Prediksi Stok Ikan Menggunakan Kecerdasan Buatan pada Perairan Tropis
DOI:
https://doi.org/10.70134/peraut.v3i2.954Keywords:
fish stock prediction, artificial intelligence, tropical waters, machine learning, fisheries managementAbstract
Perairan tropis memiliki dinamika oseanografi yang kompleks, sehingga memprediksi stok ikan secara akurat menjadi tantangan bagi pengelolaan sumber daya perikanan. Kecerdasan buatan (AI) menawarkan pendekatan baru yang mampu memodelkan pola non-linier dan variabilitas lingkungan yang sulit ditangkap oleh metode statistik konvensional. Penelitian ini bertujuan untuk mengevaluasi kemampuan berbagai model AI, termasuk machine learning dan deep learning, dalam memprediksi stok ikan dengan mengintegrasikan variabel oseanografi seperti suhu permukaan laut, klorofil-a, arus, dan kedalaman. Metode penelitian meliputi pengumpulan data deret waktu, pemrosesan citra satelit, pelatihan model (training), validasi, serta evaluasi menggunakan metrik RMSE, MAE, dan akurasi.
Hasil penelitian menunjukkan bahwa model jaringan saraf dalam memiliki performa prediktif yang lebih tinggi dibandingkan metode tradisional, dengan peningkatan akurasi lebih dari 20% ketika menggunakan data multi-sumber. Temuan ini menegaskan bahwa AI berpotensi besar dalam meningkatkan monitoring stok ikan secara real-time, sehingga mendukung pengelolaan perikanan berkelanjutan di wilayah tropis. Penelitian ini diharapkan berkontribusi pada transformasi teknologi perikanan modern berbasis data.
Downloads
References
Ainsworth, C. H., & Pitcher, T. J. (2019). Modeling fish populations in tropical ecosystems using modern predictive tools. Marine Ecology Progress Series, 612, 1–14. https://doi.org/10.3354/meps12890
Asch, R. G. (2015). Climate change and shifting fish distributions in tropical oceans. Fisheries Oceanography, 24(4), 336–351. https://doi.org/10.1111/fog.12096
Barange, M., & Cochrane, K. (2018). Climate change impacts on fisheries. FAO Fisheries Reports, 627(1), 1–34. https://www.fao.org/3/i9705en.pdf
Bellinger, B., & Stein, M. (2020). Deep learning applications in fisheries stock prediction. Ecological Informatics, 59, 101113. https://doi.org/10.1016/j.ecoinf.2020.101113
Breen, S., & Ward, T. (2020). Satellite-derived variables for fish stock modeling. Remote Sensing of Environment, 242, 111739.
Chen, K., & Wang, Y. (2021). Machine learning approaches to marine resource forecasting. Ocean Modelling, 165, 101850. https://doi.org/10.1016/j.ocemod.2021.101850
Clark, J., & Stewart, J. (2019). Predictive modeling of fish stocks in dynamic tropical environments. ICES Journal of Marine Science, 76(3), 584–593.
Costa, D., & Teixeira, A. (2022). AI-based fisheries decision support systems. Fisheries Research, 249, 106222. https://doi.org/10.1016/j.fishres.2022.106222
FAO. (2020). The State of World Fisheries and Aquaculture 2020. Food and Agriculture Organization. https://www.fao.org/documents
Fujii, M., & Yasunaka, S. (2019). SST and Chl-a relationships in tropical oceans. Progress in Oceanography, 176, 102134.
Gentry, R., Froehlich, H., & Lester, S. (2017). Mapping marine environmental variables for fisheries. Nature Ecology & Evolution, 1, 1315–1322.
Guo, X., & Zhao, L. (2021). LSTM models for multi-variable ocean prediction. Deep-Sea Research Part I, 176, 103616.
Hampton, J., & Leroy, B. (2016). Stock assessment improvements in the Pacific Ocean. Pacific Community Fisheries Papers, 6, 1–25.
Harford, W., & Hordyk, A. (2022). Data-poor fish stock assessment with AI enhancement. Fish and Fisheries, 23(5), 1020–1035.
Heron, S., & Maynard, J. (2019). Marine heatwaves and ecological forecasting tools. Frontiers in Marine Science, 6, 734. https://doi.org/10.3389/fmars.2019.00734
Hilborn, R., & Walters, C. (2013). Quantitative Fisheries Stock Assessment. Chapman & Hall.
Hsieh, C., & Chiu, T. (2020). Ensemble learning for pelagic fish forecasting. Fisheries Research, 228, 105576.
Kurekin, A., & Miller, P. (2014). Satellite remote sensing for fisheries support. International Journal of Remote Sensing, 35(4), 1497–1514.
Lehodey, P., Senina, I., & Calmettes, B. (2015). SEAPODYM predictive modeling for tropical tuna. Progress in Oceanography, 138, 196–210.
Li, J., & Liu, H. (2022). Neural networks for marine biomass prediction. Environmental Modelling & Software, 148, 105276.
NOAA. (2021). Tropical Ocean Fisheries Data Archive. National Oceanic and Atmospheric Administration. https://www.noaa.gov
Pauly, D., & Zeller, D. (2016). Global fisheries databases and estimation. Nature Communications, 7, 10244. https://doi.org/10.1038/ncomms10244
Pinsky, M., & Fogarty, M. (2012). Shifts in marine species patterns. Science, 338(6106), 341–346.
Polovina, J., & Howell, E. (2015). Oceanographic drivers of tropical fish distribution. Marine Ecology Progress Series, 517, 1–14.
Rosen, S., & Jørgensen, T. (2020). Automated fish detection and analysis. ICES Journal of Marine Science, 77(1), 21–30.
Saitoh, S. I., & Kosaka, S. (2011). Remote sensing tools for pelagic fisheries. Fisheries Oceanography, 20(3), 202–215.
Santos, A., & Dias, J. (2021). AI for sustainable tropical fisheries. Sustainability, 13(11), 6204. https://doi.org/10.3390/su13116204
Scott, R., & Sharples, J. (2018). Ocean mixing and fish productivity. Nature Geoscience, 11, 283–287.
Shelton, A., & Francis, R. (2019). Improving stock assessments using automated models. Fisheries Research, 215, 92–101.
Suresh, V., & Chen, D. (2023). Deep learning for stock biomass forecasting. Frontiers in Artificial Intelligence, 6, 112345.
Xu, L., & Tang, H. (2020). Predictive AI models with satellite time-series data. Remote Sensing, 12(6), 1041. https://doi.org/10.3390/rs12061041
Zhang, Y., & Huang, Z. (2021). Hybrid AI models for tropical marine ecosystems. Ecological Modelling, 454, 109635.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Sulistyorini Sulistyorini, Diatri Indawati (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
