Predicting Total Fish Production Using An LSTM-Based Linear Attention Model
Abstract
Predicting fish production is important for supporting food security and sustainable fisheries management in Indonesia, particularly in the context of science-based policy making and catch quota regulation. However, accurate forecasting remains challenging due to inconsistencies in fisheries logbook data and the difficulty of capturing complex temporal patterns in production records. This study proposes a deep learning-based predictive framework for forecasting total fish production using a Trapezoid Long Short-Term Memory Linear Attention model. The model integrates an LSTM architecture with a linear attention mechanism to capture temporal dependencies and assign greater weight to relevant input features. The annual total production values were normalized using a global maximum value calculated across all fish species and years in the dataset. Model performance was evaluated using root mean squared error (RMSE) and mean absolute error (MAE). The experimental results produced an RMSE of 0.00465 and an MAE of 0.00244, indicating promising predictive performance after normalization. The model was trained by minimizing the mean squared error loss function. The predicted total production trends may provide useful scientific evidence for monitoring fishery production patterns, supporting precautionary stock management, and informing sustainable catch quota policies. Overall, the proposed model offers a data-driven approach for improving fisheries forecasting and strengthening evidence-based food security planning in Indonesia.
Keywords: fish production prediction; deep learning; LSTM; linear attention; sustainable fisheries management; food security; catch quota policy; Indonesia.
Full Text:
PDFReferences
A. Baheramsyah, B. Cahyono, and Suganda, “Slurry Ice as a Cooling System on 30 GT Fishing Vessel,” International Journal of Marine Engineering Innovation and Research, vol. 1, no. 3, pp. 136–142, 2017, doi: 10.12962/J25481479.V1I3.
F. T. C. Barreto, M. B. L. da Silva, M. C. de O. Costa, K. C. Lacerda, and C. L. da S. Junior, “Convolutional long short-term memory neural network for spatiotemporal forecasting of surface currents from HF-radar,” Ocean Model. (Oxf)., vol. 201, p. 102711, Apr. 2026, doi: 10.1016/J.OCEMOD.2026.102711.
T. Marwa, Muizzuddin, A. Bashir, S. Andaiyani, and A. Cahyadi, “Determinants of the Blue Economy Growth in the Era of Sustainability: A Case Study of Indonesia,” Economies 2024, Vol. 12, Page 299, vol. 12, no. 11, p. 299, Nov. 2024, doi: 10.3390/ECONOMIES12110299.
H. Setiyowati, M. Nugroho, and A. Halik, “Developing a Blue Economy in Depok West Java, Indonesia: Opportunities and Challenges of Neon Tetra Fish Cultivation,” Sustainability (Switzerland), vol. 14, no. 20, Oct. 2022, doi: 10.3390/SU142013028.
J. P. Kritzer, F. Sun, D. Willard, J. Mimikakis, and J. Virdin, “Fisheries,” pp. 33–44, 2025, doi: 10.1007/978-981-19-4790-2_3.
J. Kelautan, P. Terapan, E. Khusus, # Korespondensi, S. Arsitektur, and S. W. Trenggono, “PENANGKAPAN IKAN TERUKUR BERBASIS KUOTA UNTUK KEBERLANJUTAN SUMBER DAYA PERIKANAN DI INDONESIA,” Jurnal Kelautan dan Perikanan Terapan (JKPT), vol. 1, no. 0, pp. 1–8, Jan. 2023, doi: 10.15578/JKPT.V1I0.12057.
M. M. H. Mozumder and P. Schneider, “Advancing sustainability through the circular economy in small-scale fisheries: A global review of practices, challenges, and policy innovations,” Mar. Policy, vol. 185, p. 107001, Mar. 2026, doi: 10.1016/J.MARPOL.2025.107001.
