Digital evolution of bioreactor's trends and frontiers in artificial intelligence/machine learning-driven process intelligence

Abstract

Bioreactors serve as the core of modern bioprocessing, enabling precise control over microbial, enzymatic, and mammalian cell cultures. Yet, their complex dynamics, nonlinear behaviour, and multivariable interactions often limit the effectiveness of traditional modelling and control methods. Recent advancements in artificial intelligence (AI) and machine learning (ML) offer data-driven solutions to enhance modelling accuracy, adaptive control, and real-time optimization. This systematic review investigates the application of AI/ML in bioreactor engineering by examining key bioreactor types, data modalities, algorithmic strategies, control frameworks, and hybrid models. Adhering to PRISMA 2020 guidelines, 58 peer-reviewed articles were selected from five databases—Scopus, IEEE Xplore, ScienceDirect, Scispace, and Google Scholar—using structured Boolean queries. The review highlights the use of algorithms such as artificial neural networks (ANN), support vector machines (SVM), random forests (RF), long short-term memory (LSTM), and reinforcement learning (RL) across batch, fed-batch, continuous, and perfusion systems. Applications include soft sensor development, state estimation, fault diagnosis, and closed-loop control using time-series, sensor, and multi-omics data. Hybrid approaches that fuse mechanistic and AI/ML models—such as grey-box systems, physics-informed neural networks (PINNs), and digital twins—are gaining traction due to their improved generalization and interpretability. Despite these advancements, challenges remain regarding model validation, scalability, and regulatory approval. The review identifies future research directions, including explainable AI, cyber-physical integration, transfer learning, and multi-omics fusion. Overall, AI/ML integration marks a paradigm shift toward intelligent, adaptive, and efficient bioprocess control.

Keywords

Bioreactor / Artificial intelligence / Machine learning / Hybrid modelling / Digital twin / Process optimization

References

[1] Abbasi EY, Deng Z, Ali Q, Khan A, Shaikh A, Reshan MSA, et al.. A machine learning and deep learning-based integrated multi-omics technique for leukemia prediction. Heliyon, 2024, 10(3. ArticleID: e25369

[2] Aburakhia S, Shami A, Karagiannidis GK. On the intersection of signal processing and machine learning a use case-driven analysis approach. arXiv, 2024.

[3] Ajala AA, Adeoye OL, Salami OM, Jimoh AY. An examination of daily CO2 emissions prediction through a comparative analysis of machine learning, deep learning, and statistical models. Environ Sci Pollut Res Int, 2025, 32(5): 2510-2535.

[4] Alhosani K, Alhashmi SM. Opportunities, challenges, and benefits of AI innovation in government services a review. Discov Artif Intell, 2024, 4. ArticleID: 18

[5] Almajed R, Ibrahim A, Abualkishik AZ, Mourad N, Almansour FA. Using machine learning algorithm for detection of cyber-attacks in cyber physical systems. Periodicals of Engineering and Natural Sciences. 2022;10261–75. https://doi.org/10.21533/pen.v10i3.3035

[6] Austerjost J, Söldner R, Edlund C, Trygg J, Pollard D, Sjögren R. A machine vision approach for bioreactor foam sensing. SLAS Technol, 2021, 26: 408-414.

[7] Bejarano LA, Espitia HE, Montenegro CE. Clustering analysis for the pareto optimal front in multi-objective optimization. Computation, 2022.

[8] Biswas SK, Anand NK. Interfacial conditioning in physics informed neural networks. Phys Fluids, 2024, 36. ArticleID: 077125

[9] Bolmanis E, Dubencovs K, Suleiko A, Vanags J. Model predictive control—a stand out among competitors for fed-batch fermentation improvement. Fermentation, 2023, 9. ArticleID: 206

[10] Bonanni D, Litrico M, Ahmed W, Morerio P, Cazzorla T, Spaccapaniccia E, et al.. A deep learning approach to optimize recombinant protein production in Escherichia coli fermentations. Fermentation (Basel), 2023, 9. ArticleID: 503

[11] Cao Y, Hu C, Ma L. Separation of organic compound from water using membrane process hybrid machine learning-based modeling and validation. Case Stud Therm Eng, 2023, 51. ArticleID: 103583

[12] ChaiWY, Teo KTK, Tan MK, Tham HJ. Model predictive control in fermentation process – A review. In. Almaty, Kazakhstan; 2022 [cited 2025 Jun 10]. p. 070008. Available from https://pubs.aip.org/aip/acp/article/2610/1/070008/2830914/Model-predictive-control-in-fermentation-process-A

