Prediction of Rice Harvest Yields Using the ARIMA Algorithm at the Agricultural Extension Center

Authors

  • Safwandi Safwandi Universitas Malikussaleh
  • Mukti Qamal Universitas Malikussaleh
  • Raziatul Khaira Universitas Malikussaleh

DOI:

https://doi.org/10.30871/jaic.v10i2.12220

Keywords:

ARIMA, Prediction, Rice Yield, ADF test, MAPE

Abstract

Rice production plays a crucial role in supporting regional food security; therefore, accurate forecasting is essential for effective agricultural planning. This study aims to forecast rice yields in Meurah Mulia District using a univariate Autoregressive Integrated Moving Average (ARIMA) model based on annual data from 2015 to 2024 obtained from the Agricultural Extension Agency. The modeling process includes stationarity testing using the Augmented Dickey–Fuller (ADF) test, model selection using Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC), and residual diagnostics using the Ljung–Box test. The selected ARIMA model generates one-step-ahead forecasts for 2025 across 48 villages, with predicted yields ranging from 130.19 tons (Pri Ketapang) to 671.83 tons (Ulee Meuria), reflecting heterogeneous production patterns among villages. Model accuracy is evaluated using the Mean Absolute Percentage Error (MAPE), with values below 2% across all villages,indicating satisfactory in-sample forecasting performance. However, this study applies a univariate ARIMA approach; therefore, external variables are not incorporated. The findings provide preliminary insights to support agricultural planning, while further research is recommended to enhance model robustness and generalizability.

Downloads

Download data is not yet available.

References

[1] Tasna Yunita, “Peramalan Jumlah Penggunaan Kuota Internet Menggunakan Metode Autoregressive Integrated Moving Average (ARIMA),” J. Math. Theory Appl., vol. 1, no. 2, pp. 16–22, 2020, doi: 10.31605/jomta.v2i1.777.

[2] W. Fuadi, F. Fajriana, and R. M, “Peramalan Hasil Panen Padi Dengan Menggunakan Metode Double Exponential Smoothing Di Kecamatan Meurah Mulia,” TECHSI - J. Tek. Inform., vol. 13, no. 1, p. 26, 2021, doi: 10.29103/techsi.v13i1.2772.

[3] M. Qamal, “Peramalan Penjualan Makanan Ringan Dengan Metode Single Exponential Smoothing,” J. Penelit. Tek. Inform., vol. 8, no. 2, pp. 25–35, 2019.

[4] A. I. La Murdani and Y. W. A. Nanlohy, “Implementasi Model Autoregressive Integrated Moving Average (Arima) Untuk Peramalan Jumlah Penumpang Kapal Laut Di Pelabuhan Ambon,” Var. J. Stat. Its Appl., vol. 3, no. 2, pp. 81–90, 2022, doi: 10.30598/variancevol3iss2page81-90.

[5] S. Safwandi, “Analisis Perancangan Sistem Informasi Sekolah Menengah Kejuruan 1 Gandapura Dengan Model Diagram Konteks Dan Data Flow Diagram,” J. Teknol. Terap. Sains 4.0, vol. 2, no. 2, p. 525, 2021, doi: 10.29103/tts.v2i2.4724.

[6] D. Benvenuto, M. Giovanetti, L. Vassallo, S. Angeletti, and M. Ciccozzi, “Data in brief Application of the ARIMA model on the COVID- 2019 epidemic dataset,” Data Br., vol. 29, p. 105340, 2020, doi: 10.1016/j.dib.2020.105340.

[7] Y. F. Wijaya and A. Triayudi, “Penerapan Data Mining Pada Prediksi Harga Emas dengan Menggunakan Algoritma Regresi Linear Berganda dan ARIMA,” J. Comput. Syst. Informatics, vol. 5, no. 1, pp. 73–81, 2023, doi: 10.47065/josyc.v5i1.4615.

[8] R. H. Br Bangun, “Penerapan Autoregressive Integrated Moving Average (Arima) Pada Peramalan Produksi Kedelai Di Sumatera Utara,” J. Agrica, vol. 9, no. 2, p. 90, 2017, doi: 10.31289/agrica.v9i2.484.

[9] M. Terbaik, A. Integrated, and M. Average, “The Best Model of the Autoregressive Integrated Moving Average ( ARIMA ) Method for Predicting the Exchange Rate of the Indonesian Rupiah Against the US Dollar ( USD ) for the Period July 2025 - June 2026,” vol. 22, no. 2, pp. 427–435, 2026, doi: 10.20956/j.v22i2.48098.

[10] Y. Dong, S. Li, and X. Gong, “Time Series Analysis: An application of ARIMA model in stock price forecasting,” vol. 29, no. Iemss, pp. 703–710, 2017, doi: 10.2991/iemss-17.2017.140.

[11] Christina Purnama Yanti, Ni Komang Ita Cahyani, Theresia Hendrawati, Yuri Prima Fittryani, and Dewa Ayu Kadek Pramita, “Prediksi Harga Material Bangunan Dengan Autoregressive Integrated Moving Average (Arima) Pada CV. TJA,” Tematik, vol. 11, no. 1, pp. 47–55, 2024, doi: 10.38204/tematik.v11i1.1914.

[12] R. F. Syahrir, “Metode Autoregressive Integrated Moving Average (Arima),” Academia.edu, pp. 1275–1289, 2027.

[13] M. A. Hamjah, “Rice Production Forecasting in Bangladesh : An Application Of Box-Jenkins ARIMA Model,” vol. 4, no. 4, pp. 1–11, 2014.

[14] V. D. Sari and B. M. Sukojo, “Analisa Estimasi Produksi Padi Berdasarkan Fase Tumbuh Dan Model Peramalan Autoregressive Integrated Moving Average (Arima) Menggunakan Citra Satelit Landsat 8 (Studi Kasus: Kabupaten Bojonegoro),” Geoid, vol. 10, no. 2, p. 194, 2015, doi: 10.12962/j24423998.v10i2.828.

[15] Z. M. E. Atlam, A. Ewis, G. Dagnew, and A. Reda, “ARIMA models for predicting the end of COVID-19 pandemic and the risk of second rebound,” Neural Comput. Appl., vol. 33, no. 7, pp. 2929–2948, 2021, doi: 10.1007/s00521-020-05434-0.

[16] H. Waryanto and D. A. Wanti, “Prediksi Penjualan Seragam Sekolah Dengan Menggunakan Metode Arima,” J. Stat. dan Mat., vol. 1, no. 1, pp. 88–102, 2019.

[17] Z. Munirah, I. B. K. Widiartha, and S. I. Murpratiwi, “Sistem Peramalan Kelahiran, Kematian dan Kemiskinan berbasis Website dengan Metode Arima,” Edumatic J. Pendidik. Inform., vol. 9, no. 1, pp. 1–10, 2024, doi: 10.29408/edumatic.v9i1.28423.

[18] A. D. Milniadi and N. O. Adiwijaya, “Analisis Perbandingan Model Arima Dan Lstm Dalam Peramalan Harga Penutupan Saham ( Studi Kasus : 6 KRITERIA,” Sibatik J., vol. 2, no. 6, pp. 1683–1692, 2023.

Downloads

Published

2026-04-21

How to Cite

[1]
S. Safwandi, M. Qamal, and R. Khaira, “Prediction of Rice Harvest Yields Using the ARIMA Algorithm at the Agricultural Extension Center”, JAIC, vol. 10, no. 2, pp. 1683–1693, Apr. 2026.

Similar Articles

<< < 22 23 24 25 > >> 

You may also start an advanced similarity search for this article.