CoChat
Sign Up
Cited by 14Reinforcement Learning in RoboticsAdaptive Dynamic Programming ControlAdvanced Control Systems Optimization

The DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.

Reinforcement learning meets bioprocess control through behavior cloning: Real-world deployment in an industrial photobioreactor

Open access
Gil, Juan D., Del Rio Chanona, Ehecatl Antonio, Guzmán, José L., Berenguel, Manuel·2026·Engineering Applications of Artificial Intelligence
DOI 10.1016/j.engappai.2025.113326
Open this paper in CoChat — free account

Abstract

The complexity of living cells as production units creates major challenges for maintaining optimal bioprocess conditions, especially in open Photobioreactors (PBRs) exposed to fluctuating environments. To address this, we propose a Reinforcement Learning (RL) controller for pH regulation in open PBR systems. This work represents, to the best of our knowledge, the first industrial validation of an RL-based control strategy in a bioprocess. Our method begins with an offline training stage in which the RL agent learns from trajectories generated by a nominal Proportional–Integral–Derivative (PID) controller, without direct interaction with the real system. This is followed by deployment, where the RL agent acts and collects data during the day and is fine-tuned every night, enabling adaptation to evolving process dynamics and stronger rejection of fast, transient disturbances. This continual policy adaptation allows the offline-trained RL to effectively handle the inherent nonlinearities and external disturbances in open PBRs. Simulation studies highlight the advantages of our method: the Integral of Absolute Error (IAE) was reduced by 8% compared to PID control, 6% relative to a classical Model Predictive Controller (MPC), and 5% relative to a standard off-policy RL. Moreover, control effort decreased substantially—by 54% compared to PID, 11% compared to MPC, and 7% compared to the standard off-policy RL. Finally, an 8-day experimental validation under varying environmental co…

Overview

Integrity signals

Registry

Crossref · 10.1016/j.engappai.2025.113326

Cites

36 of 36 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Even with the support of digital tools, environmental and nutritional factors such as temperature, pH, nitrogen and phosphorus balance, and availability of inorganic and organic carbon continue to be decisive for productivity, requiring continuous monitoring and increasingly sophisticated control strategies.

    “Moreover, even with the support of digital tools, environmental and nutritional factors—such as temperature, pH, nitrogen and phosphorus balance, as well as the availability of inorganic and organic carbon—continue to be decisive for productivity, requiring continuous monitoring and increasingly sophisticated control strategies (Gil et al., 2025; Soon et al., 2025).”

    From Microalgae biotechnology and its role in sustainable and healthy food design (2025) · cites this paper as Gil et al., 2025

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 7

  1. Castilla, 2025, Reinforcement learning based thermal comfort control in a bioclimatic building, Rev. Iberoamericana Automát. Inform. Ind. (RIAI), 22, 146
  2. Guzmán, 2021, Modelling and control of microalgae production in industrial photobioreactors, Rev. Iberoamericana Autom. Inform. Ind. (RIAI), 18, 1
  3. Isiramen, 2022, Improving pH control and carbon dioxide utilisation efficiency in microalgae cultivation systems with the use of a proportional-integral+ dead-zone control strategy, Bioresour. Technol. Rep., 17
  4. 2026, Learning to control inexact benders decomposition via reinforcement learning, Comput. Chem. Eng., 205
  5. Park, 2025, Real-world implementation of offline reinforcement learning for process control in industrial dividing wall column, Comput. Chem. Eng.
  6. Rajasekhar, 2025, Exploring reinforcement learning in process control: A comprehensive survey, Int. J. Syst. Sci., 1
  7. Wang, H., Kontoravdi, C., Del Rio Chanona, E.A., 2025. Offline Reinforcement Learning for Bioprocess Optimization with Historical Data. In: 14th IFAC Symposium on Dynamics and Control of Process Systems, Including Biosystems (DYCOPS 2025): Slovakia, Bratislava, June 16-19, 2025.

Cited by

Sorted by citations

Related

Metadata

Authors
Gil, J. D., Del Rio Chanona, E. A., Guzmán, J. L., & Berenguel, M.
Affiliations
University of Almería (ES)
Corresponding author
Gil, Juan D.
ORCID
Venue
Engineering Applications of Artificial Intelligence
Publisher
Elsevier BV
Published
2026-01
Volume
164
Pages
113326
ISSN
0952-1976 (ISSN-L)
DOI
10.1016/j.engappai.2025.113326
OpenAlex
W4416851358
Cited by
13
References
36
Citations by year
2026: 13
FWCI
5.15
Type
journal article
Language
en
Open access
Licence
Locations
Engineering Applications of Artificial Intelligence (publishedVersion, cc-by-nc-nd)
Funders
  • Universidad de Almería
  • European Regional Development Fund
  • Horizon 2020 (101060991)
  • European Commission
  • Government of Spain Ministry of Science, Innovation and Universities
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
  • Physical Sciences › Engineering › Control and Systems Engineering › Adaptive Dynamic Programming Control
  • Physical Sciences › Engineering › Control and Systems Engineering › Advanced Control Systems Optimization
Keywords
reinforcement learning, bioprocess control, photobioreactors, pH control, behavior cloning, offline training, PID controller, industrial deployment, disturbance rejection, nonlinear control, model predictive control

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review