Peramalan Produksi Padi Di Provinsi Sumatera Barat dengan Metode LSTM

Dwiki Yanata -
Helma Helma -

Abstract


The occurrence of rice surplus in West Sumatra Province, makes this province has the potential to become a rice exporting area without reducing local stocks. This research aims to forecast rice production using the LSTM method, which excels in time series data analysis. This research uses secondary data in the form of monthly rice production in West Sumatra from 2009 to 2023 obtained from the Agriculture Office of West Sumatra Province. The process involves data processing, division of the dataset into training and testing data, and construction of the LSTM model. The model is designed to recognize patterns and trends in rice paddy production. The forecasting results show a range of paddy production between 177,038 to 185,343 tons with a MAPE value of 10%, which indicates a good level of accuracy.


Full Text:

PDF

References


Badan Pusat Statistik, “Luas Panen dan Produksi Padi di Provinsi Sumatera Barat 2018-2023,” https://sumbar.bps.go.id. [Online].

“Tempo,” 23 Juni 2020. [Online]. Available: https://www.tempo.co/. [Diakses Agustus 2024].

S. Makridakis, S. Wheelwright dan V. dan McGee, Metode dan Aplikasi Peramalan Jilid 2, Jakarta: Erlangga, 1999.

I. G. S. Negara, P. Sugiartawan dan S. I. Murpratiwi, “Prediksi Sebaran Hama Padi Dengan Metode LSTM Pada Pertanian Padi di Buleleng,” Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI), pp. 43-52, 2022.

M. Aldi, “Analisis dan Implementasi Long Short Term Memory Neural Network untuk Prediksi Harga Bitcoin,” eProceeding of Engineering, p. 3548–3555, 2018.

P. A. Riyantoko, “Analisis Prediksi Harga Saham Sektor Perbankan Menggunakan Algoritma Long-Short Terms Memory (Lstm),” Seminar Nasional Informatika, pp. 427-435, 2020.

C. Olah, “Understanding LSTM Networks,” 27 Agustus 2015. [Online].

V. Krakovna dan F. Doshi-Velez, “Increasing the interpretability of recurrent neural networks using hidden markov models,” arXiv preprint arXiv:1606.05320, 2016.

Akhmad Faeda Insani, “Optimasi Kombinasi Variabel untuk Prediksi Konsumsi Listrik Rumah Tangga dengan Pendekatan Machine Learning Multivariate Time Serieskompleks,” Jurnal Inovtek Polbeng - Seri Informatika, vol. 10, 2024.

C. Meliana, “Perbandingan Metode Long Short Term Memory (LSTM) DAN Genetic Algorithm-Long Short Term Memory (GA-LSTM) Pada Peramalan Polutan Udara,” 2021.

L. Deng dan D. Yu, “Deep Learning: Methods and Applications,” Foundations and Trends in Signal Processing, pp. 197-387, 2013.

M. F. Ramadhan, D. Lestari dan U. Khaira, “Prediksi Harga Bitcoin Menggunakan Metode Long Short Term Memory,” Jurnal Pepadun, pp. 104-112, 2024.

N. Selle, “Perbandingan Prediksi Penggunaan Listrik Dengan Menggunakan Metode Long Short Term Memory (LSTM) Dan Recurrent Neural Network (RNN),” Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK), pp. 155-162, 2022.

P. Jason Brownlee, “Difference Between a Batch and an Epoch in a Neural Network,” 15 Agustus 2022. [Online].

P. N. Yulisa, M. A. Haris dan P. R. Arum, “Peramalan Nilai Ekspor Migas di Indonesia dengan Model Long Short Term Memory(LSTM)dan Gated Recurrent Unit(GRU),” jurnal.unipasby.ac.id, pp. 328-341, 2023.




DOI: http://dx.doi.org/10.24036/unpjomath.v10i1.16977