RAMADHAN, MUHAMMAD KHARISMA (2026) PERBANDINGAN ALGORITMA RANDOM FOREST DAN DECISION TREE UNTUK PREDIKSI CURAH HUJAN DAN BANJIR DI JAKARTA PUSAT. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
Cover.pdf Download (527kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
Bab1.pdf Restricted to Registered users only Download (41kB) |
|
|
Text (BAB II)
Bab2.pdf Restricted to Registered users only Download (229kB) |
|
|
Text (BAB III)
Bab3.pdf Restricted to Registered users only Download (144kB) |
|
|
Text (BAB IV)
Bab4.pdf Restricted to Registered users only Download (662kB) |
|
|
Text (BAB V)
Bab5.pdf Restricted to Registered users only Download (31kB) |
|
|
Text (DAFTAR PUSTAKA)
Daftar Pustaka.pdf Restricted to Registered users only Download (153kB) |
|
|
Text (LAMPIRAN)
lampiran.pdf Restricted to Registered users only Download (866kB) |
Abstract
Rainfall is one of the main factors influencing the occurrence of flooding in urban areas, particularly in Jakarta. To support flood mitigation efforts, a Machine learning–based approach is required to enable rainfall prediction and early classification of flood potential. This study aims to discuss the application and comparison of Decision Tree and Random Forest algorithms in predicting daily rainfall and classifying flood and non-flood conditions. The dataset used consists of daily climate data from Central Jakarta and for the period 2018 - 2025. The research methodology includes data preprocessing, time-based Feature engineering, utilization of historical data through lag features and rolling windows, construction of flood labels based on rainfall threshold values, and modeling using a time series approach. The evaluation process is conducted to assess the models’ ability to learn rainfall patterns and flood occurrences. This study is expected to contribute to the application of Machine learning in climate data analysis and to serve as a reference for the development of flood prediction systems based on historical data. Keywords: rainfall, flood, Machine learning, Random Forest, Decision Tree. Curah hujan merupakan salah satu faktor utama yang memengaruhi terjadinya banjir di wilayah perkotaan, khususnya di Jakarta Pusat. Untuk mendukung upaya mitigasi banjir, diperlukan pendekatan berbasis Machine learning yang mampu melakukan prediksi curah hujan serta klasifikasi potensi banjir secara dini. Penelitian ini bertujuan untuk membahas penerapan dan perbandingan algoritma Decision Tree dan Random Forest dalam memprediksi curah hujan harian serta mengklasifikasikan kondisi banjir dan tidak banjir. Data yang digunakan berupa data iklim harian wilayah Jakarta Pusat periode 2018–2025. Metodologi penelitian mencakup tahapan data preprocessing, Feature engineering berbasis waktu, pemanfaatan data historis melalui fitur lag dan rolling window, pembentukan label banjir berdasarkan ambang batas curah hujan, serta pemodelan menggunakan pendekatan time series. Proses evaluasi dilakukan untuk menilai kemampuan model dalam mempelajari pola curah hujan dan kejadian banjir. Penelitian ini diharapkan dapat memberikan kontribusi dalam penerapan Machine learning pada analisis data iklim serta menjadi referensi dalam pengembangan sistem prediksi banjir berbasis data historis. Kata kunci: Curah hujan, Banjir, Machine learning, Random Forest, Decision Tree.
Actions (login required)
 |
View Item |
