cs.AIOct 1, 2026

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

Authors: Michael Baldea, Linda J. Broadbelt, Marianthi G. Ierapetritou, Akhilesh Jain, Ankur Kumar, Thomas A. Kwan, Fèlix Llovell, Andrew J. Medford, +12 more

Organizations: McKetta Department of Chemical Engineering and Oden Institute for Chemical Engineering and Sciences, The University of Texas at Austin, Austin, TX 78731, USA · Department of Chemical and Biological Engineering, Northwestern University, Evanston, IL 60208, USA · Department of Chemical and Biomolecular Engineering, University of Delaware, Newark, DE 19716, USA · Advanced Analytics and AI, Baker Hughes · Smart Operations, Global AI, Linde plc, Tonawanda, NY, 14150, USA · Schneider Electric Research Institute, Schneider Electric, Boston, MA 02108, USA · Institute for Global Sustainability, Boston University, Boston, MA 02215, USA · Department of Chemical Engineering, ETSEQ, Universitat Rovira i Virgili, 43007 Tarragona, Spain · School of Chemical and Biomolecular Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA · Department of Chemical Engineering, Indian Institute of Technology Hyderabad, Kandi - 502 204, Sangareddy, Telangana, India · Department of Chemical and Biological Engineering, University of Wisconsin, Madison, WI 53706, USA · Department of Chemical and Biomolecular Engineering, National University of Singapore, Singapore 117585 · Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA · Department of Chemical Engineering, The University of Manchester, Manchester M13 9PL, United Kingdom · Department of Computing, Imperial College London, London SW7 2AZ, United Kingdom · Department of Chemical and Biological Engineering, Monash University, Clayton, Victoria 3800, Australia

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

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.

