Closed-loop photoreactor design enabled by machine learning and digital twins
Abstract
Designing efficient photoreactors remains challenging due to the complex interplay of reflection, scattering, and absorption. Here, we introduce a closed-loop workflow integrating ray-tracing digital twins with multi-objective Bayesian optimization to design photoreactors with high photon capture and uniform irradiation. A digital 3D reactor model is calibrated using measured emission characteristics, reflectivity data, and geometrical properties and validated against potassium ferrioxalate actinometry. The validated model explores reflector shape and vial positioning, identifying geometries that maximize incident photon flux while maintaining homogeneity across 16 vials. Experimental validation using a photocatalytic Suzuki–Miyaura cross-coupling shows that reaction yields track simulated photon flux. The optimized reactor is further applied to quantum-yield screening, enabling mechanistic insights across diverse conditions in a single experiment. This work establishes an experimentally validated virtual co-design framework in which machine learning and digital twins accelerate photoreactor development and support quantitative understanding of photochemical processes.
Versions
Related
- Computational Fluid Dynamics-Informed Machine Learning-Enabled Digital Twin for Vapor Maldistribution Prediction in Structured Packed Distillation Columns
- Interpretable Machine Learning in Food Analysis: Closed-Form Chemometric Calibration of Mid- and Near-Infrared Spectra Using Kolmogorov-Arnold Networks.
- Corrosion Prediction of AZ31 Mg Alloy Using Machine Learning and Digital Smartphone Images
- E → Z Photoisomerization of Cinnamamides Using a Mixed-Solvent System in a Recycling Photoreactor
- Digital and technology‑enabled approaches for post‑stroke fatigue: A scoping review protocol
BibTeX
@article{schuurmans2026closedloop,
title = {{Closed-loop photoreactor design enabled by machine learning and digital twins}},
author = {Jasper H. A. Schuurmans and Miguel Claros and Elia Savino and Florian Lukas and Aidan Slattery and Timothy Noël},
journal = {Nature Communications},
year = {2026},
month = oct,
doi = {10.1038/s41467-026-78785-2},
url = {https://www.nature.com/articles/s41467-026-78785-2},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Closed-loop photoreactor design enabled by machine learning and digital twins
AU - Jasper H. A. Schuurmans
AU - Miguel Claros
AU - Elia Savino
AU - Florian Lukas
AU - Aidan Slattery
AU - Timothy Noël
PY - 2026
DA - 2026/10/19
JO - Nature Communications
DO - 10.1038/s41467-026-78785-2
UR - https://www.nature.com/articles/s41467-026-78785-2
AB - Designing efficient photoreactors remains challenging due to the complex interplay of reflection, scattering, and absorption. Here, we introduce a closed-loop workflow integrating ray-tracing digital twins with multi-objective Bayesian optimization to design photoreactors with high photon capture and uniform irradiation. A digital 3D reactor model is calibrated using measured emission characteristics, reflectivity data, and geometrical properties and validated against potassium ferrioxalate actinometry. The validated model explores reflector shape and vial positioning, identifying geometries that maximize incident photon flux while maintaining homogeneity across 16 vials. Experimental validation using a photocatalytic Suzuki–Miyaura cross-coupling shows that reaction yields track simulated photon flux. The optimized reactor is further applied to quantum-yield screening, enabling mechanistic insights across diverse conditions in a single experiment. This work establishes an experimentally validated virtual co-design framework in which machine learning and digital twins accelerate photoreactor development and support quantitative understanding of photochemical processes.
SN - 2041-1723
ER -