[13] Chang HM, Xu Y, Chen SS, He Z. Enhanced understanding of osmotic membrane bioreactors through machine learning modeling of water flux and salinity. Sci Total Environ, 2022, 838. ArticleID: 156009

[14] Chen Q, Weigand WA. Adaptive Optimal Operation of a Bioreactor Based on a Neural Net Model. IFAC Proceedings Volumes. 1992;25391–4. https://doi.org/10.1016/S1474-6670(17)50399-7

[15] Cheng Y, Bi X, Xu Y, Liu Y, Li J, Du G, et al.. Artificial intelligence technologies in bioprocess opportunities and challenges. Bioresource Technol, 2023, 369. ArticleID: 128451

[16] DhawasP, Dhore A, Bhagat D, Pawar RD, Kukade A, Kalbande K. Big Data Preprocessing, Techniques, Integration, Transformation, Normalisation, Cleaning, Discretization, and Binning. In Big Data Analytics Techniques for Market Intelligence [Internet]. IGI Global Scientific Publishing; 2024 [cited 2025 Dec 12]. p. 159–82. Available from https://doi.org/10.4018/979-8-3693-0413-6.ch006

[17] DuttaA, De Keyser R, Dutta A, Nopens I. Robust nonlinear extended prediction self-adaptive control (NEPSAC) of continuous bioreactors. In 2012 20th Mediterranean Conference on Control & Automation (MED) [Internet]. Barcelona IEEE; 2012 [cited 2025 Jun 10]. p. 658–64. Available from https://doi.org/10.1109/MED.2012.6265713

[18] Frontistis Z, Lykogiannis G, Sarmpanis A. Artificial neural networks in membrane bioreactors a comprehensive review—overcoming challenges and future perspectives. Science, 2023, 5. ArticleID: 31

[19] Frontistis Z, Lykogiannis G, Sarmpanis A. Machine learning implementation in membrane bioreactor systems progress, challenges, and future perspectives a review. Environments, 2023.

[20] GadkariS. Application of artificial intelligence methods for the optimization and control of bioelectrochemical systems. In Scaling Up of Microbial Electrochemical Systems [Internet]. Elsevier; 2022 [cited 2025 Jun 10]. p. 437–55. Available from https://doi.org/10.1016/B978-0-323-90765-1.00023-X

[21] Gasset A, Van Wijngaarden J, Mirabent F, Sales-Vallverdú A, Garcia-Ortega X, Montesinos-Seguí JL, et al.. Continuous process verification 4.0 application in upstream adaptiveness implementation managed by AI in the hypoxic bioprocess of the Pichia pastoris cell factory. Front Bioeng Biotechnol, 2024.

[22] Goodwin T, Xu J, Celik N, Chen CH. Real-time digital twin-based optimization with predictive simulation learning. J Simul, 2024, 18: 47-64.

[23] Goshisht MK. Machine learning and deep learning in synthetic biology key architectures, applications, and challenges. ACS Omega, 2024, 9(9): 9921-9945.

[24] Hamidi O, Poorolajal J, Sadeghifar M, Abbasi H, Maryanaji Z, Faridi HR, et al.. A comparative study of support vector machines and artificial neural networks for predicting precipitation in Iran. Theor Appl Climatol, 2015, 119: 723-731.

[25] Hana Mamat N, Mohd Noor SB, A/L Ramar L, Che Soh A, Saleena Taip F, Ab. Rashid AH. Artificial neural network model and fuzzy logic control of dissolved oxygen in a bioreactor. IJEECS, 2020, 17. ArticleID: 1289

[26] Helleckes LM, Hemmerich J, Wiechert W, Von Lieres E, Grünberger A. Machine learning in bioprocess development from promise to practice. Trends Biotechnol, 2023, 41: 817-835.

[27] Hernández-del-Olmo F, Gaudioso E, Duro N, Dormido R, Gorrotxategi M. Advanced control by reinforcement learning for wastewater treatment plants a comparison with traditional approaches. Appl Sci, 2023, 13. ArticleID: 4752

[28] Himmel A, Matschek J, Kok R, Morabito B, Nguyen HH, Findeisen R. Machine learning for process control of (bio)chemical processes. arXiv, 2023.

[29] HimmelA, Matschek J, Kok (Louis) R, Morabito B, Nguyen HH, Findeisen R. Machine learning for control of (bio)chemical manufacturing systems. In Artificial Intelligence in Manufacturing [Internet]. Elsevier; 2024 [cited 2025 Jun 10]. p. 181–240. Available from https://doi.org/10.1016/B978-0-323-99134-6.00009-8

[30] Hosamo HH, Nielsen HK, Alnmr AN, Svennevig PR, Svidt K. A review of the digital twin technology for fault detection in buildings. Front Built Environ, 2022.

