Artificial Intelligence Across Chemical Engineering: From Data-Driven Models to Safe, Sustainable Process Decisions

Artificial intelligence, machine learning and other data-driven methods have become increasingly important across chemical engineering, with applications ranging from molecular and reaction modeling to process optimization, control, digital twins, sustainable manufacturing, and environmental solutions, from water to waste management. However, the field has developed rapidly, and many applications now require a closer connection between computational methods and specific engineering, environmental, and industrial challenges. Robust validation, physical consistency, interpretability, safety, and scale-up are becoming as important as algorithmic performance.This Research Topic will explore how artificial intelligence can generate practical solutions to major challenges across chemical and environmental engineering, rather than create new problems through opacity, overfitting, or disconnection from process physics. Traditional mechanistic modeling and simulation are increasingly being complemented by data-driven and AI approaches, including hybrid and physics-informed strategies, which must deliver consistent, reliable, and reproducible results. We welcome contributions that demonstrate how AI can support reaction engineering, catalysis, separations, bioprocessing, advanced materials synthesis, and the treatment of water and waste.Emphasis is placed on safer and more sustainable processes, improved resource recovery, efficient manufacturing, and reliable decision-making in the transition toward a circular economy, a paradigm where chemical engineering plays a central role. The collection connects researchers developing computational methodologies with domain experts in the experimental, environmental, and industrial fields where these solutions are deployed.We welcome Original Research, Review, Perspective, and Methods articles. Themes of interest include, but are not limited to:• AI for reaction engineering and catalysis• Separation processes and membranes• Environmental engineering and waste valorization• Biochemical processes and biomanufacturing• Electrochemical systems• Process control and optimization• Digital twins and smart manufacturing• Hybrid and physics-informed models• Explainable and trustworthy AI, and uncertainty quantification• Process safety, life-cycle assessment, and techno-economic analysisContributions should demonstrate:• Clear chemical-engineering value• Rigorous validation and, where relevant, physical consistency• Reproducibility• Sustainability and potential transfer to industrial or environmental systems Topic editors: Antoni Sánchez, Edgar Ricardo Oviedo-Ocaña, Fengqi You, Seyed Soheil Mansouri Source: https://www.frontiersin.org/research-topics/87104/artificial-intelligence-across-chemical-engineering-from-data-driven-models-to-safe-sustainable-process-decisions