I. Van-Deste, J. C. Lopes, and R. P. Lopes, “Memory vs. Attention: Investigating LSTM and Transformer Models in Human Action Recognition,” Procedia Comput. Sci., vol. 278, pp. 1299–1306, Jan. 2026, doi: 10.1016/J.PROCS.2026.03.113.
J. Huang, W. Chen, and T. Zhang, “A linear-attention-combined convolutional neural network for EEG-based visual stimulus recognition,” Biocybern. Biomed. Eng., vol. 44, no. 2, pp. 369–379, Apr. 2024, doi: 10.1016/J.BBE.2024.05.001.
N. Stacey et al., “Developing sustainable small-scale fisheries livelihoods in Indonesia: Trends, enabling and constraining factors, and future opportunities,” Mar. Policy, vol. 132, p. 104654, Oct. 2021, doi: 10.1016/J.MARPOL.2021.104654.
A. Suherman, Y. Hernuryadin, P. Suadela, U. A. Furkon, and T. Amboro, “Transformation of Indonesian capture fisheries governance: Review and prospects,” Mar. Policy, vol. 174, p. 106619, Apr. 2025, doi: 10.1016/J.MARPOL.2025.106619.
K. Wang, C. Zhang, Y. Ji, B. Xu, Y. Xue, and Y. Ren, “Navigating life-history parameter uncertainty in data-limited fisheries: a comparative analysis of length-based stock assessment methods,” Reviews in Fish Biology and Fisheries 2025 35:3, vol. 35, no. 3, pp. 1711–1733, Jul. 2025, doi: 10.1007/S11160-025-09979-Y.
J. P. P. Merma Yucra, D. J. Cerezo Quina, G. A. Echaiz Espinoza, M. A. Valderrama Solis, D. D. Yanyachi Aco Cardenas, and A. Ortiz Salazar, “Design and Implementation of an LSTM Model with Embeddings on MCUs for Prediction of Meteorological Variables,” Sensors, vol. 25, no. 12, Jun. 2025, doi: 10.3390/s25123601.
M. Alazab, S. Khan, S. S. R. Krishnan, Q. V. Pham, M. P. K. Reddy, and T. R. Gadekallu, “A Multidirectional LSTM Model for Predicting the Stability of a Smart Grid,” IEEE Access, vol. 8, pp. 85454–85463, 2020, doi: 10.1109/ACCESS.2020.2991067.
D. G. Lui, G. Tartaglione, F. Conti, G. De Tommasi, and S. Santini, “Long Short-Term Memory-Based Neural Networks for Missile Maneuvers Trajectories Prediction∗,” IEEE Access, vol. 11, pp. 30819–30831, 2023, doi: 10.1109/ACCESS.2023.3262023.
A. Moghar and M. Hamiche, “Stock Market Prediction Using LSTM Recurrent Neural Network,” in Procedia Computer Science, Elsevier B.V., 2020, pp. 1168–1173. doi: 10.1016/j.procs.2020.03.049.
Y. P. Huang and S. P. Khabusi, “Artificial Intelligence of Things (AIoT) Advances in Aquaculture: A Review,” Processes 2025, Vol. 13, Page 73, vol. 13, no. 1, p. 73, Jan. 2025, doi: 10.3390/PR13010073.
M. M. Comesaña, L. Febrero-Garrido, F. Troncoso-Pastoriza, and J. Martínez-Torres, “Prediction of building’s thermal performance using LSTM and MLP neural networks,” Applied Sciences (Switzerland), vol. 10, no. 21, pp. 1–16, Nov. 2020, doi: 10.3390/app10217439.
A. Q. Wu et al., “Deep Learning for Sustainable Aquaculture: Opportunities and Challenges,” Sustainability 2025, Vol. 17, Page 5084, vol. 17, no. 11, p. 5084, Jun. 2025, doi: 10.3390/SU17115084.
Y. He and Q. Chen, “Construction and Application of LSTM-Based Prediction Model for Tunnel Surrounding Rock Deformation,” Sustainability (Switzerland), vol. 15, no. 8, Apr. 2023, doi: 10.3390/su15086877.