[31] Ibrahim S, Abdul Wahab N. Optimizing neural network algorithms for submerged membrane bioreactor a comparative study of OVAT and RSM hyperparameter optimization techniques. Water Sci Technol, 2024, 89: 1701-1724.

[32] Imamoglu E. Artificial intelligence and/or machine learning algorithms in microalgae bioprocesses. Bioengineering, 2024, 11(11. ArticleID: 1143

[33] Juárez Barojas I, Posada-Gómez R, Alvarado-Lassman A, Rodríguez-Jarquín J. Condition-based maintenance of an anaerobic reactor using artificial intelligence. Electronics (Basel), 2023.

[34] Khan SA, Engelbrecht AP. A fuzzy particle swarm optimization algorithm for computer communication network topology design. Appl Intell, 2012, 36: 161-177.

[35] Khanam R, Hussain M, Hill R, Allen P. A comprehensive review of convolutional neural networks for defect detection in industrial applications. IEEE Access, 2024, 12. ArticleID: 94250–95

[36] KimD, Wang K, Sclaroff S, Saenko K. A Broad Study of Pre-training for Domain Generalization and Adaptation [Internet]. arXiv; 2022 [cited 2025 Dec 15]. Available from https://doi.org/10.48550/arXiv.2203.11819

[37] Kusterer A, Krause C, Kaufmann K, Arnold M, Weuster-Botz D. Fully automated single-use stirred-tank bioreactors for parallel microbial cultivations. Bioprocess Biosyst Eng, 2008, 31(3): 207-215.

[38] Li H, Qiu T, You F. AI-based optimal control of fed-batch biopharmaceutical process leveraging deep reinforcement learning. Chem Eng Sci, 2024, 292. ArticleID: 119990

[39] Liu C, Gong Z, Feng E, Yin H. Nonlinear dynamical systems of fed-batch fermentation and their optimal control. Int J Syst Sci, 2012, 43: 809-819.

[40] Liu D, Chang L, Koenig R. Comparative classification of twin architectures. Manuf Syst & AI, 2022, 7: 181-192

[41] Liu Y, Tian W, Xie J, Huang W, Xin K. LSTM-based model-predictive control with rationality verification for bioreactors in wastewater treatment. Water, 2023, 15. ArticleID: 1779

[42] Miletic M, Sariyar M. Challenges of using synthetic data generation methods for tabular microdata. Appl Sci Basel, 2024, 14. ArticleID: 5975

[43] Mitra S, Murthy GS. Bioreactor control systems in the biopharmaceutical industry a critical perspective. Syst Microbiol Biomanuf, 2022, 2: 91-112.

[44] Morabito B, Pohlodek J, Kranert L, Espinel-Ríos S, Findeisen R. Efficient and simple gaussian process supported stochastic model predictive control for bioreactors using HILO-MPC. IFAC-PapersOnLine, 2022, 55: 922-927.

[45] Morabito B, Pohlodek J, Kranert L, Espinel-Ríos S, Findeisen R. Efficient and simple Gaussian process supported stochastic model predictive control for bioreactors using HILO-MPC. IFAC-PapersOnLine, 2022, 55. ArticleID: 922–7

[46] Mowbray M, Savage T, Wu C, Song Z, Cho BA, Del Rio-Chanona EA, et al.. Machine learning for biochemical engineering a review. Biochem Eng J, 2021, 172. ArticleID: 108054

[47] Muhuri P, Chatterjee P, Yuan X, Roy K, Esterline A. Using a long short-term memory recurrent neural network (LSTM-RNN) to classify network attacks. Information (Basel), 2020, 11. ArticleID: 243

[48] Nasimi R, Azadi S, Jazaeri M, Farzinfar M. Nonlinear model-based predictive control of a yeast fermentation bioreactor using new bee colony-WNN modelling structure. Journal of Engineering Research. 2024;S2307187724001809. https://doi.org/10.1016/j.jer.2024.06.011

[49] Nikita S, Mishra S, Gupta K, Runkana V, Gomes J, Rathore AS. Advances in bioreactor control for production of biotherapeutic products. Biotechnol Bioeng, 2023, 120: 1189-1214.

[50] Nokhbatolfoghahaei H, Bohlouli M, Paknejad Z, R. Rad M, M. Amirabad L, Salehi-Nik N, et al.. Bioreactor cultivation condition for engineered bone tissue effect of various bioreactor designs on extra cellular matrix synthesis. J Biomed Mater Res A, 2020, 108: 1662-1672.

