IPB University Logo

SCIENTIFIC REPOSITORY

IPB University Scientific Repository collects, disseminates, and provides persistent and reliable access to the research and scholarship of faculty, staff, and students at IPB University

AI Repository
 
Building and Categories


      View Item 
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - School of Data Science, Mathematic and Informatics
      • UF - Mathematics
      • View Item
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - School of Data Science, Mathematic and Informatics
      • UF - Mathematics
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Prediksi Curah Hujan di DKI Jakarta menggunakan Metode Long Short-Term Memory dan Analisis Hubungannya terhadap Banjir

      Thumbnail
      View/Open
      Cover (458.5Kb)
      Fulltext (2.724Mb)
      Lampiran (260.3Kb)
      Date
      2026
      Jenis/Type
      Skripsi
      Subtype
      Undergraduate Theses
      Author
      Giana, Andriani Dwiandra
      Najib, Mohamad Khoirun
      Nurdiati, Sri
      Metadata
      Show full item record
      Abstract
      Curah hujan di Indonesia, terkhususnya wilayah DKI Jakarta, sangat tinggi sehingga berpotensi memicu banjir. Oleh karena itu, upaya mitigasi yang efektif memerlukan sistem prediksi yang akurat. Penelitian ini bertujuan membangun model prediksi akumulasi curah hujan bulanan dan probabilitas kejadian banjir. Data historis akumulasi curah hujan periode Januari 2015 sampai Desember 2024, beserta variabel rata-rata suhu, kecepatan angin, dan kelembapan udara, diproses menggunakan metode Long Short-Term Memory (LSTM). Selanjutnya, digunakan metode Regresi Logistik untuk mengklasifikasi probabilitas terjadinya banjir. Hasil evaluasi model LSTM menunjukkan arsitektur yang stabil tanpa overfitting yang dibuktikan dengan nilai Root Mean Square Error pada data training (63.905), validation (64.175), dan testing (64.095). Hasil analisis Spearman antara curah hujan dan banjir menunjukkan adanya korelasi, akan tetapi hasil Regresi Logistik mengindikasikan bahwa curah hujan sebagai variabel tunggal belum cukup untuk menangkap probabilitas banjir aktual. Penelitian ini untuk selanjutnya disarankan untuk menambahkan variabel lingkungannya seperti drainase dan banjir kiriman di masing-masing wilayah untuk meningkatkan presisi prediksi banjir.
       
      Rainfall in Indonesia, especially in DKI Jakarta, is very high, which can potentially trigger flooding. Therefore, effective mitigation efforts require an accurate prediction system. This study aims to build a monthly rainfall accumulation prediction model and the probability of flooding. Historical rainfall accumulation data for the period from January 2015 to December 2024, along with the average of temperature, wind speed, and humidity variables, are processed using Long Short-Term Memory (LSTM) method. Furthermore, the Logistic Regression method is used to classify the probability of flooding. The results of LSTM model evaluation show a stable architecture without overfitting, as proven by Root Mean Square Error for training data (63.905), validation data (64.175), and testing data (64.095). The result of Spearman correlation analysis between rainfall and flooding indicates a correlation, however, the results of Logistic Regression indicate that precipitation as a single variable is not sufficient to capture the actual flood probability. This research further recommends integrating variables such as drainage and incoming flood for each region.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/175589
      Collections
      • UF - Mathematics [164]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository