A Smart Decision Support System for Floating Net Cage Site Selection Based on Water Quality and Machine Learning
DOI:
https://doi.org/10.3991/ijoe.v21i14.59301Keywords:
fish, floating net cage, IoT, location based, machine learning, sensors, water quality indexAbstract
Fish is a vital food source with high nutritional value and a growing global demand. However, natural fishing can no longer meet consumption needs, prompting a shift toward sustainable aquaculture such as floating net cages. The success of these systems depends greatly on water quality, as sudden changes may cause mass fish mortality and economic loss. This study applies five machine-learning algorithms: 1) support vector machine (SVM), 2) K-nearest neighbor (KNN), 3) Naïve Bayes, 4) AdaBoost, and 5) random forest—to classify water quality using three features: 1) dissolved oxygen (DO), 2) pH, and 3) temperature. The dataset, publicly available at https://doi.org/10.5281/zenodo.15600660, shows DO as the most influential feature (48.15%), followed by pH (40.23%) and temperature (11.62%). Random forest achieved the highest accuracy (99.96%) with the lowest errors (MSE = 0.0004, RMSE = 0.0196, R² = 0.9981). The trained model was embedded in an IoT device coded in C for real-time water-quality monitoring and site recommendations. The results confirm that combining IoT and machine learning offers an intelligent and efficient solution for adaptive, sustainable fish-farming systems.
References
[1] Food and Agriculture Organization of the United Nations, The State of World Fisheries and Aquaculture - Blue Transformation in Action. 2024. [Online]. Available: https://www.fao.org/3/ca9229en/online/ca9229en.html#chapter-1_1
[2] C. Nithin, N. Reddy, S. Gautham, P. A. V, and P. Kumar, “Water Quality Monitoring System Based On Iot,” vol. 8, no. 4, pp. 69–73, 2023.
[3] W. Eric, E. Wa, U. Eric, N. Pb-, and G. Eric, “Water Quality & Standards,” Water, pp. 76–86, 2017.
[4] W. Khan, A. Vahab, and A. M. | N. Hasan, “Water Quality Requirements and Management Strategies for Fish Farming A Case Study of Ponds Around Gurgaon Canal NUH Palwal,” Int. J. Trend Sci. Res. Dev., vol. Volume-2, no. Issue-1, pp. 388–393, 2017, doi: 10.31142/ijtsrd5914.
[5] K. S. Negara, Appendix VI concerning National Water Quality Standards - PP Number 22 of 2021 concerning the Implementation of Environmental Protection and Management, vol. 1, no. 078487A. 2021, p. 483. [Online]. Available: http://www.jdih.setjen.kemendagri.go.id/
[6] D. Hermanto, D. Stiawan, B. Y. Suprapto, E. Permata, and E. P. Widiyanto, “New Approach Monitoring System with ESP32 and MQTT for the Best Position of the Floating Net Cage,” Int. Conf. Electr. Eng. Comput. Sci. Informatics, no. September, pp. 139–144, 2023, doi: 10.1109/EECSI59885.2023.10295802.
[7] J. S. Fidari and M. Bisri, “Intensive Pond Design Model Planning for Probolinggo Regency”.
[8] B. Di, W. Plta, K. Panjang, and K. Riau, “Sustainable Floating Net Cage Development Strategy in Koto Panjang Hydroelectric Reservoir Kampar Riau,” vol. 2, pp. 145–160, 2010.
[9] L. Atzori, A. Iera, and G. Morabito, “The Internet of Things : A survey,” Comput. Networks, vol. 54, no. 15, pp. 2787–2805, 2025, doi: 10.1016/j.comnet.2010.05.010.
[10] P. Malhotra, Y. Singh, P. Anand, D. K. Bangotra, P. K. Singh, and ..., “Internet of things: Evolution, concerns and security challenges,” 2021, mdpi.com. [Online]. Available: https://www.mdpi.com/1424-8220/21/5/1809
[11] G. Gao, K. Xiao, and M. Chen, “An intelligent IoT-based control and traceability system to forecast and maintain water quality in freshwater fish farms,” Comput. Electron. Agric., vol. 166, no. March, 2019, doi: 10.1016/j.compag.2019.105013.
[12] and C. S. Muti’ah, M S A Majid, “What determines aquaculture fish production ? empirical evidence from South Aceh Regency , Indonesia,” IOP Conf. Ser. Earth Environ. Sci., no. March, 2021, doi: 10.1088/1755-1315/674/1/012040.
[13] W. Kusumawijaya and A. Aula, “Water Quality Monitoring And Control System In Fish Cultivation Pond Using Arduino Cloud,” Comput. Electr. Eng. J., vol. 1, no. 3, pp. 333–340, 2024, doi: 10.26418/telectrical.v1i3.73567.
[14] J. S. Fidari and M. Bisri, “Intensive Pond Pond Design Model Planning,” Tek. Pengair., vol. 8, pp. 252–261, 2017.
[15] F. Simanjuntak. I.C.B.H dan Muhamad, “Floating Net Cage Management Strategy,” Semin. Nas. Edusainstek FMIPA UNIMUS 2018, pp. 38–46, 2018.
[16] K. Abirami, P. C. Radhakrishna, and M. A. Venkatesan, “Water Quality Analysis and Prediction using Machine Learning,” Proc. - 2023 12th IEEE Int. Conf. Commun. Syst. Netw. Technol. CSNT 2023, vol. 10, pp. 241–245, 2023, doi: 10.1109/CSNT57126.2023.10134661.
[17] B. Shrimali, S. Surati, A. Patel, and R. Kansagara, “Predictive Modeling of Water Quality in Indian Rivers: A Machine Learning Approach for Sustainable Resource Management,” no. IC3Com 2024, pp. 165–174, 2025, doi: 10.5220/0013303800004646.