[51] Oh TH, Park HM, Kim JW, Lee JM. Integration of reinforcement learning and model predictive control to optimize semi‐batch bioreactor. AIChE J, 2022, 68. ArticleID: e17658

[52] Pandey AK, Nayak SC, Kim SH. Functional link hybrid artificial neural network for predicting continuous biohydrogen production in dynamic membrane bioreactor. Bioresour Technol, 2024, 397. ArticleID: 130496

[53] Panjwani S, Almazan A, Wei H, Spetsieris K. A comparative evaluation of the enhanced PLS-Tree algorithm with multiple latent score vectors. J Adv Manuf Process, 2025, 7. ArticleID: e70004

[54] Parameshwar Reddy K, Vinod Kumar K, Sai Surya Mounika D. Integrating AI and machine learning in quality assurance for automation engineering. JRPS, 2024, 15: 93-102.

[55] Parthiban S, Vijeesh T, Gayathri T, Shanmugaraj B, Sharma A, Sathishkumar R. Artificial intelligence-driven systems engineering for next-generation plant-derived biopharmaceuticals. Front Plant Sci, 2023, 14. ArticleID: 1252166

[56] Peres J, Oliveira R, Serafim LS, Lemos P, Reis MA, Feyo De Azevedo S. Hybrid Modelling of a PHA Production Process Using Modular Neural Networks. In Computer Aided Chemical Engineering [Internet]. Elsevier; 2004 [cited 2025 Jun 10]. p. 733–8. Available from https://doi.org/10.1016/S1570-7946(04)80188-3 https://www.academia.edu/165074333/Hybrid_Modelling_of_a_PHA_Production_Process_Using_Modular_Neural_Networks

[57] Petsagkourakis P, Sandoval IO, Bradford E, Zhang D, del Rio-Chanona EA. Reinforcement learning for batch bioprocess optimization. Comput Chem Eng, 2020, 133. ArticleID: 106649

[58] Pinto J, Mestre M, Costa RS, Striedner G, Oliveira R. A general deep hybrid model for bioreactor systems combining first Principles equations with deep neural networks [Internet]. Systems Biology; 2022 [cited 2025 Jun 10]. Available from http//biorxiv.org/lookup/doi/https://doi.org/10.1101/2022.06.07.495118

[59] Rahimzadeh A, Ranjbarrad S, Ein-Mozaffari F, Lohi A. Application of machine learning models in coaxial bioreactors classification and torque prediction. ChemEngineering, 2024.

[60] Rajasekhar N, Radhakrishnan TK, Mohamed SN. Reinforcement learning based temperature control of a fermentation bioreactor for ethanol production. Biotechnol Bioeng, 2024, 121: 3114-3127.

[61] Rajulapati L, Sivadurgaprasad C, Shyamala B, Rengaswamy R. Integration of machine learning and first principles models. AIChE J, 2022.

[62] Rana M, Sall S, Sagvekar V, Gaiwad V, Gaikwad U, Patil P, et al.. Obstacles to the full realization and adoption of artificial intelligence (AI). South East Eur J Public Health, 2024, 10: 03-16.

[63] Rashedi M, Khodabandehlou H, Demers M, Wang T, Garvin C. Model predictive controller design for bioprocesses based on machine learning algorithms. IFAC-PapersOnLine, 2022, 55: 45-50.

[64] Rashedi M, Rafiei M, Demers M, Khodabandehlou H, Wang T, Tulsyan A, et al.. Machine learning‐based model predictive controller design for cell culture processes. Biotech Bioeng, 2023, 120: 2144-2159.

[65] Rathore AS, Mishra S, Nikita S, Priyanka P. Bioprocess control current progress and future perspectives. Life, 2021, 11. ArticleID: 557

[66] Rodríguez-Roda I, Comas J, Monclús H, Sipma J, Poch M. Intelligent Environmental Decision Support System for integrated operation of Membrane Bioreactors.