Figures & tables

Figure 1: AI/ML methodological classes relevant to chemical engineering applications
Current capabilitiesRemaining barriersFuture opportunities
MLIPs reproduce DFT-level adsorption energetics ( ∼\sim 0.2–0.5 eV) at orders-of-magnitude lower cost, enabling active-site, nanoparticle- and micron-scale surface simulationsMLIP accuracy is bounded by the underlying DFT training data; long-timescale trajectories are difficult to validate, and UQ outside the training domain remains immatureTighter active-learning loops coupling MLIPs with DFT, and systematic UQ benchmarks for long-timescale/ out-of-domain predictions
AI-based mechanism generators (e.g., RMG-Cat, Genesys-Cat) and diffusion-based adsorbate-placement models automate construction of catalytic reaction networksEstimating rate coefficients for every elementary step, adsorbate configuration, and facet remains combinatorially difficult; many ML rate models are not mechanistically interpretableBroader use of physics-constrained (mass-action, site-conservation, thermodynamically consistent) kinetic ML to reduce reliance on empirical rate rules
ML surrogates for coverage-dependent kinetics and microkinetic/reactor coupling (e.g., lattice CNNs, AMUSE) enable reactor-scale simulation with retained mechanistic fidelityValidation of learned kinetic models still relies heavily on comparison to DFT rather than synthesis and testing of real catalystsExtending multiscale, DFT-to-reactor automation frameworks to routine industrial reactor design workflows
ML directly extracts rate coefficients and full rate laws from reactor/experimental data (SINDy-type and kinetics-informed neural networks), and LLM-assisted tools (e.g., SKAI) translate reaction descriptions into model equationsData quality/quantity requirements for reliable kinetic discovery are often unmet in typical experimental datasetsDevelopment of shared kinetics data benchmarks (e.g., Catechol, Summit, ORDERLY) to enable reproducible comparison across methods
High-throughput ML screening, generative (VAE, diffusion) and LLM-based (CatGPT, CataLM) models, and autonomous “self-driving lab” platforms accelerate catalyst discovery and optimizationGenerated catalyst candidates are not always synthetically accessible; autonomous platforms remain limited to specific reaction classes and equipment configurationsCloser integration of generative catalyst design with autonomous synthesis-testing loops and multiobjective (activity/selectivity/sustainability) optimization
Emerging kinetics data benchmarks (e.g., Catechol, Summit, ORDERLY) provide shared datasets for reaction-kinetics MLCode, trained MLIP/kinetic-model parameters, hyperparameters, and data splits are rarely released alongside published results, making it difficult to reproduce reported rate coefficients or reimplement mechanism-generation pipelinesJournal- and community-level requirements for code, model weights, and versions of software/environments as a condition of publication, mirroring practice in adjacent computational chemistry venues
Table 1: Kinetics, Catalysis and Reaction Engineering: current capabilities, remaining barriers, and future opportunities.
Current capabilitiesRemaining barriersFuture opportunities
Deep learning (CNNs, U-Net, attention/residual architectures) segments droplets/bubbles and reconstructs multiphase flow fields directly from holographic and simulation data, without hand-engineered featuresConventional design/optimization strategies (empirical correlations, iterative experiments) still struggle with the spatiotemporal complexity of multiphase flows, and purely data-driven models can violate physical constraintsContinued convergence of high-speed/holographic sensing with physics-informed ML for real-time, self-optimizing multiphase systems
Hybrid and physics-informed frameworks (e.g., PINNs) embed mass/momentum/energy conservation directly into architectures or loss functions, improving robustness under sparse or noisy dataReal-time ML-based control of multiphase flows is still constrained by sensing bandwidth and computational costBroader deployment of RL-based control for atomization, bubble-column operation, and spray cooling in industrial settings
ML/ANN models predict thermophysical and transport properties (viscosity, thermal and ionic conductivity, diffusion coefficients) competitively with or better than semi-empirical correlations, especially for tunable compound families (e.g., ionic liquids)Thermophysical/transport property data remain scarce, inconsistent, and heterogeneous across sources, limiting the reliability of purely data-driven modelsCuration of standardized, cross-laboratory thermophysical property databases to reduce data heterogeneity
Thermodynamics-informed ML (embedding Gibbs–Helmholtz, Clausius–Clapeyron and related identities) and ML-augmented/neural EoS improve internal consistency and extrapolation in low-data regimesEnforcing full thermodynamic consistency (Maxwell relations, convexity of free energies, positivity of entropy production) remains difficult for generic architecturesDeeper architectural embedding of stability/phase-equilibrium constraints so ML augments, rather than replaces, EoS-based thermodynamic theory
Inverse-design workflows map molecular representations (SMILES, fingerprints, σ\sigma -profiles) to EoS parameters, enabling rapid virtual screening for target phase behaviorExtrapolation beyond the training domain, critical for process synthesis and safety, remains a persistent weakness; integration into commercial process software requires robust UQ and validationDevelopment of transparent, well-validated ML thermodynamic modules with long-term maintainability for integration into standard process simulators
Neural EoS surrogates and thermodynamics-informed property-prediction models are increasingly reported in the literatureTrained network weights, training/test splits, and the specific software/library versions used to fit thermodynamic surrogates are seldom shared, hindering independent verification against reported accuraciesMinimum code- and data-availability requirements for published thermodynamic/transport ML models, enabling direct reproduction and fair cross-study comparison
