Joel A. Paulson
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Joel A. Paulson has a total of 176 co-authors. Here are the top co-authors by number of shared publications:
Richard D. Braatz
18 shared publicationsAli Mesbah
University of California, Berkeley, CA, 94720
16 shared publications- Ali Mesbah
Department of Chemical and Biomolecular Engineering University of California Berkeley Berkeley California USA
13 shared publications - Richard D. Braatz
Massachusetts Institute of Technology
6 shared publications Farshud Sorourifar
Department of Chemical and Biomolecular Engineering
5 shared publications- Farshud Sorourifar
The Ohio State University, Department of Chemical and Biomolecular Engineering, Columbus, OH, 43210, USA
5 shared publications
Latest Publications
- 26 October 2026
- Published by Royal Society of Chemistry (RSC) in Green Chemistry
- Vol. 28 (41) , 16122-16190
Machine learning-enabled bio-oil co-processing for sustainable aviation fuel: catalyst-to-refinery integration for blend expansion
An integrated machine-learning framework connects catalyst and processing, hydrocarbon composition, fuel properties, blending, and ASTM qualification for multi-objective optimization across the SAF production chain toward scalable 100% SAF aviation.
- 26 October 2026
- Published by Royal Society of Chemistry (RSC) in Green Chemistry
- Vol. 28 (41) , 16122-16190
Machine learning-enabled bio-oil co-processing for sustainable aviation fuel: catalyst-to-refinery integration for blend expansion
An integrated machine-learning framework connects catalyst and processing, hydrocarbon composition, fuel properties, blending, and ASTM qualification for multi-objective optimization across the SAF production chain toward scalable 100% SAF aviation.
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems
- Vol. 46 (5) , 74-97
Polynomial Chaos-Based Stochastic Model Predictive Control: An Overview and Future Research Directions
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems
- Vol. 46 (5) , 74-97
Polynomial Chaos-Based Stochastic Model Predictive Control: An Overview and Future Research Directions
- 30 September 2026
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 65 (40) , 21460-21499
Atoms to Processes: The Role of Artificial Intelligence and Machine Learning in Chemical Engineering
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 Perspective provides an account of 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 life cycle 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.
- 30 September 2026
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 65 (40) , 21460-21499
Atoms to Processes: The Role of Artificial Intelligence and Machine Learning in Chemical Engineering
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 Perspective provides an account of 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 life cycle 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.
- Open Access
- 23 June 2026
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 5 (7) , 3116-3127
BEACON: a Bayesian optimization inspired strategy for efficient novelty search
BEACON uses multi-output probabilistic models and novelty scores to guide costly evaluations, enabling efficient discovery of diverse attainable outcomes rather than a single optimum.
- 23 June 2026
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 5 (7) , 3116-3127
Open AccessBEACON: a Bayesian optimization inspired strategy for efficient novelty search
BEACON uses multi-output probabilistic models and novelty scores to guide costly evaluations, enabling efficient discovery of diverse attainable outcomes rather than a single optimum.
- Open Access
- 17 May 2026
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry B
- Vol. 130 (21) , 5378-5386
Thermodynamics-Informed Machine Learning of Organic Electrode Material Solubility in Nonaqueous Electrolytes
Organic electrode materials (OEMs) based on abundant elements, such as C, N, O, and S, represent a promising class of sustainable alternatives to traditional transition-metal-based cathodes. However, discovery of new OEMs remains slow and resource-intensive because the design process is dominated by empirical trial-and-error. Although recent machine-learning approaches have accelerated the identification of redox-active compounds, the prediction of OEM solubility─a critical property governing cycle life─remains a major bottleneck. Here, we developed a physics-informed model for predicting OEM solubility using solvation energies (ΔGsolv) and sublimation (ΔGsub) energetics derived from a curated set of 44 redox-active organic compounds. While the DFT-calculated ΔGsolv and sublimation enthalpies (ΔHsub) correlate well with experimental measurements, the computed sublimation entropies (ΔSsub) exhibit large systematic errors, thereby limiting the overall predictive accuracy based on first-principles thermodynamics alone. To overcome this limitation, we integrated the physically meaningful computed descriptors into our recently developed symbolic regression framework, SyMANTIC, which learns a corrective model for solubility prediction in nonaqueous electrolytes. Despite the modest data set size, the resulting hybrid model shows good predictive performance under cross-validation and on held-out test compounds, illustrating that this framework can recover compact, chemically meaningful structure-property relationships and offers a new path toward rational design of low-solubility OEMs with reduced reliance on trial-and-error experimentation.
- 17 May 2026
- Published by American Chemical Society (ACS) in The Journal of Physical Chemistry B
- Vol. 130 (21) , 5378-5386
Open AccessThermodynamics-Informed Machine Learning of Organic Electrode Material Solubility in Nonaqueous Electrolytes
Organic electrode materials (OEMs) based on abundant elements, such as C, N, O, and S, represent a promising class of sustainable alternatives to traditional transition-metal-based cathodes. However, discovery of new OEMs remains slow and resource-intensive because the design process is dominated by empirical trial-and-error. Although recent machine-learning approaches have accelerated the identification of redox-active compounds, the prediction of OEM solubility─a critical property governing cycle life─remains a major bottleneck. Here, we developed a physics-informed model for predicting OEM solubility using solvation energies (ΔGsolv) and sublimation (ΔGsub) energetics derived from a curated set of 44 redox-active organic compounds. While the DFT-calculated ΔGsolv and sublimation enthalpies (ΔHsub) correlate well with experimental measurements, the computed sublimation entropies (ΔSsub) exhibit large systematic errors, thereby limiting the overall predictive accuracy based on first-principles thermodynamics alone. To overcome this limitation, we integrated the physically meaningful computed descriptors into our recently developed symbolic regression framework, SyMANTIC, which learns a corrective model for solubility prediction in nonaqueous electrolytes. Despite the modest data set size, the resulting hybrid model shows good predictive performance under cross-validation and on held-out test compounds, illustrating that this framework can recover compact, chemically meaningful structure-property relationships and offers a new path toward rational design of low-solubility OEMs with reduced reliance on trial-and-error experimentation.
