A Comprehensive Review of Machine Learning Applications in Liquid-Based Cooling Solutions of PV/T Systems

Aug 4, 2026

This paper provides a systematic review of machine learning (ML) applications in liquid-based photovoltaic-thermal (PV/T) systems, addressing a gap in prior review literature despite the growing relevance of these hybrid renewables. Seventy-two publications are classified into three methodological families: artificial neural networks (ANNs), ensemble methods, and other ML techniques. The review is augmented with a patent landscape for liquid-based PV/T technologies and an evaluation of the experimental basis used to build the reviewed ML models. Results show ANNs lead PV/T modeling (63%), while ensemble models such as Random Forest and XGBoost reach the highest accuracies (R² up to 0.999), and most studies report R² above 0.95.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages58

Reading Time2 h 26 min

AccessFree to download

Introduction

Machine learning applications in PV/T systems

Methodological families and publication set

Patent landscape and experimental validation

Journal Pre-proofs A comprehensive review of machine learning applications in liquid-based cooling solutions of PV/T systems Krzysztof Rajski, Mirosław Żukowski, Alina Żabnieńska-Góra, Hussam Jouhara PII: S2451-9049(26)00154-X DOI: [https://doi.org/10.1016/j.tsep.2026.104628](https://doi.org/10.1016/j.tsep.2026.104628) Reference: TSEP 104628 To appear in: Thermal Science and Engineering Progress Received Date: 4 November 2025 Revised Date: 23 February 2026 Accepted Date: 7 March 2026 Please cite this article as: K. Rajski, M. Żukowski, A. Żabnieńska-Góra, H. Jouhara, A comprehensive review of machine learning applications in liquid-based cooling solutions of PV/T systems, Thermal Science and Engineering Progress (2026), doi: [https://doi.org/10.1016/j.tsep.2026.104628](https://doi.org/10.1016/j.tsep.2026.104628) This is a PDF of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability. This version will undergo additional copyediting, typesetting and review before it is published in its final form. As such, this version is no longer the Accepted Manuscript, but it is not yet the definitive Version of Record; we are providing this early version to give early visibility of the article. Please note that Elsevier's sharing policy for the Published Journal Article applies to this version, see: [https://www.elsevier.com/about/policies-and-standards/sharing\#4-published-journal-article](https://www.elsevier.com/about/policies-and-standards/sharing#4-published-journal-article. Please)[. Please](https://www.elsevier.com/about/policies-and-standards/sharing#4-published-journal-article. Please) also note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain. © 2026 The Author(s). Published by Elsevier Ltd. Title: A Comprehensive Review of Machine Learning Applications in Liquid-Based cooling solutions of PV/T Systems Authors: Krzysztof Rajski a, *, Mirosław Żukowski b, Alina Żabnieńska-Góra a, Hussam Jouhara c,d Affiliations for all authors: a Faculty of Environmental Engineering, Wrocław University of Science and Technology, 27 Wybrzeże Stanisława Wyspiańskiego st., 50-377, Wrocław, Poland b Department of HVAC Engineering, Faculty of Civil Engineering and Environmental Sciences, Białystok University of Technology, Wiejska 45E Street, 15-351, Białystok, Poland c Heat Pipe and Thermal Management Research Group, College of Engineering, Design and Physical Sciences, Brunel University, London UB8 3PH, UK d Vytautas Magnus University, Studentu Str. 11, LT-53362 Akademija, Kaunas Distr., Lithuania * Author [to whom correspondence should be addressed: krzysztof.rajski@pwr.edu.pl](to whom correspondence should be addressed: krzysztof.rajski@pwr.edu.pl) [A Comprehensive Review of Machine Learning Applications in Liquid-Based cooling](A Comprehensive Review of Machine Learning Applications in Liquid-Based cooling)[ ](A Comprehensive Review of Machine Learning Applications in Liquid-Based cooling)[solutions of PV/T Systems](solutions of PV/T Systems) Abstract: This paper presents a systematic review of machine learning (ML) applications in liquid-based photovoltaic-thermal (PV/T) systems, a topic that remains largely unaddressed in the existing review literature despite the growing importance of these hybrid systems in renewable energy. A total of 72 publications are analyzed and categorized across three methodological families: artificial neural networks (ANNs), ensemble methods, and other ML techniques. The review is complemented by a patent landscape analysis covering liquid-based PV/T technologies and a critical assessment of the experimental foundations underlying the reviewed ML models. The analysis reveals that ANNs dominate PV/T modeling at 63% of reviewed studies, with Multilayer Perceptron being the most freque

FAQs

What scope does the review cover for liquid-based PV/T systems?

It systematically reviews machine learning applications for liquid-based photovoltaic-thermal (PV/T) systems, focusing on how models are built and assessed and how they address thermal-electrical coupling.

How are the reviewed ML methods grouped?

The review categorizes 72 publications into three methodological families: artificial neural networks (ANNs), ensemble methods, and other ML techniques.

What key trends and performance findings are reported?

ANNs dominate PV/T modeling (63%), while ensemble methods like Random Forest and XGBoost deliver the highest prediction accuracies, with reported R² values reaching 0.999 in some studies.

Aug 4, 2026

Upload by Valentina