IoT-based Water Quality Analysis and Fish Species Detection using Deep Learning
Keywords:
Aquaculture, Deep learning, Fish species detection, IoT, Raspberry Pi, Water quality analysisAbstract
Water quality plays a vital role in maintaining aquatic ecosystems and ensuring sustainable aquaculture operations. Continuous monitoring of key parameters such as pH, temperature, and dissolved oxygen is crucial to maintain the optimal environment for aquatic life and to prevent health hazards in fish farming systems. Traditional water quality monitoring methods often involve manual sampling and laboratory analysis, which are time-consuming, less accurate, and fail to provide real-time insights into the aquatic environment. This project presents a smart IoT-based water quality monitoring and fish species detection system integrated with deep learning technology. IoT sensors continuously collect and transmit data related to pH, temperature, and dissolved oxygen to a cloud server for real-time visualization and analysis. Simultaneously, a deep learning model identifies and classifies fish species using image data, enabling intelligent management of aquaculture resources. The system enhances productivity, minimizes human error, and supports sustainable aquaculture by ensuring timely intervention through automated alerts and predictive insights.
References
Ali Hanafi Ahmad, Azizul Azhar Ramli, Afiq Syazwan, “Water quality monitoring and control system in koi fish cultivation based on internet-of-things (IoT),” Jurnal Rekayasa Elektrika, vol. 21, no. 1, Mar. 2025.
A. A. Abu Bakar, Z. Abu Bakar, Z. Mohd Yusoff, M. J. Mohamed Ibrahim, N. A. Mokhtar, and S. N. Zaiton, “IoT-based real-time water quality monitoring and sensor calibration for enhanced accuracy and reliability”, Int. J. Interact. Mob. Technol., vol. 19, no. 1, pp. 155–170, Jan. 2025.
I. Mettildha Mary, T. Raghuntar, M. Priyadarshini, “Automatic Fish species identification using convolutional neural networks (CNN)”, 2024 4th International Conference on Sustainable Expert Systems, Kaski, Nepal, 2024, pp. 1558–1561.
M. Y. Ouis and M. Akhloufi, “YOLO-based fish detection in underwater environments,” Environmental Sciences Proceedings, vol. 29, no. 1, p. 44, 2024.
D. Dhinakaran, S. Manoharan, A. Naveen, “IoT-based environmental control system for fish farms using machine learning”, Int. J. Recent Innov. Trends Comput. Commun., vol. 11, no. 10, 2023, pp. 203–217.
M. Hamzaoui, M. Ould-Elhassen Aoueileyine, L. Romdhani, and R. Bouallegue, “An improved deep learning model for underwater species recognition in aquaculture,” Fishes, vol. 8, no. 10, p. 514, 2023.
A. Bachri, “Freshwater monitoring system design in real-time for fish cultivation”, Int. J. Multidiscipline. Approach. Res. Sci., vol. 2, no. 01, pp. 362–370, Dec. 2023.
G. N. Satya Sai, R. Sudheer, K. S. Manikanta, S. G. Arjula, B. N. Rao and D. V. Sai Maneeswar Mutyala, “IoT based water quality monitoring system,” 2021 IEEE 9th Region 10 Humanitarian Technology Conference (R10-HTC), Bangalore, India, 2021, pp. 1–6.
N. Naj and A. Sanzgiri, “An IoT based real-time monitoring of water quality System”, Asian Journal of Convergence in Technology (AJCT), vol. 7, no. 2, pp. 44–51, Aug. 2021.
Erlend Olsvik et al., “Biometric Fish Classification of Temperate Species Using Convolutional Neural Network with Squeeze-and-Excitation,” Lecture notes in computer science, pp. 89–101, Jan. 2019.
A. Kamilaris, F. X. Prenafeta-Boldú, “Deep learning in agriculture: A survey”, 2018 Computers and Electronics in Agriculture, vol. 147, Apr. 2018, pp. 70–80.
H. Qin, X. Li, J. Liang, Y. Peng, C. Zhang, “DeepFish: Accurate underwater live fish recognition with a deep architecture”, Neurocomputing, vol. 187, pp. 49–58, Apr. 2016.
S. Li, L. D. Xu, Wu He, “The internet of things: A survey”, IEEE Transactions on Industrial Informatics vol. 10, no. 4, Nov. 2014, pp. 2233–2243.
J. Jayaraman, A. Yavari, D. Georgakopoulos, A. Morshed, “Internet of things platform for smart farming: experiences and lessons learnt”, Sensors, 2016, vol. 16, no. 11, 1884.
