Abstract
Spirulina/Arthrospira is well known as a microscopic filamentous cyanobacterium, which is rich in nutrition and minerals. Therefore, Spirulina/Arthrospira cultivation industry has been adopting many optimization methods for enhancing biomass productivity. Recently, machine learning has been an emerging approach thanks to their efficacy. In this paper, a novel time-dependent reinforcement learning (RL) method with state prediction by long short-term memory (LSTM) networks is proposed to optimize the dry-weight yield of Spirulina sp. HH cultivation. The simulation results show that under the same light condition, with the proposed algorithm, the Spirulina sp. HH cultivation system produces a yield 17% higher than that of the traditional cultivation method and 10% higher than that of the threshold-based method. The results of the RL method from this study promise a significant benefit in Spirulina farm production when applying it for proactively planning biomass production and enhancing profit.
Graphical abstract
Similar content being viewed by others
Availability of data and material
Ready to present if requested
Code availability
We used the Python programming language. Code will be provided upon request
Notes
The commercially produced species have been transferred from the genus Spirulina to the genus Arthrospira; however we will continue to use the name Spirulina in the text.
References
Aiba S (1982) Growth kinetics of photosynthetic microorganisms. In: Microbial reactions. Advances in Biochemical Engineering, 23rd edn. Springer, Berlin, pp 85–156
Béchet Q, Shilton A, Guieysse B (2013) Modeling the effects of light and temperature on algae growth: state of the art and critical assessment for productivity prediction during outdoor cultivation. Biotechnol Adv 31:1648–1663
Bellman R (1957) A Markovian decision process. J Math Mech 6:679–684
Boyan J, Littman M (2000) Exact solutions to time-dependent MDPs. Adv Neural Inf Proces Syst 13:1026–1032
Choi E, Hewlett D, Uszkoreit J, Polosukhin I, Lacoste A, Berant J (2017) Coarse-to-fine question answering for long documents. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). pp 209–220
Chung I, Kim S, Lee J, Kim KJ, Hwang SJ, Yang E (2020) Deep mixed effect model using Gaussian processes: a personalized and reliable prediction for healthcare. In: Proceedings of the 34th AAAI Conference on Artificial Intelligence. pp 3649–3657
da Fontoura PD, Duarte JH, Vendruscolo RG, Wagner R, Ballus CA, da Silva OW, Godoy HT, Barcia MT, de Morais MG, Radmann EM, Costa JAV (2020) Role of light emitting diode (LED) wavelengths on increase of protein productivity and free amino acid profile of Spirulina sp. cultures. Bioresour Technol 306:123184
De Morais MG, Da Fontoura PD, Moreira JB, Duarte JH, Costa JAV (2018) Phycocyanin from microalgae: properties, extraction and purification, with some recent applications. Ind Biotechnol 14:30–37
Doan YTT, Obbard JP (2015) Two-stage cultivation of a Nannochloropsis mutant for biodiesel feedstock. J Appl Phycol 27:2203–2208
Fan H, Wang K, Wang C, Yu F, He X, Ma J, Li X (2020) A comparative study on growth characters and nutrients removal from wastewater by two microalgae under optimized light regimes. Environ Technol Innov 19:100849
Gershwin ME, Belay A (eds) (2007) Spirulina in human nutrition and health. CRC Press, Boca Raton
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9:1735–1780
Huong TT, Thanh NH, Van NT, Dat NT, Long NV, Mrshall A (2018) Water and energy-efficient irrigation based on Markov decision model for precision agriculture. In: 2018 IEEE Seventh International Conference on Communications and Electronics (ICCE). IEEE, pp 51–56
Irukula S (2015) Reinforcement learning based controller for precision irrigation. Masters Thesis, Texas A&M University
Jeong K-S, Joo G-J, Kim H-W, Ha K, Rechnagel F (2001) Prediction and elucidation of phytoplankton dynamics in the Nakdong River (Korea) by means of a recurrent artificial neural network. Ecol Model 146:115–129
