A Multivariate LSTM Approach for Monthly Rice Production Forecasting in East Java
Abstract
Accurate forecasting of rice output is essential for improving regional food security planning, particularly in East Java Province, which serves as a major national rice granary. This study develops a Long Short-Term Memory (LSTM) model to predict rice production using monthly data on production and harvested area from 2018 to 2024. The methodology includes data preprocessing, normalization, sequence construction with a sliding window, training of a multivariate LSTM model, and performance evaluation using mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE). Results show that the LSTM model achieves superior predictive accuracy, with an MAE of 95,030.16, RMSE of 120,229.01, and MAPE of 16.64%, significantly outperforming baseline Moving Average and Linear Regression models. While the model effectively captures seasonal production trends, some inaccuracies remain during periods of anomalous production values. These findings suggest that the LSTM model is effective for projecting rice production and may provide a foundation for early warning systems and regional food distribution strategies. Further improvements could be realized by integrating climate variables or adopting a hybrid model architecture to enhance predictive precision.
Downloads
References
T. Mariani and I. Rosyida, “Implementasi Metode Double Exponential Smoothing untuk Peramalan Luas Panen Padi di Kabupaten Pati dengan Bantuan Software Minitab 16,” PRISMA, Prosiding Seminar Nasional Matematika, vol. 6, pp. 707–713, 2023, [Online]. Available: https://journal.unnes.ac.id/sju/index.php/prisma/
R. A. Atmoko et al., “Indonesia Rice Yields Forecasting Using Agri-Graph Neural Network,” in 2025 9th International Conference on Man-Machine Systems (ICoMMS), IEEE, Aug. 2025, pp. 245–249. doi: https://doi.org/10.1109/ICoMMS66553.2025.11200184.
R. S. Mardiah, A. Suhendra, F. Fitrianingsih, and D. K. Putri, “Advancing Prediction of Rice Production in Sumatra: Utilizing eXtreme Gradient Boosting Algorithm for Accurate Forecasts,” in 2024 Ninth International Conference on Informatics and Computing (ICIC), IEEE, Oct. 2024, pp. 1–6. doi: https://doi.org/10.1109/ICIC64337.2024.10957232.
D. A. Prasetyo and R. Rokhim, “Indonesian Stock Price Prediction using Deep Learning during COVID-19 Financial Crisis,” International Journal of Business, Economics, and Social Development, vol. 3, no. 2, pp. 64–70, May 2022, doi: https://doi.org/10.46336/ijbesd.v3i2.273.
J. I. Q. Adiba, J. Slamet, A. M. Teguh, A. F. Septiyanto, and R. Sarno, “Advanced Deep Learning and Hybrid Models for Forecasting Rice Production in Indonesia,” in 2024 11th International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE), IEEE, Aug. 2024, pp. 302–307. doi: https://doi.org/10.1109/ICITACEE62763.2024.10762812.
J. Li, L. Zhou, and L. Song, “Multivariate Time Series Forecasting Based on Sliding Attention Correction LSTM Network,” in 2024 4th International Conference on Consumer Electronics and Computer Engineering (ICCECE), IEEE, Jan. 2024, pp. 204–208. doi: https://doi.org/10.1109/ICCECE61317.2024.10504235.
V. J. Halim, A. Ryanlie, K. Djong, K. E. Setiawan, and M. Fikri Hasani, “Rice Yield Production Forecasting using Deep Learning Models,” in 2023 International Conference on Networking, Electrical Engineering, Computer Science, and Technology (IConNECT), IEEE, Aug. 2023, pp. 54–59. doi: https://doi.org/10.1109/IConNECT56593.2023.10327193.
Y. Gao, C. A. Ellis, V. D. Calhoun, and R. L. Miller, “Improving Age Prediction: Utilizing LSTM-Based Dynamic Forecasting For Data Augmentation in Multivariate Time Series Analysis,” in 2024 IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI), IEEE, Mar. 2024, pp. 125–128. doi: https://doi.org/10.1109/SSIAI59505.2024.10508611.
A. R. Kesuma, M. Siringoringo, and S. Mahmuda, “Forecasting the Total of Paddy Production in Indonesia Using Time Series Regression Model,” ARRUS Journal of Mathematics and Applied Science, vol. 4, no. 2, pp. 78–88, Dec. 2024, doi: https://doi.org/10.35877/mathscience3175.
P. A. et al., “From Traditional to Advanced Models: A Comparative Study between Time Series and Machine Leaning Models in Agriculture,” J Sci Res Rep, vol. 30, no. 9, pp. 314–325, Aug. 2024, doi: https://doi.org/10.9734/jsrr/2024/v30i92356.
G. A. Rahardi, H. Mohammad Firdausi, W. Hadi, D. Setiabudi, and I. Wicaksono, “Application of ANFIS in Decision-Making on the Smart Control Early Warning System for Tornadoes,” Majalah Ilmiah Teknologi Elektro, vol. 23, no. 1, p. 49, Aug. 2024, doi: https://doi.org/10.24843/MITE.2024.v23i01.P06.