Table 2: Thermodynamics, Transport and Fluid Mechanics: current capabilities, remaining barriers, and future opportunities.
Current capabilitiesRemaining barriersFuture opportunities
Generative AI (e.g., VAE-based) has been applied to distillation column design and energy-use optimization; interpretable ML predicts performance of intensified gas–liquid operationsMost ML research targets membranes and adsorption; distillation, still the dominant industrial technology, remains comparatively underserved by AI/ML advancesExtending generative and interpretable ML methods to established gas–liquid operations and complex/impure multicomponent streams
Large curated databases (CoRE MOF, Polymer Genome) and ML screening (multitask learning, random forest) enable rapid evaluation of MOF/polymer gas-separation and CO 2 -capture performance across millions of candidatesMOF ML workflows rely largely on simulated (DFT/GCMC) data, whereas membrane ML studies mix experimental and simulated data, complicating cross-domain model transferDevelopment of unified, experimentally grounded datasets spanning adsorbents and membranes to improve model transferability
Generative models (MOFDiff, VAE-based inverse design, ChatMOF) propose entirely new MOF and membrane candidates targeted at CO 2 capture and gas separationGenerated hypothetical adsorbents/membranes are not always synthetically accessible, and models trained on equilibrium isotherms struggle with dynamic, multicomponent industrial conditionsCoupling generative materials design with synthesis-feasibility filters and models that capture adsorption/desorption kinetics alongside thermodynamics
Physics-based ML process emulators (e.g., MAPLE, PANACHE) achieve ∼\sim 100 ×\times speedups over conventional solvers while retaining transport-equation fidelity for adsorption/chromatography cyclesIntegration of molecular-scale material properties with process-level design and control remains only partially realizedEnd-to-end frameworks that translate material-level predictions directly into optimal process configurations
RL and optimization algorithms autonomously tune membrane and adsorption operating parameters (pressure, concentration, temperature) to improve selectivity and reduce energy use and foulingEmergent, complex fluid–solid interfacial behaviors (cooperative ion transport, dynamic fouling) remain difficult to capture with conventional analytical or numerical methodsBroader real-time, AI-driven control of desalination, lithium-extraction, and gas-separation operations informed by AI-identified interfacial mechanisms
Process-level ML emulators (MAPLE, PANACHE) and generative adsorbent/membrane models are increasingly published with reported performance metricsUnderlying code, isotherm/simulation datasets, trained network parameters, and hyperparameters are inconsistently released, complicating independent verification of speedup and accuracy claimsAdoption of explicit code- and data-availability requirements for separations ML publications, comparable to those emerging in adjacent computational chemistry journals
Table 3: Separations: current capabilities, remaining barriers, and future opportunities.
Current capabilitiesRemaining barriersFuture opportunities
GNNs and equivariant architectures (NequIP/Allegro, MACE, M3GNet, CHGNet) predict formation energies, band gaps, and elastic moduli near DFT accuracy at a fraction of the costReported benchmark accuracies (e.g., ∼\sim 0.2 eV MAE) are often sufficient for screening but inadequate for quantitative kinetic modelingPhysics-informed extensions of universal potentials that capture non-equilibrium/kinetic behavior beyond static equilibrium properties
Universal ML interatomic potentials (e.g., GNoME) combined with iterative ML–DFT cycles have expanded the known stable-materials database by an order of magnitudeOut-of-distribution generalization is weak for compositions with underrepresented elements or unusual coordination environmentsSystematic, topology/scaffold-based (rather than random) benchmark splits and comparison against strong traditional baselines
Generative and inverse design (CVAE, transformer/foundation models such as MOFormer, MOFTransformer, Uni-MOF) propose new membranes, surfactants, and reticular materials with targeted propertiesHypothetical materials databases used for training often lack synthesis-feasibility annotations, yielding ”high-performing” but unsynthesizable candidatesCoupling generative design with synthesis-feasibility screening and lifecycle/sustainability objectives embedded directly in the optimization
Self-driving laboratories (A-Lab, mobile robotic chemists) autonomously synthesize and characterize new materials, with industrial analogues emerging (e.g., automated battery-material sintering and testing)Diversity of synthesis routes and characterization techniques across material classes limits broader industrial scaling of autonomous platformsWider industrial adoption of closed-loop autonomous discovery platforms across additional material classes
Standardized benchmarks (Matbench, OC20/OC22) and infrastructure (cloud HPC) support reproducible, community-wide evaluation of materials ML modelsData heterogeneity, inconsistent metadata, and incomplete FAIR-principle adoption across repositories hinder cross-dataset trainingCommunity-wide data harmonization (e.g., via initiatives such as NOMAD) and multimodal, literature-integrated foundation models for materials discovery
Benchmark datasets and leaderboards report standardized accuracy metrics across many groupsCode, trained model checkpoints, exact data splits, and hyperparameter/tuning details behind reported benchmark numbers are frequently withheld, so reported accuracies cannot be independently reproduced or fairly compared across studiesMinimum reproducibility requirements (released code, splits, weights, hyperparameters, software versions) as a condition of publication, as increasingly enforced in adjacent computational chemistry journals
Table 4: Materials and Interfaces, and Applied Chemistry: current capabilities, remaining barriers, and future opportunities.
Current capabilitiesRemaining barriersFuture opportunities