Jin J, Song C, Li H, Gai K, Wang J, Zhang W (2018) Real-time bidding with multi-agent reinforcement learning in display advertising. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management. pp 2193–2201
Juneja A, Murthy GS (2018) Model predictive control coupled with economic and environmental constraints for optimum algal production. Bioresour Technol 250:556–563
Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations,. ICLR 2015 - Conference Track Proceedings. arXiv:1412.6980
Kormushev P, Calinon S, Caldwell DG (2013) Reinforcement learning in robotics: applications and real-world challenges. Robotics 2:122–148
Landeta JMI, Cortés CBY, Azúa HM (2014) Markovian decision process to find optimal policies in the management of an orange farm. Investig Operacional 35:68–77
Lee HY, Erickson LE, Yang SS (1987) Kinetics and bioenergetics of light-limited photoautotrophic growth of Spirulina platensis. Biotechnol Bioeng 29:832–843
Lee E, Jalalizadeh M, Zhang Q (2015) Growth kinetic models for microalgae cultivation: a review. Algal Res 12:497–512
Liang X, Wang T, Yang L, Xing E (2018) CIRL: controllable imitative reinforcement learning for vision-based self-driving. In: Ferrari V, Hebert M, Sminchisescu C, Weiss Y (eds) Computer Vision – ECCV 2018. ECCV 2018. Lecture Notes in Computer Science, vol 11211. Springer, Cham pp 604-620
Liu L, Sukhatme GS (2018) A solution to time-varying Markov decision processes. IEEE Robot Autom Lett 3:1631–1638
Ma Y, Kelman A, Daly A, Borrelli F (2012) Predictive control for energy efficient buildings with thermal storage: modeling, stimulation, and experiments. IEEE Control Syst Mag 32:44–64
Müller MA, Allgöwer F (2017) Economic and distributed model predictive control: recent developments in optimization-based control. SICE J Control Meas Syst Integr 10:39–52
Muys M, Sui Y, Schwaiger B, Lesueur B, Vandesheuvel D, Vermeir P, Vlawminck SE (2019) High variability in nutritional value and safety of commercially available Chlorella and Spirulina biomass indicates the need for smart production strategies. Bioresour Technol 275:247–257
Nwoba EG, Parlevliet DA, Laird DW, Alameh K, Moheimani NR (2019) Light management technologies for increasing algal photobioreactor efficiency. Algal Res 39:101433
Ogbonna JC, Tanaka H (2000) Light requirement and photosynthetic cell cultivation -development of processes for efficient light utilization in photobioreactors. J Appl Phycol 12:207–218
Pan X, You Y, Wang Z, Lu C (2017) Virtual to real reinforcement learning for autonomous driving. arXiv 170403952
Paulus R, Xiong C, Socher R (2017) A deep reinforced model for abstractive summarization. arXiv170504304
Rasmussen C.E. (2004) Gaussian processes in machine learning. In: Bousquet O., von Luxburg U., Rätsch G. (eds) Advanced Lectures on Machine Learning. ML 2003. Lecture Notes in Computer Science, vol 3176. Springer, Berlin pp 63–71
Rastogi RP, Madamwar D, Pandey A (2017) Nutraceuticals from algae and cyanobacteria. In: Rastogi RP, Madamwar D, Pandey A (eds) Algal Green Chemistry: Recent Progress in Biotechnology. Elsevier, Amsterdam, pp 66–89
Ravindran B, Gupta SK, Cho W-M, Kim JK, Lee SR, Jeong K-H, Lee DJ, Choi H-C (2016) Microalgae potential and multiple roles-current progress and future prospects-an overview. Sustainability 8:1215
Rostam M, Nagamune R, Grebenyuk V (2020) A hybrid Gaussian process approach to robust economic model predictive control. J Process Control 92:149–160
Salama E-S, Hwang J-H, El-Dalatony MM, Kurade MB, Kabra AN, Abou-Shanab RAI, Kim K-H, Yang I-S, Govindwar SP, Kim S, Jeon B-H (2018) Enhancement of microalgal growth and biocomponent-based transformations for improved biofuel recovery: a review. Bioresour Technol 258:365–375
Schaefer AJ, Bailey MD, Shechter SM, Roberts MS (2005) Modeling medical treatment using Markov decision processes. In: Brandeau ML, Sainfort F, Pierskalla WP (eds). Operations Research and Health Care. I Springer, Boston, pp 593–612
