Atoms to Processes: The Role of Artificial Intelligence and Machine Learning in Chemical Engineering

Abstract

The rapid maturation of artificial intelligence (AI) and machine learning (ML) has catalyzed a profound shift in how chemical engineering problems are formulated, analyzed, and solved. Advances in computing, data availability, and learning algorithms have enabled AI/ML methods to impact applications spanning atomic-scale simulations, materials and catalyst discovery, transport and thermodynamics, separations, process systems engineering, and industrial operations. This article provides a perspective on recent methodological developments and representative applications, emphasizing how AI/ML tools are being integrated with first-principles models to address challenges of predictive accuracy, data scarcity, extrapolation, interpretability, and model lifecycle management. Across domains, a unifying trend is the move away from purely black-box approaches toward hybrid and physics-informed frameworks that explicitly respect conservation laws, thermodynamic consistency, and known structural constraints. These approaches not only improve robustness and reliability, but also enable meaningful human-AI collaboration by providing information at an appropriate level of abstraction for the task and decision context. We conclude that AI and ML are not replacing the core principles of chemical engineering; rather, they are amplifying them. As the field advances toward increasingly autonomous, adaptive, and sustainable systems, the thoughtful integration of AI/ML with first-principles understanding and domain expertise will be essential to realizing their full potential across both research and industrial practice.

References in corpus (62)

• Automatic chemical design using a data-driven continuous representation of molecules
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Machine Learning for Fluid Mechanics
• Tuneable Sieving of Ions Using Graphene Oxide Membranes
• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• A Universal Graph Deep Learning Interatomic Potential for the Periodic Table
• The Open Catalyst 2020 (OC20) Dataset and Community Challenges
• Benchmarking Materials Property Prediction Methods: The Matbench Test Set and Automatminer Reference Algorithm
• Safe Reinforcement Learning Using Robust MPC
• The Open Catalyst 2022 (OC22) Dataset and Challenges for Oxide Electrocatalysts
• Learning an Approximate Model Predictive Controller with Guarantees
• A Hybrid Science-Guided Machine Learning Approach for Modeling and Optimizing Chemical Processes
• Gryffin: An algorithm for Bayesian optimization of categorical variables informed by expert knowledge
• Autonomous Discovery of Unknown Reaction Pathways from Data by Chemical Reaction Neural Network
• Deep Reinforcement Learning for Process Control: A Primer for Beginners
• Accelerating computational materials discovery with artificial intelligence and cloud high-performance computing: from large-scale screening to experimental validation
• Deep Reinforcement Learning with Shallow Controllers: An Experimental Application to PID Tuning
• Maximizing information from chemical engineering data sets: Applications to machine learning
• Machine Learning Holography for 3D Particle Field Imaging
• Graph Neural Network Predictions of Metal Organic Framework CO2 Adsorption Properties
• Graph Neural Networks for Temperature-Dependent Activity Coefficient Prediction of Solutes in Ionic Liquids
• An Artificial Intelligence (AI) workflow for catalyst design and optimization
• Generative AI and Process Systems Engineering: The Next Frontier
• Probing out-of-distribution generalization in machine learning for materials
• Learning from flowsheets: A generative transformer model for autocompletion of flowsheets
• De novo Design of Polymer Electrolytes with High Conductivity using GPT-based and Diffusion-based Generative Models
• DySMHO: Data-Driven Discovery of Governing Equations for Dynamical Systems via Moving Horizon Optimization
• Generative Language Model for Catalyst Discovery
• Global optimization of atomic structures with gradient-enhanced Gaussian process regression
• Integrating production scheduling and process control using latent variable dynamic models
• Size distribution of a drop undergoing breakup at moderate Weber numbers
• Large Language Models for Supply Chain Optimization
• Bayesian Optimization of Catalysis With In-Context Learning
• Droplet size distribution in a swirl airstream using in-line holography technique
• OR-Gym: A Reinforcement Learning Library for Operations Research Problems
• MPC Controller Tuning using Bayesian Optimization Techniques
• NEP-MB-pol: A unified machine-learned framework for fast and accurate prediction of water's thermodynamic and transport properties
• Micron-scale heterogeneous catalysis with Bayesian force fields from first principles and active learning
• Machine Learning Accelerated Descriptor Design for Catalyst Discovery in CO${}_2$ to Methanol Conversion
• Prediction uncertainty validation for computational chemists
• Machine Learning with bond information for local structure optimizations in surface science
• MOFDiff: Coarse-grained Diffusion for Metal-Organic Framework Design
• Computationally efficient solution of mixed integer model predictive control problems via machine learning aided Benders Decomposition
• Autonomous Industrial Control using an Agentic Framework with Large Language Models
• Thermodynamically consistent machine learning model for excess Gibbs energy
• CataLM: Empowering Catalyst Design Through Large Language Models
• BONSAI: Structure-exploiting robust Bayesian optimization for networked black-box systems under uncertainty
• AdsorbDiff: Adsorbate Placement via Conditional Denoising Diffusion
• Learning interpretable and stable dynamical models via mixed-integer Lyapunov-constrained optimization
• Neural Luenberger state observer for nonautonomous nonlinear systems
• Context is all you need: Towards autonomous model-based process design using agentic AI in flowsheet simulations
• A Hybrid Reinforcement and Self-Supervised Learning Aided Benders Decomposition Algorithm
• A constrained symbolic regression approach for Lyapunov function discovery
• UniMat: Unifying Materials Embeddings through Multi-modal Learning
• Approximate Dynamic Optimization via Deep Neural Operators
• Hierarchical RL-MPC for Demand Response Scheduling
• SafeOR-Gym: A Benchmark Suite for Safe Reinforcement Learning Algorithms on Practical Operations Research Problems
• Graph-Based Imitation and Reinforcement Learning for Efficient Benders Decomposition
• BoGrape: Bayesian optimization over graphs with shortest-path encoded
• Discovering interpretable piecewise nonlinear model predictive control laws via symbolic decision trees
• Survey and Tutorial of Reinforcement Learning Methods in Process Systems Engineering