Explainable AI (XAI) for Industrial Catalysis: Interpretable Machine Learning for Catalyst Design, Optimization, and Process Efficiency

Dear Colleagues,

Artificial intelligence (AI), particularly machine learning, is rapidly transforming industrial catalysis by enabling data-driven modeling, catalyst screening, reaction pathway analysis, and process optimization. These technologies offer significant advantages in terms of speed, scalability, and cost-effectiveness over conventional trial-and-error or first-principle approaches. However, one of the critical barriers to the widespread adoption of AI in industrial contexts is the lack of interpretability, often referred to as the "black-box" nature of many machine learning models.

In industrial catalysis, where safety, efficiency, regulatory compliance, and scientific credibility are paramount, model transparency is not optional, it is essential. Explainable artificial intelligence (XAI) addresses this challenge by providing insights into how models make predictions, identifying key features driving catalyst behavior, and enabling researchers and engineers to trust and validate AI-derived conclusions. XAI techniques such as SHAP (SHapley Additive exPlanations), LIME (Local Interpretable Model-agnostic Explanations), and surrogate models are increasingly being used to interpret machine learning outputs in meaningful physical and chemical terms.

This Special Issue aims to highlight the growing impact of XAI in industrial catalytic systems, from heterogeneous and homogeneous catalysts to electrocatalysts and process-integrated systems. We invite original research articles, reviews, and case studies that showcase how XAI contributes to the understanding, design, screening, performance prediction, and optimization of catalysts and catalytic processes. Contributions that bridge the gap between data science and chemical engineering, or that combine XAI with computational chemistry, kinetic modeling, or process simulation, are especially encouraged. Topics of Interest include (but are not limited to):

• XAI-guided design and optimization of industrial catalysts;
• Interpretable ML models for process intensification and scale-up;
• SHAP, LIME, and other XAI tools in catalyst performance analysis;
• XAI applications in petrochemical, refinery, fine chemical, or environmental catalysis;
• Integration of XAI with process simulation, DFT, or kinetic modeling;
• Case studies of XAI for catalyst lifetime prediction, deactivation analysis, or regeneration;
• Human-in-the-loop AI for catalyst development and deployment;
• Visualization and interpretation of AI-derived structure–activity relationships.

This Special Issue will serve as a cross-disciplinary platform for researchers and practitioners to share innovations at the intersection of industrial catalysis and explainable machine learning. It aims to promote trustworthy, interpretable, and industry-ready AI tools that accelerate catalyst development while preserving scientific insight and operational safety.

Prof. Dr. Nagireddy Gari Subba Reddy
Guest Editor

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. Catalysts 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 2200 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.

• explainable artificial intelligence (XAI)
• industrial catalysis
• interpretable machine learning
• catalyst design and optimization
• SHAP and LIME in catalysis
• data-driven process engineering
• catalyst performance prediction
• AI-enhanced reaction mechanisms
• process intensification
• AI in petrochemical and chemical industries