Schütze N, Schmitz GH (2007) Neuro-dynamic programming as a new framework for decision support for deficit irrigation systems. In: International Congress on Modelling and Simulation (ModSim 2007). Christchurch, New Zealand, pp 2271–2277
Song H, Liu C-C, Lawarrée J, Dahlgren RW (2000) Optimal electricity supply bidding by Markov decision process. IEEE Trans Power Syst 15:618–624
Soni RA, Sudhakar K, Rana RS (2017) Spirulina – from growth to nutritional product: a review. Trends Food Sci Technol 69:157–171
Sun L, Yang Y, Hu J, Porter D, Marek T, Hillyer C (2017) Reinforcement learning control for water-efficient agricultural irrigation. In: 2017 IEEE International Symposium on Parallel and Distributed Processing with Applications and 2017 IEEE International Conference on Ubiquitous Computing and Communications (ISPA/IUCC). IEEE, pp 1334–1341
Sutton RS, Barto AG (2018) Reinforcement learning: an introduction. MIT Press, Cambridge
Syafiie S, Tadeo F, Martinez E (2007) Model-free learning control of neutralization processes using reinforcement learning. Eng Appl Artif Intell 20:767–782
Talib A, Recknagel F, Cao H, van der Molen DT (2008) Forecasting and explanation of algal dynamics in two shallow lakes by recurrent artificial neural network and hybrid evolutionary algorithm. Math Comput Simul 78:424–434
Vonshak A (2002) Spirulina: growth, physiology and biochemistry. In: Avigad Vonshak (ed) Spirulina platensis (Arthrospira): Physiology, cell-biology and biotechnology. Taylor&Francis, London pp 43–66
Vu MTT, Douëtte C, Rayner TA, Thoisen C, Nielsen SL, Hansen BW (2016) Optimization of photosynthesis, growth, and biochemical composition of the microalga Rhodomonas salina—an established diet for live feed copepods in aquaculture. J Appl Phycol 28:1485–1500
Walter M, Recknagel F, Carpenter C, Bormans M (2001) Predicting eutrophication effects in the Burrinjuck Reservoir (Australia) by means of the deterministic model SALMO and the recurrent neural network model ANNA. Ecol Model 146:97–113
Wang Y, Alamo T, Puig V, Cembrano G (2018) Economic model predictive control with nonlinear constraint relaxation for the operational management of water distribution networks. Energies 11:991
Watkins CJCH, Dayan P (1992) Q-learning. Mach Learn 8:279–292
Wholesale Electricity Tariff (2018) Access 2018 URL: https://en.evn.com.vn/d6/news/WHOLESALE-ELECTRICITYTARIFF-9-28-260.aspx
Wood AM, Everroad RC, Wingard LM (2005) Measuring growth rates in microalgal cultures. In: Andersen RA (ed) Algal Culturing Techniques. Elsevier, Amsterdam, pp 269–288
Zhi PW, Zhao Y (2005) Morphological reversion of Spirulina (Arthrospira) platensis (Cyanophyta): from linear to helical. J Phycol 41:622–628
Funding
This research is funded by the Hanoi University of Science and Technology (HUST) under grant number T2017-LN-01.
Author information
Authors and Affiliations
Contributions
Doan Thi Thai Yen made substantial contributions to:
• Obtaining of funding
• Conception and design
• Collection and assembly of the data
• Analysis and interpretation of the data
• Drafting of the article
• Critical revision of the article for important intellectual content
• Final approval of the final manuscript
Ho Minh Tri
• Conception and design
• Simulation and performance analysis of the algorithm
• Collection and assembly of the data
• Drafting of the first manuscript
• Final approval of the final manuscript
Nguyen Huu Kim
• Development of the algorithm
• Collection and assembly of the data
• Drafting of the article
• Final approval of the final manuscript
Han Huy Dung
• Conception and design
• Editing and revision of the manuscript
• Final approval of the final manuscript
Doan Thi Thai Yen took overall responsibility for the integrity of the work as a whole, from inception to the finished article.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Doan, Y.TT., Ho, MT., Nguyen, HK. et al. Optimization of Spirulina sp. cultivation using reinforcement learning with state prediction based on LSTM neural network. J Appl Phycol 33, 2733–2744 (2021). https://doi.org/10.1007/s10811-021-02488-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10811-021-02488-y