Bayesian optimization is widely used for process/product design, with extensions for discrete, graph-structured, and robust/safe design under uncertaintyGenerative/AI process-design tools remain largely interpolative; genuine extrapolation beyond training data toward novel designs is unprovenInteractive tools/copilots that help engineers visualize, cluster, and navigate high-dimensional process-design spaces
ML-learned dynamic models (Koopman operators, sparse regression, neural/Gaussian-process surrogates) support system identification while increasingly preserving stability and dissipativity propertiesLack of open, shared process-design benchmark datasets (unlike molecular/materials domains) due to proprietary industrial data limits systematic algorithm comparisonCommunity efforts to establish open process-design benchmarks and metrics, drawing on precedents from self-driving-lab and BO communities
RL-based and NN-approximated MPC laws, together with ML-accelerated mixed-integer solvers (e.g., learned Benders warm-starts), speed up online control and scheduling computationHigh-dimensional, discrete/mixed-integer design and scheduling spaces remain challenging for BO and RL; deep learning controllers can lack interpretabilityTighter integration of superstructure optimization with data-driven surrogate modeling; extending ML-based solver tuning to nonlinear MPC
AI/ML forecasting (LSTM, kernel methods) improves demand/inventory/procurement planning; RL supports dynamic scheduling, predictive maintenance, and vehicle routing under uncertaintyEnsuring safety and constraint satisfaction is difficult once RL policies operate outside their training distribution; online exploration is often unsafe in safety-critical settingsBroader deployment of safe/robust BO and constrained or offline RL for uncertainty-aware, safety-critical design and control
Standardized RL benchmark environments (OR-Gym, SafeOR-Gym, PC-Gym) and digital-twin/blockchain-enabled data-governance concepts support reproducible PSE algorithm evaluation and resilient supply chainsSupply-chain AI adoption is limited by data-privacy/sharing constraints, high infrastructure costs, and organizational resistance to automationLLM-assisted extraction of regulatory/sustainability constraints into optimization formulations, and expanded digital-twin-based, closed-loop decision support
Benchmark RL environments provide shared, standardized testbeds for algorithm comparisonBeyond these environments, published PSE control/scheduling studies often withhold trained policy parameters, hyperparameters, random seeds, and software versions, making reported performance hard to reproduce or compare across algorithmsExtending benchmark-environment culture into explicit minimum code-, model-, and environment-release requirements for PSE control/scheduling/design publications
Table 5: Process Systems Engineering: current capabilities, remaining barriers, and future opportunities.
Figure 2: Application areas of AI/ML in industrial operations with substantial AI penetration.
Figure 3: Factors inhibiting widespread adoption of AI/ML solutions.
Current capabilitiesRemaining barriersFuture opportunities
Process control and monitoring (ML-augmented APC, PCA/PLS, autoencoder-based anomaly detection) is the most mature AI/ML application domain in chemical plantsMany AI/ML applications remain “add-ons” rather than essential components of the operating toolkit, limiting sustained integrationEmbedding AI capabilities as core, trusted components of standard operating and control infrastructure
Predictive maintenance using vibration, thermal, acoustic, and process-history data has delivered documented reductions in unplanned downtime at companies such as Shell and Marathon Petroleum“Last-mile” adoption failure: sophisticated models often fail to influence operator decisions due to distrust of opaque, black-box recommendationsExplainable, uncertainty-aware AI systems that build operator trust and gracefully acknowledge out-of-distribution situations
Virtual/soft sensors (NN, Gaussian process, ensemble methods), increasingly physics-informed, infer hard-to-measure variables from routine measurements; ML surrogates enable real-time optimization (RTO)Model drift from catalyst deactivation, fouling, and equipment changes requires ongoing maintenance; “dashboard fatigue” and platform fragmentation hinder adoption at scaleFormalized model-lifecycle-management frameworks (continuous monitoring, automated drift detection, defined retraining triggers, governance) embedded in unified analytics platforms
Hybrid digital twins (mechanistic + ML) are deployed at plant scale for real-time health monitoring and have a growing base of plant-scale case studies across process industriesTraining data reflect narrow, closed-loop operating envelopes, limiting applicability to optimization/control tasks requiring broader excitation; comprehensive high-fidelity digital twins remain aspirational for many processesExpanded hybrid digital twins enabling autonomous management of startups, shutdowns, and transitions, with humans focused on supervisory oversight
LLM-based copilots are beginning to lower the barrier to natural-language interaction with plant analytics, contextual knowledge retrieval, and operator knowledge transferLLM hallucination, confident-but-incorrect outputs, and lack of intrinsic numerical/physical guarantees pose safety risks if used beyond an orchestrator roleRestricting LLMs to orchestrator roles interfacing with verified simulators/historians/optimizers, with human-in-the-loop review before safety-critical actions
Published industrial case studies (e.g., digital twins, predictive maintenance, RL-based control) report quantified operational benefitsProprietary data and IP concerns mean industrial AI/ML studies rarely release code, trained models, or full data-processing pipelines, making reported gains difficult for independent researchers to verify or reproduceDevelopment of anonymized benchmark problems and reporting norms that let industrial studies disclose methodology and reproducibility artifacts without exposing proprietary plant data
Table 6: Industrial Applications of AI: current capabilities, remaining barriers, and future opportunities.
Figure 4: For Table of Contents Only

