Hasanur Mohammad Firdausi
KH Bahaudin Mudhary Madura University
Gamma Aditya Rahardi
University of Jember
Dani Hari Tunggal Prasetiyo
University of Jember
ABSTRAK
Produksi padi sangat penting untuk memastikan ketersediaan pangan yang cukup bagi masyarakat, terutama di daerah berkembang seperti Jawa Timur, Indonesia. Namun, tingkat produksi sangat bervariasi karena musim dan lingkungan, sehingga perkiraan yang akurat sangat penting untuk perencanaan dan pengambilan keputusan. Studi ini meneliti efektivitas model hibrida Particle Swarm Optimisation–Long Short-Term Memory (PSO–LSTM) untuk memprediksi produksi padi secara time-series. Metode yang disarankan menggunakan Particle Swarm Optimisation (PSO) untuk menemukan hyperparameter terbaik untuk model Long Short-Term Memory (LSTM). Hasil eksperimen menunjukkan bahwa meskipun LSTM dapat secara efektif menangkap ketergantungan temporal dan pola musiman, penggabungan PSO terutama meningkatkan stabilitas pelatihan daripada akurasi prediksi. Model PSO–LSTM memiliki nilai kesalahan yang lebih tinggi daripada model dasar dan menunjukkan perilaku over-smoothing dengan bias underestimasi, terutama selama periode produksi tinggi. Hasil ini menunjukkan adanya kesenjangan optimasi-generalisasi, yang berarti bahwa optimasi menurunkan kesalahan pelatihan tetapi tidak meningkatkan kinerja pada data baru. Hasil penelitian menunjukkan bahwa keberhasilan optimasi metaheuristik sangat bergantung pada data, terutama ketika data bersifat musiman dan jumlah sampelnya sedikit. Penelitian ini menjelaskan kendala model hibrida berbasis optimasi dan menggarisbawahi perlunya metodologi yang lebih adaptif terhadap data dalam peramalan pertanian.
Kata Kunci: LSTM; Optimasi Swarm Partikel; Peramalan Deret Waktu Musiman; Prediksi Pertanian; Produksi Padi
REFERENSI
[1] S. B. Dhal and D. Kar, “Transforming Agricultural Productivity with AI-Driven Forecasting: Innovations in Food Security and Supply Chain Optimisation,” Forecasting, vol. 6, no. 4, pp. 925–951, Oct. 2024, doi: 10.3390/forecast6040046.
[2] A. Duisenbekova, “Machine learning in ensuring food security: domestic and international practices,” InterConf, no. 61(264), pp. 6–21, Sep. 2025, doi: 10.51582/interconf.19-20.09.2025.001.
[3] T. Yamaguchi, A. M. Radanielson, O. Angeles, K. Katsura, and K. Saito, “Understanding rice yield gaps with crop modeling and machine learning in a long-term continuous cropping experiment,” Field Crops Res., vol. 342, p. 110477, May 2026, doi: 10.1016/j.fcr.2026.110477.
[4] H. M. Firdausi, S. B. Utomo, G. A. Rahardi, and D. H. T. Prasetiyo, “A Multivariate LSTM Approach for Monthly Rice Production Forecasting in East Java,” Jurnal Sistem Cerdas, vol. 8, no. 3, pp. 364–374, Dec. 2025, doi: 10.37396/jsc.v8i3.595.
[5] R. Jaiswal, G. K. Jha, K. Choudhary, and R. R. Kumar, “Agricultural Commodity Price Prediction using Long Short-Term Memory (LSTM) based Neural Networks,” Bhartiya Krishi Anusandhan Patrika, no. Of, Oct. 2023, doi: 10.18805/BKAP613.
[6] M. Johri, Y. Mangal, N. Parashar, A. Ashish, and Kumud, “Optimizing Crop Yield Prediction using Machine Learning and Deep Learning Approach,” in 2024 7th International Conference on Contemporary Computing and Informatics (IC3I), IEEE, Sep. 2024, pp. 1–5. doi: 10.1109/IC3I61595.2024.10828647.