E. Yoshino, F. I. Kurniadi, and B. Juarto, “Forecasting Rice Production in Indonesia using Regression Techniques: A Comparative Analysis of Support Vector Machine, Linear Regression, and XGBoost Regression,” in 2023 10th International Conference on ICT for Smart Society (ICISS), IEEE, Sep. 2023, pp. 1–5. doi: https://doi.org/10.1109/ICISS59129.2023.10291271.
M. Silfiani, R. Herliansyah, and D. Nurlaily, “A Comparative Analysis of Hybrid Approach for Rice Production Forecasting,” in 2024 International Conference on Electrical and Information Technology (IEIT), IEEE, Sep. 2024, pp. 78–83. doi: https://doi.org/10.1109/IEIT64341.2024.10763092.
M. Silfiani, P. Hasanah, and I. Fitria, “Optimizing Rice Production Forecasts with Combined Time Series Models,” in 2024 International Conference on Electrical and Information Technology (IEIT), IEEE, Sep. 2024, pp. 54–59. doi: https://doi.org/10.1109/IEIT64341.2024.10763164.
D. Zhao and H. Ren, “Multivariate Time Series Forecasting Based on Fuzzy Information Granulation and LSTM,” in 2023 IEEE 11th International Conference on Information, Communication and Networks (ICICN), IEEE, Aug. 2023, pp. 189–193. doi: https://doi.org/10.1109/ICICN59530.2023.10393574.
N. Vintha and K. Devinder, “Comparative Analysis of Deep Learning Approaches for Analysis and Prediction of Multivariate Time Series Data,” in 2023 Congress in Computer Science, Computer Engineering, & Applied Computing (CSCE), IEEE, Jul. 2023, pp. 76–82. doi: https://doi.org/10.1109/CSCE60160.2023.00018.
Z. Z. Oo and W. L. L. Phyu, “Comparative Analysis of SARIMAX and LSTM Models for Fisheries and Multivariate Time Series Forecasting,” in 2025 6th International Conference on Advanced Information Technologies (ICAIT), IEEE, Nov. 2025, pp. 1–6. doi: https://doi.org/10.1109/ICAIT68809.2025.11236797.
Y. Ying and R. Zhao, “Research on Multivariate Dynamic Cost Standard Prediction Model Based on Random Forest and LSTM Combined with XGBoost,” in 2025 Asia-Europe Conference on Cybersecurity, Internet of Things and Soft Computing (CITSC), IEEE, Jan. 2025, pp. 686–690. doi: https://doi.org/10.1109/CITSC64390.2025.00128.
A. K. Salem and A. A. Abokifa, “A Multivariate LSTM Model for Short-Term Water Demand Forecasting,” in The 3rd International Joint Conference on Water Distribution Systems Analysis & Computing and Control for the Water Industry (WDSA/CCWI 2024), Basel Switzerland: MDPI, Sep. 2024, p. 167. doi: https://doi.org/10.3390/engproc2024069167.
Badan Pusat Statistik Provinsi Jawa Timur, “Luas Panen Padi Menurut Kabupaten/Kota - Tabel Statistik - Badan Pusat Statistik Provinsi Jawa Timur.” Accessed: Nov. 13, 2025. [Online]. Available: https://jatim.bps.go.id/id/statistics-table/2/NTc4IzI=/luas-panen-padi-menurut-kabupaten-kota--hektar-.html
Badan Pusat Statistik Provinsi Jawa Timur, “Produksi Padi Menurut Kabupaten/Kota - Tabel Statistik - Badan Pusat Statistik Provinsi Jawa Timur.” Accessed: Nov. 13, 2025. [Online]. Available: https://jatim.bps.go.id/id/statistics-table/2/NTc5IzI=/produksi-padi-menurut-kabupaten-kota.html
K. Lavanya and N. R. Prathik, “Deep Learning-Based Air Pollution Forecasting System Using Multivariate LSTM,” 2023, pp. 101–114. doi: https://doi.org/10.4018/978-1-6684-8516-3.ch006.
H. Jeong, J. Jeong, J. Chun, and H.-J. Kim, “Multivariate Time-series Data Correction by combining Attention-based LSTM and GAN Model,” in 2023 9th International Conference on Applied System Innovation (ICASI), IEEE, Apr. 2023, pp. 211–213. doi: https://doi.org/10.1109/ICASI57738.2023.10179548.
X. Zhou, A. Pranolo, and Y. Mao, “AB-LSTM: Attention Bidirectional Long Short-Term Memory for Multivariate Time-Series Forecasting,” in 2023 International Conference on Computer, Electronics & Electrical Engineering & their Applications (IC2E3), IEEE, Jun. 2023, pp. 1–6. doi: https://doi.org/10.1109/IC2E357697.2023.10262559.
F. Santosa, E. Oktafanda, H. Setiawan, and A. Latif, “Advanced Long Short-Term Memory (LSTM) Models for Forecasting Indonesian Stock Prices,” Jurnal Galaksi, vol. 1, no. 3, pp. 198–208, Dec. 2024, doi: https://doi.org/10.70103/galaksi.v1i3.42.