Explore similar work

CardsList
Sep 30, 2026physics.chem-ph

A strategic roadmap for an atomistic machine-learning ecosystem

Data-driven machine learning (ML) techniques have become an essential tool in many domains of science. Their application to atomistic simulations of matter is particularly widespread and impactful. This success is due largely to the existence of a well-developed and established physics-based modeling framework, ranging from first-principles electronic-structure calculations to molecular dynamics and statistical sampling, into which ML was integrated naturally to reshape long-standing trade-offs between accuracy, efficiency, and scale. Nevertheless, this integration raises both conceptual and practical challenges, from choosing between data-centric and physics-based modeling approaches to adapting established software stacks to modern hardware accelerators and ML libraries. As the field evolves rapidly, fueled in part by widespread enthusiasm but also by tangible impact, it seems appropriate to take a moment to consider the current state of the art and open challenges, and reflect on what can be done to better coordinate efforts across the community. With this goal in mind, several members of this community met in Lausanne in January 2026 at CECAM to discuss algorithms, models, software and hardware infrastructure, and the most promising scientific applications that have become possible thanks to the use of artificial intelligence in atomic-scale simulations. This strategic roadmap paper summarizes the outcomes of these discussions, suggesting some long-term goals, and some concrete actions, to establish a healthy, sustainable and impactful atomistic ML ecosystem.

Jörg Behler, Michele Ceriotti, Cecilia Clementi +46

Molecular DynamicsRoadmapScientific Discovery
AskPDF
Jun 15, 2026cs.LG

Prediction of Runtime Parameters of Parallel Chemistry Applications via Active and Generative Learning

In this work, we develop two main Machine Learning based approaches to predict the runtime parameters of highly scalable parallel chemistry computations.These approaches employ active and generative learning together with the empirically determined gradient boosted regression tree models chosen among a rich suite of machine learning models. When evaluated on Coupled-Cluster with Singles and Doubles computations, our models achieve a mean absolute error percentage (MAPE) as low as 0.023 and a coefficient of determination as high as 99.9%. Furthermore, when combined with active learning to mitigate the lack of large amounts of training data, our models score a MAPE about 0.2 with 20-25% of the original dataset.

Tanzila Tabassum, Omer Subasi, Ajay Panyala +5

1Louisiana State University, Baton Rouge, Louisiana, USA · 2Pacific Northwest National Laboratory, Richland, Washington, USA · University of Utah, Salt Lake City, Utah, USA

Quantum ChemistryHeterogeneous CatalysisActive LearningGenerative ModelsRuntimeDecision Trees
AskPDF
Jun 29, 2026physics.chem-ph

ElemeNet: Multiscale Molecular Machine Learning with Uncertainty Quantification Across the Periodic Table

Advances in deep learning architectures and representations have enabled ML-driven chemical property prediction, but state-of-the-art (SOTA) models have remained largely confined to independent codebases and lack support for diverse chemical species. This work introduces ElemeNet, a unified, general-purpose software package for molecular machine learning. The ElemeNet software package enables the training of advanced ML models for diverse properties and datasets with an enlarged range of elemental compositions. We define molecular representations compatible with elements 1-100, supporting diverse organometallic and biological systems in addition to organic chemistry already well-served by the Chemprop ML toolkit. As well as more common atom-, bond-, and molecule-level predictions, we introduce moiety predictions. We also natively define optional conditioning on charge and spin states. Advanced E(3)-equivariant and transformer architectures are supported, as well as classical 2D models, with all classes including built-in uncertainty quantification through deterministic and statistical measures. We benchmark our protocols for ML model training against representative datasets from organic, inorganic, coordination, and biological chemistry, achieving competitive and SOTA performance relative to literature baselines and favorable scaling to millions of molecules. The entire workflow is exposed through a concise command-line interface, lowering the barrier to entry for non-expert users. We anticipate ElemeNet will empower non-computational researchers to leverage modern deep learning methods across the chemical and physical sciences.

Jacob W. Toney, Samir Darouich, Yiran Wang +3

Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA · Center for Computational Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA · Institute for Theoretical Chemistry, University of Stuttgart, Germany +2

Molecular Property PredictionAtomsUncertainty Quantification
AskPDF