[7] Y. Mao, A. Pranolo, A. P. Wibawa, A. B. Putra Utama, F. A. Dwiyanto, and S. Saifullah, “Selection of Precise Long Short Term Memory (LSTM) Hyperparameters based on Particle Swarm Optimisation,” in 2022 International Conference on Applied Artificial Intelligence and Computing (ICAAIC), IEEE, May 2022, pp. 1114–1121. doi: 10.1109/ICAAIC53929.2022.9792708.
[8] U. Bhimavarapu, G. Battineni, and N. Chintalapudi, “Improved Optimisation Algorithm in LSTM to Predict Crop Yield,” Computers, vol. 12, no. 1, p. 10, Jan. 2023, doi: 10.3390/computers12010010.
[9] M. Kashani, S. Jespersen, and Z. Yang, “Comparative Analysis of Deep Neural Networks for Oil-in-Water Concentration Prediction Using PSO-Based Hyperparameter Optimisation,” in 2025 10th International Conference on Machine Learning Technologies (ICMLT), IEEE, May 2025, pp. 182–187. doi: 10.1109/ICMLT65785.2025.11193272.
[10] A. Badjan, G. I. Rashed, A. O. M. Bahageel, H. Ali I Gony, H. I. Shaheen, and F. M. Tuaimah, “Efficient grid management: smart forecasting of short-term power load using PSO-LSTM,” Engineering Research Express, vol. 6, no. 3, p. 035364, Sep. 2024, doi: 10.1088/2631-8695/ad7ad8.
[11] Y. Y. Hong and J. B. D. Santos, “Day-Ahead Spatiotemporal Wind Speed Forecasting Based on a Hybrid Model of Quantum and Residual Long Short-Term Memory Optimized by Particle Swarm Algorithm,” IEEE Syst. J., vol. 17, no. 4, pp. 1–12, Dec. 2023, doi: 10.1109/JSYST.2023.3265982.
[12] Y.-X. Luo and Y. Ji, “Prediction of the Stock Adjusted Closing Price Based On Improved PSO-LSTM Neural Network,” in 2022 International Conference on Machine Learning and Cybernetics (ICMLC), IEEE, Sep. 2022, pp. 43–48. doi: 10.1109/ICMLC56445.2022.9941330.
[13] C. CHAOURA, H. LAZAR, and Z. JARIR, “Traffic Flow Prediction at Intersections: Enhancing with a Hybrid LSTM-PSO Approach,” International Journal of Advanced Computer Science and Applications, vol. 15, no. 5, pp. 494–501, May 2024, doi: 10.14569/IJACSA.2024.0150549.
[14] T. Lu, R. Wei, and L. Du, “Development and Assessment of Trading Strategies for the A-Share Market Based on PSO-Enhanced LSTM Models,” in 2025 IEEE 7th Symposium on Computers & Informatics (ISCI), IEEE, Aug. 2025, pp. 299–303. doi: 10.1109/ISCI65687.2025.11167189.
[15] M. haziq Anwar, “Crop Yield Prediction Using Machine-Learning,” Journal of Innovative Computing and Emerging Technologies, vol. 4, no. 2, Oct. 2024, doi: 10.56536/jicet.v4i2.136.
[16] M. L. I. Garba, N. Harouna, C. Kadri, M. A. Ali, and H. Moussa, “Crop Yield Prediction in Niger Using Machine Learning Techniques,” Journal of Computer Science, vol. 21, no. 8, pp. 1811–1818, Aug. 2025, doi: 10.3844/jcssp.2025.1811.1818.
[17] Bushara A. R, Adnan Zaman K. T, and Fathima Misriya P. S, “Optimizing crop yield forecasting with ensemble machine learning techniques,” International Journal of Science and Research Archive, vol. 14, no. 1, pp. 1456–1467, Jan. 2025, doi: 10.30574/ijsra.2025.14.1.0189.
[18] Y. Ning, J. Wang, Z. Wang, Y. Zhu, and J. Zhang, “Electricity Load Forecasting Method Based on Improved PSO-LSTM Modeling,” in 2025 International Conference on Power Electronics and Electric Drives (PEED), IEEE, Mar. 2025, pp. 56–60. doi: 10.1109/PEED63748.2025.00019.
