Prediksi Curah Hujan Memanfaatkan Statistical Downscaling Data Global Forecast System Menggunakan Support Vector Regression dan Long Short-Term Memory Sebagai Penunjang Keputusan Top Management

Rohman, Priya Setiawan A. (2024) Prediksi Curah Hujan Memanfaatkan Statistical Downscaling Data Global Forecast System Menggunakan Support Vector Regression dan Long Short-Term Memory Sebagai Penunjang Keputusan Top Management. Masters thesis, Institut Teknologi Sepuluh Nopember.

Text 6032231054-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2027. Download (9MB) | Request a copy

Abstract

Wilayah Sungai (WS) Brantas sering mengalami kejadian banjir akibat dari curah hujan yang tinggi, sehingga diperlukan prediksi cuaca yang akurat untuk mendukung keputusan manajemen dalam mitigasi banjir. Data Global Forecast System (GFS) digunakan dalam memprediksi cuaca khususnya prediksi curah hujan, namun resolusinya yang rendah tidak cukup memadai untuk skala lokal di WS Brantas. Masalah yang dihadapi adalah bagaimana cara untuk meningkatkan ketepatan prediksi curah hujan dengan mengintegrasikan data GFS yang memiliki resolusi rendah dengan data curah hujan lokal. Penelitian ini bertujuan untuk meningkatkan akurasi prediksi curah hujan di WS Brantas dengan teknik Statistical downscaling menggunakan metode Support Vector Regression (SVR) yang baik dalam menangani data non-linear dan Long Short-Term Memory (LSTM), sebuah jenis jaringan saraf tiruan yang dapat menangkap hubungan temporal dalam data deret waktu. Data yang diperlukan adalah prediksi curah hujan dari GFS dan data curah hujan lokal hasil pengukuran di WS Brantas. Hasil penelitian menunjukkan bahwa tingkat akurasi prediksi dengan SVR dan LSTM lebih tinggi daripada akurasi data prediksi GFS, sehingga dapat diusulkan untuk diimplementasikan sebagai data penunjang top management.
==================================================================================================================================
The Brantas River Basin (Brantas RB) often experiences flooding events due to high rainfall, so accurate weather predictions are needed to support management decisions in flood mitigation. Global Forecast System (GFS) data is used in predicting weather, especially rainfall prediction, but its low resolution is not sufficient for the local scale in the Brantas RB. The problem faced is how to improve the accuracy of rainfall prediction by integrating low-resolution GFS data with local rainfall data. This study aims to improve the accuracy of rainfall prediction in Brantas RB with statistical downscaling technique using Support Vector Regression (SVR) method which is good in handling non-linear data and Long Short-Term Memory (LSTM), a type of artificial neural network that can capture temporal relationships in time series data. The data required are rainfall predictions from GFS and local rainfall data measured in Brantas RB. The results show that the accuracy of prediction with SVR and LSTM is higher than the accuracy of GFS prediction data, so it can be proposed to be implemented as top management support data.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	GFS, LSTM, Prediksi Curah Hujan, Rainfall Prediction, Statistical Downscaling, SVR
Subjects:	Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry) Q Science > QA Mathematics > QA336 Artificial Intelligence Q Science > QA Mathematics > QA76.6 Computer programming. Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) Q Science > QA Mathematics > QA9.58 Algorithms Q Science > QC Physics > QC866.5 Climatology--Forecasting. Q Science > QC Physics > QC925 Rain and rainfall T Technology > T Technology (General) > T174 Technological forecasting T Technology > T Technology (General) > T57.5 Data Processing T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models. T Technology > T Technology (General) > T58.62 Decision support systems T Technology > TC Hydraulic engineering. Ocean engineering > TC167 Dams, reservoirs T Technology > TC Hydraulic engineering. Ocean engineering > TC530 Flood control
Divisions:	Interdisciplinary School of Management and Technology (SIMT) > 61101-Master of Technology Management (MMT)
Depositing User:	Priya Setiawan A. Rohman
Date Deposited:	14 Jan 2025 04:26
Last Modified:	14 Jan 2025 04:26
URI:	http://repository.its.ac.id/id/eprint/116288

Actions (login required)

View Item