<?xml version="1.0" encoding="UTF-8" ?>
<modsCollection xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://www.loc.gov/mods/v3" xmlns:slims="http://slims.web.id" xsi:schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-3.xsd">
<mods version="3.3" ID="20437">
<titleInfo>
<title><![CDATA[PEMETAAN KERENTANAN TANAH LONGSOR DI KABUPATEN BANDUNG BARAT MENGGUNAKAN ALGORITMA RANDOM FOREST DAN SUPPORT VECTOR MACHINE BERBASIS GOOGLE EARTH ENGINE]]></title>
</titleInfo>
<name type="Personal Name" authority="">
<namePart>0407096502 - Dr. Dewi Kania Sari, Ir., M.T.</namePart>
<role><roleTerm type="text">Dosen Pembimbing 1</roleTerm></role>
</name>
<name type="Personal Name" authority="">
<namePart>GHIAST AZRU MAULIDAN SUTIA RAHAYU / 232021034</namePart>
<role><roleTerm type="text">Penulis</roleTerm></role>
</name>
<typeOfResource manuscript="yes" collection="yes"><![CDATA[mixed material]]></typeOfResource>
<genre authority="marcgt"><![CDATA[bibliography]]></genre>
<originInfo>
<place><placeTerm type="text"><![CDATA[Teknik Geodesi]]></placeTerm></place>
<publisher><![CDATA[FTSP]]></publisher>
<dateIssued><![CDATA[]]></dateIssued>
<issuance><![CDATA[monographic]]></issuance>
<edition><![CDATA[0]]></edition>
</originInfo>
<language>
<languageTerm type="code"><![CDATA[en]]></languageTerm>
<languageTerm type="text"><![CDATA[English]]></languageTerm>
</language>
<physicalDescription>
<form authority="gmd"><![CDATA[Text]]></form>
<extent><![CDATA[]]></extent>
</physicalDescription>
<note>Tanah longsor merupakan salah satu bencana geologi yang sering terjadi di
Kabupaten Bandung Barat dan berdampak pada kerusakan lingkungan serta
kerugian ekonomi. Penelitian ini bertujuan untuk memetakan kerentanan tanah
longsor menggunakan algoritma Random Forest (RF) dan Support Vector Machine
(SVM) berbasis Google Earth Engine (GEE). Parameter yang digunakan meliputi
kemiringan lereng, curah hujan, NDVI, jenis tanah, jenis batuan, dan tutupan lahan.
Data diolah di GEE dengan pembagian data pelatihan dan pengujian sebesar 80:20.
Evaluasi model dilakukan menggunakan confusion matrix dan validasi spasial
berdasarkan data longsor tahun 2024. Model RF mengklasifikasikan 28,40%
wilayah sebagai kerentanan rendah dan 9,88% sebagai sangat tinggi, dengan
akurasi 80%, sedangkan SVM memperoleh akurasi 76,24%. Analisis feature
importance menunjukkan bahwa kemiringan lereng dan curah hujan merupakan
faktor paling dominan. Hasil penelitian menunjukkan bahwa Random Forest
memberikan performa dan akurasi yang lebih baik dibandingkan SVM. Peta
kerentanan yang dihasilkan dapat digunakan sebagai dasar dalam perencanaan tata
ruang dan upaya mitigasi bencana tanah longsor.

Landslides are one of the major geological disasters in West Bandung Regency,
often resulting in environmental damage and economic losses. This study aims to
map landslide vulnerability using the Random Forest (RF) and Support Vector
Machine (SVM) algorithms through the Google Earth Engine (GEE) platform. Key
parameters used include slope, rainfall, NDVI, soil type, lithology, and land use.
These were processed in GEE to train RF and SVM models, using 80% of the data
for training and 20% for testing. Model performance was evaluated using a
confusion matrix and validated with landslide data from 2024. The RF model
classified 28.40% of the area as low vulnerability and 9.88% as very high. It
achieved 80% accuracy, while the SVM model reached 76.66%. Feature
importance analysis revealed that slope and rainfall were the most influential
factors. The results indicate that the Random Forest algorithm outperforms the
Support Vector Machine in both accuracy and spatial prediction. The resulting
vulnerability maps are expected to support local governments and communities in
spatial planning and landslide risk mitigation efforts.</note>
<subject authority=""><topic><![CDATA[Support Vector Machine, Google Earth Engine]]></topic></subject>
<subject authority=""><topic><![CDATA[tanah longsor, Random Forest]]></topic></subject>
<subject authority=""><topic><![CDATA[Machine learning]]></topic></subject>
<classification><![CDATA[]]></classification><identifier type="isbn"><![CDATA[20250909]]></identifier><location>
<physicalLocation><![CDATA[Setiadi Open Source ETD System]]></physicalLocation>
<shelfLocator><![CDATA[1128GD/25]]></shelfLocator>
<holdingSimple>
<copyInformation>
<numerationAndChronology type="1"><![CDATA[1128GD/25]]></numerationAndChronology>
<sublocation><![CDATA[]]></sublocation>
<shelfLocator><![CDATA[1128GD/25]]></shelfLocator>
</copyInformation>
</holdingSimple>
</location>
<slims:digitals>
<slims:digital_item id="22453" url="" path="/232021034_1128GD.pdf" mimetype="application/pdf"><![CDATA[PEMETAAN KERENTANAN TANAH LONGSOR DI KABUPATEN BANDUNG BARAT MENGGUNAKAN ALGORITMA RANDOM FOREST DAN SUPPORT VECTOR MACHINE BERBASIS GOOGLE EARTH ENGINE]]></slims:digital_item>
</slims:digitals><recordInfo>
<recordIdentifier><![CDATA[20437]]></recordIdentifier>
<recordCreationDate encoding="w3cdtf"><![CDATA[2025-11-11 15:23:50]]></recordCreationDate>
<recordChangeDate encoding="w3cdtf"><![CDATA[2025-11-11 15:24:46]]></recordChangeDate>
<recordOrigin><![CDATA[machine generated]]></recordOrigin>
</recordInfo></mods></modsCollection>