AI-Enabled Decision-Making and Optimization for Sustainable Chemical and Process Engineering

The field of chemical and process engineering is undergoing a transformation driven by digitalization and the push towards sustainability. Engineers today face the challenge of designing processes that are economically feasible, resource‑efficient, and environmentally responsible, all at once. Traditional single‑objective optimization tools are no longer sufficient to capture the multi‑dimensional nature of these competing objectives. Recent advances in multi‑objective optimization, artificial intelligence (AI), and multi‑criteria decision‑making (MCDM) are opening exciting possibilities to address this complexity. Machine learning models have evolved as powerful surrogates for costly simulations, while Pareto‑based frameworks now enable more transparent negotiation of trade‑offs among technical, economic, and ecological priorities. However, despite these advances, key questions remain regarding model interpretability, data reliability, and the workflow integration of AI‑driven methods into large‑scale process design and operation. This gap highlights the need for stronger links between computational tools and their engineering applications to achieve truly sustainable process solutions.This Research Topic aims to foster the integration of AI and decision‑support frameworks into sustainable process systems engineering. It seeks contributions that explore new algorithmic developments, hybrid data‑driven and mechanistic models, and decision‑analysis approaches that enhance the robustness, interpretability, and real‑world usability of optimization results. The goal is to generate cross‑disciplinary insights on how AI, multi‑objective optimization, and MCDM can jointly drive innovation in process design, control, and sustainability assessment. Studies presenting novel theoretical advances, methodological comparisons, or practical industrial applications will equally be valued.To gather further insights into this rapidly evolving area, we welcome contributions that focus on the intersection of computational intelligence and process systems engineering. The collection primarily targets research within the Computational Methods in Chemical Engineering section and will host both method‑ and application‑driven papers. Themes may include, but are not limited to:• Machine learning–aided surrogate modeling and multi‑objective optimization• MCDM methods applied to process design, sustainability assessment, and technology selection• AI‑driven optimization for sustainable chemical manufacturing• Data‑driven approaches to energy minimization, waste reduction, and emissions control• Optimization under uncertainty, including robust and stochastic frameworks• Digital‑twin integration for real‑time decision support and monitoring• Case studies combining process simulation, optimization, and systematic decision analysis• Environmental, social, and governance (ESG) in process engineering• Applications of large language models (LLMs) for process engineeringArticle types accepted: Original Research, Review, Mini Review, Perspective, Technology and Code, Methods, and Brief Research Report. Topic editors: Zhiyuan Wang, Zemin Feng Source: https://www.frontiersin.org/research-topics/83250/ai-enabled-decision-making-and-optimization-for-sustainable-chemical-and-process-engineering