
Text (BAB IV)
06 BAB 4.pdf Restricted to Registered users only Download (294kB) |
|
Text (BAB V)
07 BAB 5.pdf Restricted to Registered users only Download (52kB) |
|
Text (DAFTAR PUSTAKA)
08 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (92kB) |
|
Text (LAMPIRAN)
09 LAMPIRAN.pdf Restricted to Registered users only Download (1MB) |
Abstract
Indonesia is a disaster-prone area in Southeast Asia. This refers to geological, demographic and geographical conditions that trigger the possibility of a disaster, both due to natural factors such as landslides, earthquakes, tsunamis, volcanic eruptions, floods, tsunamis and non-natural factors. One of the areas in Indonesia which is a disaster-prone area, especially floods, is Jakarta. From a geographical point of view, the area which is in the lowlands and between the headwaters and the coast makes DKI Jakarta has a large potential for flooding. Based on the results of CNN alerts, in 2020 the water that has stagnated DKI Jakarta can reach a height of 350 cm. To minimize the big impact of flooding, this research will carry out clustering using the K-Means algorithm for flood-prone areas in DKI Jakarta in the value of water_height and inundation_length by dividing 3 clusters. The final results of this study will determine the incidence of flooding with the lowest cluster to the highest. A silhouette score of 0.60 was obtained based on grouping using the K-Means algorithm with the results of Cluster 0 (flood with a low level of vulnerability) there were 1207 cluster members, Cluster 1 (flood with a moderate level of vulnerability) there were 705 cluster members, and Cluster 2 (flood with a high level of vulnerability) there are 178 cluster members. Keywords: Flood, K-means Algorithm, Clustering, Elbow Method Indonesia menjadi kawasan rawan bencana di Asia Tenggara. Hal ini mengacu pada kondisi geologis, demografis, dan geografis yang memicu kemungkinan bencana, baik karena faktor alam seperti tanah longsor, gempa bumi, tsunami, letusan gunung berapi, banjir, tsunami dan faktor non alam. Salah satu daerah di Indonesia yang merupakan daerah rawan bencana khusunya bencana banjir yaitu Jakarta. Dilihat dari segi geografis, dengan daerah yang berada di dataran rendah serta di antara hulu sungai dan pesisi menjadikan DKI Jakarta memiliki potensi banjir yang besar. Berdasarkan hasil lansiran CNN pada tahun 2020 air yang menggenang DKI Jakarta bisa mencapai ketiggian 350 cm. Untuk meminimalisir dampak besar dari banjir, maka penelitian kali ini akan melakukan clustering menggunakan algoritma K-Means untuk daerah rawan banjir di DKI Jakarta di nilai dari Tinggi_air dan lama_genangan dengan membagi 3 cluster. Hasil akhir dari penelitian ini akan mengetahui pengujian Algoritma K-Means untuk kejadian banjir dengan cluster yang di bagi menjadi 3. Didapatkan nilai silhouette score sebesar 0.60 berdasarkan pengelompokkan dengan algoritma K-Means dengan hasil Cluster 0 (banjir dengan tingkat rawan yang rendah) terdapat 1207 anggota cluster, Cluster 1 (banjir dengan tingkat rawan yang sedang) terdapat 705 anggota cluster, dan Cluster 2 (banjir dengan tingkat rawan yang tinggi) terdapat 178 anggota cluster Kata Kunci : Banjir , Algoritma K-means , Clustering, Metode Elbow
Actions (login required)
 |
View Item |