[18] G. A. Rudrani et al., “Machine learning approaches for predicting water quality towards climate-resilient groundwater management in southern India,” Hydrol. Res., vol. 56, no. 8, pp. 754–773, 2025, doi: 10.2166/nh.2025.042.
[19] A. Sharma, R. Sharma, R. Rana, and A. Kalia, “Water quality prediction using Machine Learning Models,” E3S Web Conf., vol. 596, pp. 1–12, 2024, doi: 10.1051/e3sconf/202459601025.
[20] M. Vijay Anand, C. Sohitha, G. N. Saraswathi, and G. V. Lavanya, “Water quality prediction using CNN,” J. Phys. Conf. Ser., vol. 2484, no. 1, 2023, doi: 10.1088/1742-6596/2484/1/012051.
[21] X. Wang, Y. Li, Q. Qiao, A. Tavares, and Y. Liang, “Water Quality Prediction Based on Machine Learning and Comprehensive Weighting Methods,” Entropy, vol. 25, no. 8, pp. 1–20, 2023, doi: 10.3390/e25081186.
[22] A. G. Sohom Sen, Samaresh Maiti, Sumanta Manna, Bibaswan Roy, “Smart Prediction of Water Quality System for Aquaculture Using Machine Learning Algorithms,” J. Curr. Trends Comput. Sci. Res., vol. 2, no. 3, pp. 212–225, 2023.
[23] J. Julian, A. B. Dewantara, and F. Wahyuni, “Design of machine learning-based water quality prediction system with recursive feature elimination cross-validation,” J. Infotel, vol. 15, no. 3, pp. 249–255, 2023, doi: 10.20895/infotel.v15i3.977.
[24] C. L. Li Tingting, Lu Jian, Wu Jun, Zhang Zhenhua, “Predicting Aquaculture Water Quality Using Machine Learning Approaches,” Educ. Psychol., vol. 40, no. 5, pp. 533–534, 2020, doi: 10.1080/01443410.2020.1755503.
[25] M. Manoj, R. Rajan, W. Quality, and R. Pi, “Precision Aquaculture Using Iot & Machine Learning,” AGPE R. Gondwana Res. J. Hist. Sci. Econ. Polit. Soc. Sci., vol. 02, no. 01, pp. 105–111, 2021.
[26] D. Hermanto, D. Stiawan, B. Y. Suprapto, E. Permata, and E. P. Widiyanto, “New Approach Monitoring System with ESP32 and MQTT for the Best Position of the Floating Net Cage,” 2023 10th Int. Conf. Electr. Eng. Comput. Sci. Informatics, no. September, pp. 139–144, 2023, doi: 10.1109/EECSI59885.2023.10295802.
[27] T. B. K.Phani Rama Krishna, Dr.G.V. Prasanna Anjaneyulu, Anjaneyulu Naik.R, Dr.B.Keerthi Samhitha,Dr.J.Ravindranadh, Sreedhar Bhukya, “Dissolved Oxygen Measurement in Water,” J. Theor. Appl. Inf. Technol., vol. 103, no. 4, pp. 1426–1431, 2025.
[28] R. Pramana, B. Y. Suprapto, and Z. Nawawi, “Application of fuzzy logic in decision-making process for relocation of floating net cages in river fish farming,” Glob. J. Environ. Sci. Manag., vol. 10, no. 1, pp. 117–132, 2024, doi: 10.22034/gjesm.2024.01.09.
[29] P. G. Arepalli, K. Jairam Naik, and J. K. Rout, “Aquaculture Water Quality Classification with Sparse Attention Transformers: Leveraging Water and Environmental Parameters,” ACM Int. Conf. Proceeding Ser., pp. 318–325, 2024, doi: 10.1145/3651781.3651829.
[30] H. Liu, Y. Pei, Q. Bei, and L. Deng, “Improved DeepSORT Algorithm Based on Multi-Feature Fusion,” Appl. Syst. Innov., 2022, doi: https://doi.org/10.3390/asi5030055.
[31] M. Ragab, “Internet of Things Assisted Solid Biofuel Classification Using Sailfish Optimizer Hybrid Deep Learning Model for Smart Cities,” Sustain., vol. 15, no. 16, 2023, doi: 10.3390/su151612523.
[32] B. Sliwa, N. Piatkowski, and C. Wietfeld, “LIMITS: Lightweight Machine Learning for IoT Systems with Resource Limitations,” in IEEE International Conference on Communications, 2020. doi: 10.1109/ICC40277.2020.9149180.
[33] K. P. Rasheed Abdul Haq and V. P. Harigovindan, “Water Quality Prediction for Smart Aquaculture Using Hybrid Deep Learning Models,” IEEE Access, vol. 10, pp. 60078–60098, 2022, doi: 10.1109/ACCESS.2022.3180482.
[34] I. Cvitić, D. Peraković, M. Periša, and B. Gupta, “Ensemble machine learning approach for classification of IoT devices in smart home,” Int. J. Mach. Learn. Cybern., vol. 12, no. 11, pp. 3179–3202, 2021, doi: 10.1007/s13042-020-01241-0.
[35] Z. R. Saputra Elsi et al., “Feature Selection using Chi Square to Improve Attack Detection Classification in IoT Network: Work in Progress,” Int. Conf. Electr. Eng. Comput. Sci. Informatics, vol. 2022-Octob, no. October, pp. 226–232, 2022, doi: 10.23919/EECSI56542.2022.9946621.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Dedy Hermanto, Deris Stiawan, Bhakti Yudho Suprapto, Mohd. Yazid Idris, Rahmat Budiarto
This work is licensed under a Creative Commons Attribution 4.0 International License.
