View Item 
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - School of Data Science, Mathematic and Informatics
      • UT - Statistics and Data Sciences
      • View Item
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - School of Data Science, Mathematic and Informatics
      • UT - Statistics and Data Sciences
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Performa LSTM dan GRU dalam Peramalan Curah Hujan Harian di Kabupaten Gresik untuk Menentukan Waktu Tanam Padi yang Tepat

      Thumbnail
      View/Open
      Cover (452.6Kb)
      Fulltext (1.018Mb)
      Date
      2025
      Author
      Taqiah, Butsainah
      Masjkur, Mohammad
      Dito, Gerry Alfa
      Metadata
      Show full item record
      Abstract
      Padi merupakan komoditas utama penunjang ketahanan pangan di Indonesia. Penurunan produksi padi, khususnya di Kabupaten Gresik, dipengaruhi oleh perubahan pola curah hujan yang tidak menentu. Penelitian ini bertujuan untuk membandingkan performa model Long Short-Term Memory (LSTM) dan Gated Recurrent Unit (GRU) dengan strategi Multiple Input Multiple Output (MIMO) dalam peramalan curah hujan harian selama 365 hari ke depan, serta menentukan waktu tanam padi yang optimal. Data curah hujan harian selama 3653 hari diperoleh dari situs web NASA POWER. Proses pemodelan dilakukan dengan lag 365 hari dan lead 365 hari. Hasil penelitian menunjukkan bahwa LSTM dengan kombinasi hyperparameter 100 neurons di hidden layer, fungsi aktivasi softplus, optimizer Adam, dan 200 epoch menghasilkan performa terbaik dengan Root Mean Square Error (RMSE) sebesar 15,15; Mean Absolute Scaled Error (MASE) sebesar 1,48 dan Mean Absolute Error (MAE) sebesar 7,66. Sementara itu, GRU menghasilkan RMSE sebesar 27,54; MASE sebesar 4,15 dan MAE sebesar 8,51. Berdasarkan hasil peramalan, waktu tanam padi yang optimal di Kabupaten Gresik diperkirakan dimulai pada 1 Mei 2025
       
      Rice is the main commodity that plays an important role in supporting food security in Indonesia. The decline in rice production, particularly in Gresik Regency, is influenced by increasingly unpredictable rainfall patterns. This study aims to compare the performance of Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models using the Multiple Input Multiple Output (MIMO) strategy for forecasting daily rainfall over the next 365 days, as well as to determine the optimal rice planting time. A total of 3653 days of daily rainfall data were obtained from the NASA POWER website. The modeling process was conducted using a lag of 365 days and a lead of 365 days. The results show that the LSTM model, with a combination of 100 neurons in the hidden layer, the softplus activation function, Adam optimizer, and 200 epochs, achieved the best performance with a Root Mean Square Error (RMSE) of 15.15, Mean Absolute Scaled Error (MASE) of 1.48 and Mean Absolute Error (MAE) of 7.66. In comparison, the GRU model resulted in an RMSE of 27.54, MASE of 4.15 and MAE of 8.51. Based on the forecasting results, the optimal rice planting time in Gresik Regency is estimated to begin on May 1, 2025.;
       
      URI
      http://repository.ipb.ac.id/handle/123456789/169121
      Collections
      • UT - Statistics and Data Sciences [82]

      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