Fish Growth Trajectory Tracking via Reinforcement Learning in Precision Aquaculture

This paper studies the fish growth trajectory tracking via reinforcement learning under a representative bioenergetic growth model. Due to the complex aquaculture condition and uncertain environmental factors such as temperature, dissolved oxygen, un-ionized ammonia, and strong nonlinear couplings, including multi-inputs of the fish growth model, the growth trajectory tracking problem can not be efficiently solved by the model-based control approaches in precision aquaculture. To this purpose, we formulate the growth trajectory tracking problem as sampled-data optimal control using discrete state-action pairs Markov decision process. We propose two Q-learning algorithms that learn the optimal control policy from the sampled data of the fish growth trajectories at every stage of the fish life cycle from juveniles to the desired market weight in the aquaculture environment. The Q-learning scheme learns the optimal feeding control policy to fish growth rate cultured in cages and the optimal feeding rate control policy with an optimal temperature profile for the aquaculture fish growth rate in tanks. The simulation results demonstrate that both Q-learning strategies achieve high trajectory tracking performance with less amount feeding rates.

[1]  R. Filgueira,et al.  A fully-spatial ecosystem-DEB model of oyster (Crassostrea virginica) carrying capacity in the Richibucto Estuary, Eastern Canada , 2014 .

[2]  Erik Ursin,et al.  A Mathematical Model of Some Aspects of Fish Growth, Respiration, and Mortality , 1967 .

[3]  Masashi Sugiyama,et al.  Statistical Reinforcement Learning - Modern Machine Learning Approaches , 2015, Chapman and Hall / CRC machine learning and pattern recognition series.

[4]  D. Little,et al.  Reproductive performance and the growth of pre-stunted and normal Nile tilapia (Oreochromis niloticus) broodfish at varying feeding rates , 2007 .

[5]  Changyin Sun,et al.  Deterministic Policy Gradient With Integral Compensator for Robust Quadrotor Control , 2020, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[6]  Min Sun,et al.  Models for estimating feed intake in aquaculture: A review , 2016, Comput. Electron. Agric..

[7]  Peter Stone,et al.  Reinforcement learning , 2019, Scholarpedia.

[8]  Gerardo G. Acosta,et al.  AUV Position Tracking Control Using End-to-End Deep Reinforcement Learning , 2018, OCEANS 2018 MTS/IEEE Charleston.

[9]  Y. Yi A bioenergetics growth model for Nile tilapia (Oreochromis niloticus) based on limiting nutrients and fish standing crop in fertilized ponds , 1998 .

[10]  Mark Gall,et al.  An ecosystem model for optimising production in integrated multitrophic aquaculture systems , 2012 .

[11]  Cosimo Solidoro,et al.  A bioenergetic growth model for comparing Sparus aurata's feeding experiments , 2008 .

[12]  Kwang-Ming Liu,et al.  Bioenergetic modelling of effects of fertilization, stocking density, and spawning on growth of the Nile tilapia, Oreochromis niloticus (L.) , 1992 .

[13]  Panos M. Pardalos,et al.  Approximate dynamic programming: solving the curses of dimensionality , 2009, Optim. Methods Softw..

[14]  P. Gatta state of world fisheries and aquaculture , 2017 .

[15]  Jinliang Ding,et al.  Reinforcement Learning Based Decision Making of Operational Indices in Process Industry Under Changing Environment , 2021, IEEE Transactions on Industrial Informatics.

[16]  Sean R Eddy,et al.  What is dynamic programming? , 2004, Nature Biotechnology.

[17]  Divas Karimanzira,et al.  Dynamic modeling of the INAPRO aquaponic system , 2016 .

[18]  Cheng Wu,et al.  Depth Control of Model-Free AUVs via Reinforcement Learning , 2017, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[19]  Daniel Berckmans,et al.  Precision fish farming: A new framework to improve production in aquaculture , 2017, Biosystems Engineering.

[20]  Dominique P. Bureau,et al.  Development of bioenergetic models and the Fish-PrFEQ software to estimate production, feeding ration and waste output in aquaculture , 1998 .

[21]  Dimitri P. Bertsekas,et al.  Dynamic Programming and Optimal Control, Two Volume Set , 1995 .

[22]  K. Chunkao,et al.  Fish Growth Model for Nile Tilapia (Oreochromis niloticus) in Wastewater Oxidation Pond, Thailand , 2012 .

[23]  H. Mooney,et al.  Effect of aquaculture on world fish supplies , 2000, Nature.

[24]  A. Humphries,et al.  Modeling the Growth of Sugar Kelp (Saccharina latissima) in Aquaculture Systems using Dynamic Energy Budget Theory , 2020, Ecological Modelling.

[25]  Jay H. Lee,et al.  Approximate dynamic programming-based approaches for input-output data-driven control of nonlinear processes , 2005, Autom..

[26]  J. Giske,et al.  Hormones as adaptive control systems in juvenile fish , 2019, Biology Open.

[27]  Bas Kooijman,et al.  Dynamic Energy Budget Theory for Metabolic Organisation , 2005 .

[28]  I. Seginer Growth models of gilthead sea bream (Sparus aurata L.) for aquaculture: A review , 2016 .