H. Xu, L. Song, Y. Li, T. Zhang, and J. Shen, “Comparison of LSTM and QR models for predicting CPUE of albacore tuna in waters near the Cook Islands,” vol. 91, pp. 259–274, 2025, doi: 10.1007/s12562-025-01851-z.
H. Xu et al., “Effects of Different Spatial Resolutions on Prediction Accuracy of Thunnus alalunga Fishing Ground in Waters Near the Cook Islands Based on Long Short-Term Memory (LSTM) Neural Network Model,” Journal of Ocean University of China 2023 22:5, vol. 22, no. 5, pp. 1427–1438, Sep. 2023, doi: 10.1007/S11802-023-5525-5.
H. Liu and L. Yang, “A Comparative Study of CNN-sLSTM-Attention-Based Time Series Forecasting: Performance Evaluation on Data with Symmetry and Asymmetry Phenomena,” Symmetry (Basel)., vol. 17, no. 11, Nov. 2025, doi: 10.3390/sym17111846.
S. Bilotta, E. Collini, P. Nesi, and G. Pantaleo, “Short-Term Prediction of City Traffic Flow via Convolutional Deep Learning,” IEEE Access, vol. 10, pp. 113086–113099, 2022, doi: 10.1109/ACCESS.2022.3217240.
N. González-Cancelas, J. Vaca-Cabrero, and A. Camarero-Orive, “The Role of the Fishing Sector in the Blue Economy: Prioritization, Environmental Challenges, and Sustainable Strategies in Europe, with a Focus on Spain,” Journal of Marine Science and Engineering 2025, Vol. 13, Page 621, vol. 13, no. 3, p. 621, Mar. 2025, doi: 10.3390/JMSE13030621.
W. Taparhudee et al., “An Attention-Based Hybrid CNN–Bidirectional LSTM Model for Classifying Chlorophyll-a Concentration in Coastal Waters,” Water 2026, Vol. 18, Page 33, vol. 18, no. 1, p. 33, Dec. 2025, doi: 10.3390/W18010033.
Y. Zhang, M. Yamamoto, G. Suzuki, and H. Shioya, “Collaborative Forecasting and Analysis of Fish Catch in Hokkaido From Multiple Scales by Using Neural Network and ARIMA Model,” IEEE Access, vol. 10, pp. 7823–7833, 2022, doi: 10.1109/ACCESS.2022.3141767.
Y. Zhao, C. S. Lim, F. Xue, C. Long, and A. H. P. Tan, “Lightweight LSTM and GRU Design for Data-Driven Rotor Position Error Estimation in IPMSM Drives,” IEEE Open Journal of the Industrial Electronics Society, vol. 6, pp. 851–867, 2025, doi: 10.1109/OJIES.2025.3571204.
H. Xu et al., “Effects of Different Spatial Resolutions on Prediction Accuracy of Thunnus alalunga Fishing Ground in Waters Near the Cook Islands Based on Long Short-Term Memory (LSTM) Neural Network Model,” Journal of Ocean University of China, vol. 22, no. 5, pp. 1427–1438, Oct. 2023, doi: 10.1007/s11802-023-5525-5.
W. Wirata et al., “Development of a Deep Learning Based Price Prediction Model for Katsuwonus pelamis at Nizam Zachman Fishing Port Jakarta Indonesia,” Thalassas: An International Journal of Marine Sciences 2025 41:2, vol. 41, no. 2, pp. 69-, Mar. 2025, doi: 10.1007/S41208-025-00822-6.
S. Bilotta, E. Collini, P. Nesi, and G. Pantaleo, “Short-Term Prediction of City Traffic Flow via Convolutional Deep Learning,” IEEE Access, vol. 10, pp. 113086–113099, 2022, doi: 10.1109/ACCESS.2022.3217240.
Refbacks
- There are currently no refbacks.
