Forecasting Aquaponic Systems Behaviour With Recurrent Neural Networks Models


  • Juan Cardenas-Cartagena University of Agder
  • Mohamed Elnourani
  • Baltasar Beferull-Lozano



Recurrent Neural Network, Long Short-term Memory, Gated Recurrent Unit, Data-driven Modelling, Aquaponics


Aquaponic systems provide a reliable solution to grow vegetables while cultivating fish (or other aquatic organisms) in a controlled environment. The main advantage of these systems compared with traditional soil-based agriculture and aquaculture installations is the ability to produce fish and vegetables with low water consumption. Aquaponics requires a robust control system capable of optimizing fish and plant growth while ensuring a safe operation. To support the control system, this work explores the design process of Deep Learning models based on Recurrent Neural Networks to forecast one hour of pH values in small-scale industrial Aquaponics. This implementation guides us through the machine learning life-cycle with industrial time-series data, i.e. data acquisition, pre-processing, feature engineering, architecture selection, training, and model verification.


M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, G. S. Corrado, A. Davis, J. Dean, M. Devin, S. Ghemawat, I. Goodfellow, A. Harp, G. Irving, M. Isard, Y. Jia, R. Jozefowicz, L. Kaiser, M. Kudlur, J. Levenberg, D. Mane, R. Monga, S. Moore, D. Murray, C. Olah, M. Schuster, J. Shlens, B. Steiner, I. Sutskever, K. Talwar, P. Tucker, V. Vanhoucke, V. Vasudevan, F. Viegas, O. Vinyals, P. Warden, M. Wattenberg, M. Wicke, Y. Yu, and X. Zheng. TensorFlow: Large-scale machine learning on heterogeneous systems, 2015. URL Software available from

A. Ahmed, S. Zulfiqar, A. Ghandar, Y. Chen, M. Hanai, and G. Theodoropoulos. Digital Twin Technology for Aquaponics: Towards Optimizing Food Production with Dynamic Data Driven Application Systems. In G. Tan, A. Lehmann, Y. M. Teo, and W. Cai, editors, Methods and Applications for Modeling and Simulation of Complex Systems, volume 1094, pages 3–14. Springer Singapore, 2019. ISBN 9789811510779 9789811510786. doi: 10.1007/978-981-15-1078-6 1.

T. Dozat. Incorporating nesterov momentum into adam. In The International Conference on Learning Representations, 2016.

K. P. Ferentinos and L. D. Albright. Predictive neural network modeling of ph and electrical conductivity in deep-though hydroponics. Transactions of the ASAE, 45:10, 2002. doi: 10.13031/2013.11412.

R. Sallenave. Important water quality parameters in aquaponics systems. Technical report, College of Agricultural, Consumer and Environmental Science, New Mexico State University, 2016. URL

M. Timmons, T. Guerdat, and B. Vinci. Recirculating Aquaculture. Ithaca Publishing Company LLC, 4th edition, 2018. ISBN 9780971264670.

S. Goddek, A. Joyce, B. Kotzen, and G. M. Burnell, editors. Aquaponics Food Production Systems: Combined Aquaculture and Hydroponic Production Technologies for the Future. Springer International Publishing, Cham, 2019. ISBN 978-3-030-15942-9 978-3030-15943-6. doi: 10.1007/978-3-030-15943-6.

I. Goodfellow, Y. Bengio, and A. Courville. Deep Learning. Adaptive Computation and Machine Learning. The MIT Press, Cambridge, Massachusetts, 2016. ISBN 978-0-26203561-3. doi: 10.5555/3086952.

Z. Hu, Y. Zhang, Y. Zhao, M. Xie, J. Zhong, Z. Tu, and J. Liu. A water quality prediction method based on the deep LSTM network considering correlation in smart mariculture. 19(6):1420, 2019. ISSN 1424-8220. doi: 10.3390/s19061420. URL

W. Li, H. Wu, N. Zhu, Y. Jiang, J. Tan, and Y. Guo. Prediction of dissolved oxygen in a fishery pond based on gated recurrent unit (GRU). Information Processing in Agriculture, Feb. 2020. ISSN 22143173. doi: 10.1016/j.inpa.2020.02.002.

J. Liu, C. Yu, Z. Hu, Y. Zhao, Y. Bai, M. Xie, and J. Luo. Accurate prediction scheme of water quality in smart mariculture with deep bis-SRU learning network. 8:24784–24798, 2020. ISSN 2169-3536. doi: 10.1109/ACCESS.2020. 2971253. URL