[67] Rutland H, You J, Liu H, Bull L, Reynolds D. A systematic review of machine-learning solutions in anaerobic digestion. Bioengineering, 2023, 10. ArticleID: 1410

[68] Sahu S, Kaur A, Singh G, Kumar Arya S. Harnessing the potential of microalgae-bacteria interaction for eco-friendly wastewater treatment a review on new strategies involving machine learning and artificial intelligence. J Environ Manage, 2023, 346. ArticleID: 119004

[69] SarnaS, Patel N, Mhaskar P, Corbett B, McCready C. Data Driven Modeling and Model Predictive Control of Bioreactor for Production of Monoclonal Antibodies. In 2022 American Control Conference (ACC) [Internet]. Atlanta, GA, USA IEEE; 2022 [cited 2025 Jun 10]. p. 1347–52. Available from https://doi.org/10.23919/ACC53348.2022.9867419

[70] Schlögel G, Lück R, Kittler S, Spadiut O, Kopp J, Zanghellini J, et al.. Optimizing bioprocessing efficiency with OptFed dynamic nonlinear modeling improves product-to-biomass yield. Comput Struct Biotechnol J, 2024, 23: 3651-3661.

[71] Singh NK, Yadav M, Singh V, Padhiyar H, Kumar V, Bhatia SK, et al.. Artificial intelligence and machine learning-based monitoring and design of biological wastewater treatment systems. Bioresource Technol, 2023, 369. ArticleID: 128486

[72] Singh VK, Jiménez Del Val I, Glassey J, Kavousi F. Integration approaches to model bioreactor hydrodynamics and cellular kinetics for advancing bioprocess optimisation. Bioengineering, 2024, 11. ArticleID: 546

[73] Theriault-Lauzier P, Corbin D, Tastet O, Langlais EL, Taji B, Kang G, et al.. A responsible framework for applying artificial intelligence on medical images and signals at the point of care The PACS-AI Platform. Can J Cardiol, 2024.

[74] TziolasT, Papageorgiou K, Theodosiou T, Papageorgiou E, Mastos T, Papadopoulos A. Autoencoders for Anomaly Detection in an Industrial Multivariate Time Series Dataset. In The 8th International Conference on Time Series and Forecasting [Internet]. MDPI; 2022 [cited 2025 Dec 12]. p. 23. Available from https://doi.org/10.3390/engproc2022018023

[75] Vaitkus V, Brazauskas K, Repšytė J. Soft-sensors based on Black-box Models for Bioreactors Monitoring and State Estimation. In Proceedings of the 2020 12th International Conference on Bioinformatics and Biomedical Technology [Internet]. Xi’an China ACM; 2020 [cited 2025 Jun 10]. p. 43–7. Available from https://doi.org/10.1145/3405758.3405780

[76] Valente E, Rocha I, Rocha M. Modelling Fed-Batch Fermentation Processes An Approach Based on Artificial Neural Networks. In Corchado JM, Paz JF, Rocha MP, Fernández Riverola F, editors. 2nd International Workshop on Practical Applications of Computational Biology and Bioinformatics (IWPACBB 2008) [Internet]. Berlin, Heidelberg Springer Berlin Heidelberg; 2009 [cited 2025 Jun 10]. p. 30–9. (Advances in Soft Computing). Available from https://doi.org/10.1007/978-3-540-85861-4_4

[77] Vekaria D, Sinha S. aiWATERS an artificial intelligence framework for the water sector. AI Civ Eng, 2024.

[78] Wang T, Li YY. Predictive modeling based on artificial neural networks for membrane fouling in a large pilot-scale anaerobic membrane bioreactor for treating real municipal wastewater. Sci Total Environ, 2024, 912. ArticleID: 169164

[79] Wang B, Wang Z, Chen T, Zhao X. Development of novel bioreactor control systems based on smart sensors and actuators. Front Bioeng Biotechnol, 2020, 8. ArticleID: 7

[80] Wang C. Research on Intelligent Real time Monitoring System based on Neural Network Optimization. In 2022 Sixth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC) [Internet]. Dharan, Nepal IEEE; 2022 [cited 2025 Jun 10]. p. 646–9. Available from https://doi.org/10.1109/I-SMAC55078.2022.9987336

[81] Yang N, Guerin C, Kokanyan N, Perré P. In-line monitoring of bioreactor by Raman spectroscopy direct use of a standard-based model through cell-scattering correction. J Biotechnol, 2024, 396: 41-52.

[82] Zarzycki K, Ławryńczuk M. Long short-term memory neural networks for modeling dynamical processes and predictive control a hybrid physics-informed approach. Sensors Basel, 2023, 23. ArticleID: 8898

[83] Zhang Z, Wu Z, Rincon D, Christofides P. Real-time optimization and control of nonlinear processes using machine learning. Mathematics (Basel), 2019, 7. ArticleID: 890

[84] Zhao X, Sun Y, Li Y, Jia N, Xu J. Applications of machine learning in real-time control systems a review. Meas Sci Technol, 2025, 36. ArticleID: 012003

RIGHTS & PERMISSIONS

Jiangnan University