Machine Learning-Driven Kinetic Modeling in Chemical- and Energy-Related Processes

Dear Colleagues,

Machine learning (ML) is transforming the landscape of kinetic modeling in chemical- and energy-related processes by introducing data-driven, adaptive methodologies capable of capturing intricate reaction dynamics. Traditional kinetic modeling approaches, which often rely heavily on detailed mechanistic understanding and extensive experimental datasets, face limitations when applied to systems characterized by nonlinear behaviors, multi-scale interactions, or incomplete knowledge. In contrast, ML techniques, such as decision trees, support vector machines (SVMs), random forests, and artificial neural networks (ANNs), enable the development of predictive models directly from empirical data, supporting a bottom–up modeling paradigm that reduces dependency on predefined theoretical assumptions.

This Special Issue aims to showcase cutting-edge advances in ML-based kinetic modeling, with a particular focus on the following topics:

• Bottom–up data-driven modeling strategies that extract mechanistic insights from experimental, industrial, or simulated datasets.
• Applications such as catalysis, combustion systems, electrochemistry, and reaction engineering, where traditional modeling techniques struggle with complexity or uncertainty.
• Real-time integration of ML models with digital twins, sensor networks, and process control systems to enable adaptive, scalable, and efficient process operation.

Key challenges in this field include ensuring the physical interpretability of ML models, addressing data sparsity or noise in experimental datasets, and enhancing model generalizability across different systems or operating conditions. The black-box nature of many ML algorithms also raises concerns about trust and transparency in critical applications.

Emerging research directions include hybrid modeling approaches that combine ML with first-principles knowledge, physics-informed machine learning, active learning for data-efficient model training, and uncertainty quantification to improve model robustness.

Looking forward, ML-driven kinetic modeling holds immense potential to accelerate innovation in chemical engineering and energy systems, enabling smarter experimentation, closed-loop optimization, and the development of autonomous systems with minimal human intervention. The aim of this Special Issue is to highlight recent innovations in machine learning-based kinetic modeling, emphasizing data-driven and bottom–up approaches that improve predictive accuracy, computational efficiency, and process adaptability across chemical- and energy-related domains.

Dr. Yong Sun
Dr. Kien Woh Kow
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Eng is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1200 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• data-driven
• machine learning
• bottom–up approach
• decision tree
• support vector machine
• artificial neural networks
• kinetic modeling
• chemical processes
• energy systems
• predictive modeling