[19] G. Wan et al., “Wheat Yield Prediction Using LSTMRFNet: A Hybrid Model Based on Time-Series Data,” Smart Agricultural Technology, p. 102072, Apr. 2026, doi: 10.1016/j.atech.2026.102072.
[20] S. Amalia, A. Dhini, Zulkarnain, C. Za’in, and I. Surjandari, “A temporal fusion transformer for multi-step forecasting of Indonesia’s strategic food commodity prices,” Results in Engineering, vol. 30, p. 110131, Jun. 2026, doi: 10.1016/j.rineng.2026.110131.
[21] M. Bhih, Z. E. A. Elassad, H. Siti, O. EL Meslouhi, K. Abouelmehdi, and A. El Boustani, “Temporal pattern-aware temperature forecasting using CatBoost: A hybrid machine learning approach,” Results in Engineering, vol. 30, p. 110212, Jun. 2026, doi: 10.1016/j.rineng.2026.110212.
[22] M. A. Tanjung, A. P. Sari, and A. Junaidi, “Optimisation of LSTM Hyperparameters Using PSO for Forecasting Shallots and Garlic,” bit-Tech, vol. 8, no. 1, pp. 416–426, Aug. 2025, doi: 10.32877/bt.v8i1.2569.
[23] A. R. Dzaky, M. F. Fathoni, and A. G. Putrada, “PSO-LSTM for Optimum Fertilizer Level Forecasting with NPK Virtual Sensors,” in 2024 7th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), IEEE, Dec. 2024, pp. 344–349. doi: 10.1109/ISRITI64779.2024.10963540.
[24] “Produksi Padi Menurut Kabupaten/Kota - TABLE Statistik - Badan Pusat Statistik Provinsi Jawa Timur.” Accessed: Apr. 12, 2026. [Online]. Available: https://jatim.bps.go.id/id/statistics-table/2/NTc5IzI=/produksi-padi-menurut-kabupaten-kota--ton-.html
[25] “Luas Panen Padi Menurut Kabupaten/Kota - TABLE Statistik - Badan Pusat Statistik Provinsi Jawa Timur.” Accessed: Apr. 12, 2026. [Online]. Available: https://jatim.bps.go.id/id/statistics-table/2/NTc4IzI=/luas-panen-padi-menurut-kabupaten-kota--hektar-.html
[26] “Produksi Padi Menurut Provinsi (Bulanan) - TABLE Statistik - Badan Pusat Statistik Indonesia.” Accessed: Apr. 12, 2026. [Online]. Available: https://www.bps.go.id/id/statistics- table/2/MjUwNiMy/produksi-padi-menurut-provinsi--bulanan---ton-.html
[27] “Luas Panen Padi Menurut Provinsi (Bulanan) - TABLE Statistik - Badan Pusat Statistik Indonesia.” Accessed: Apr. 12, 2026. [Online]. Available: https://www.bps.go.id/id/statistics- table/2/MjUwNCMy/luas-panen-padi-menurut-provinsi-bulanan-.html
[28] S. Thirumal and R. Latha, “Automated Rice Crop Yield Prediction using Sine Cosine Algorithm with Weighted Regularized Extreme Learning Machine,” in 2023 7th International Conference on Intelligent Computing and Control Systems (ICICCS), IEEE, May 2023, pp. 35–40. doi: 10.1109/ICICCS56967.2023.10142403.
[29] R. Murugesan, E. Mishra, and A. H. Krishnan, “Forecasting agricultural commodities prices using deep learning-based models: basic LSTM, bi-LSTM, stacked LSTM, CNN LSTM, and convolutional LSTM,” International Journal of Sustainable Agricultural Management and Informatics, vol. 8, no. 3, p. 242, 2022, doi: 10.1504/IJSAMI.2022.125757.
PUBLISHED
30-6-2026
ISSUE
Vol. 12 No. 2 (2026)
SECTION
Articles