- 24 February 2026
- Published by AIP Publishing in The Journal of Chemical Physics
- Vol. 164 (8)
MD-BAX: A general-purpose Bayesian design framework for molecular dynamics simulations with input-dependent noise
Molecular dynamics (MD) simulations are a powerful tool for understanding complex molecular behavior, but exhaustively exploring the large space of input parameters can be computationally prohibitive, especially when the outcomes are noisy and/or expensive to evaluate. In this work, we introduce MD-Bayesian algorithm execution (BAX), a general-purpose, automated design framework that builds on BAX acquisition strategy to efficiently guide simulation campaigns toward learning meaningful features of the system. Unlike optimization-centric Bayesian optimization approaches, MD-BAX seeks to identify broader system properties (e.g., phase transition boundaries, level sets, and threshold crossings) by strategically selecting input/parameter settings based on uncertainty. To accurately represent the variability in simulation outcomes, MD-BAX incorporates a Gaussian process surrogate model with input-dependent noise, estimated directly from MD trajectory statistics at each simulation setting. This enables construction of reliable uncertainty estimates for guiding the next simulation. We demonstrate the approach on a case study involving coil-to-globule transitions in amphiphilic block copolymers, highlighting that explicitly including trajectory-derived noise improves uncertainty calibration and enables our framework to more efficiently map the relationship between polymer structure, solvent quality, and conformational behavior. MD-BAX represents a domain-informed specialization of the BAX framework for MD and is broadly applicable to molecular modeling problems where the goal is to infer key system behaviors from stochastic, trajectory-based simulation outputs rather than to locate a single optimal condition.
- 24 February 2026
- Published by AIP Publishing in The Journal of Chemical Physics
- Vol. 164 (8)
MD-BAX: A general-purpose Bayesian design framework for molecular dynamics simulations with input-dependent noise
Molecular dynamics (MD) simulations are a powerful tool for understanding complex molecular behavior, but exhaustively exploring the large space of input parameters can be computationally prohibitive, especially when the outcomes are noisy and/or expensive to evaluate. In this work, we introduce MD-Bayesian algorithm execution (BAX), a general-purpose, automated design framework that builds on BAX acquisition strategy to efficiently guide simulation campaigns toward learning meaningful features of the system. Unlike optimization-centric Bayesian optimization approaches, MD-BAX seeks to identify broader system properties (e.g., phase transition boundaries, level sets, and threshold crossings) by strategically selecting input/parameter settings based on uncertainty. To accurately represent the variability in simulation outcomes, MD-BAX incorporates a Gaussian process surrogate model with input-dependent noise, estimated directly from MD trajectory statistics at each simulation setting. This enables construction of reliable uncertainty estimates for guiding the next simulation. We demonstrate the approach on a case study involving coil-to-globule transitions in amphiphilic block copolymers, highlighting that explicitly including trajectory-derived noise improves uncertainty calibration and enables our framework to more efficiently map the relationship between polymer structure, solvent quality, and conformational behavior. MD-BAX represents a domain-informed specialization of the BAX framework for MD and is broadly applicable to molecular modeling problems where the goal is to infer key system behaviors from stochastic, trajectory-based simulation outputs rather than to locate a single optimal condition.
- Open Access
- 3 February 2026
- Published by Elsevier in Chemical Engineering Journal
- Vol. 530
Modular one-step gas-to-liquid reactor for stranded natural gas monetization: Comprehensive thermodynamic assessment, techno-economic evaluation, and optimized field deployment
- 3 February 2026
- Published by Elsevier in Chemical Engineering Journal
- Vol. 530
Open AccessModular one-step gas-to-liquid reactor for stranded natural gas monetization: Comprehensive thermodynamic assessment, techno-economic evaluation, and optimized field deployment
- Open Access
- 21 December 2025
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 65 (1) , 628-642
Generative Multiobjective Bayesian Optimization with Scalable Batch Evaluations for Sample-Efficient De Novo Molecular Design
Designing molecules that must satisfy multiple, often conflicting, objectives is a central challenge in molecular discovery. The enormous size of the chemical space and the cost of high-fidelity simulations have driven the development of machine learning-guided strategies for accelerating design with limited data. Among these, Bayesian optimization (BO) offers a principled framework for sample-efficient search, while generative models provide a mechanism to propose novel, diverse candidates beyond fixed libraries. However, existing methods that couple the two often rely on continuous latent spaces, which introduce both architectural entanglement and scalability challenges. This work introduces an alternative, modular “generate-then-optimize” framework for de novo multiobjective molecular design/discovery. At each iteration, a generative model is used to construct a large, diverse pool of candidate molecules, after which a novel acquisition function, qPMHI (multipoint Probability of Maximum Hypervolume Improvement), is used to optimally select a batch of candidates most likely to induce the largest Pareto front expansion. The key insight is that qPMHI decomposes additively, enabling exact, scalable batch selection via only a simple ranking of probabilities that can be easily estimated with Monte Carlo sampling. We benchmark the framework against state-of-the-art latent-space and discrete molecular optimization methods, demonstrating significant improvements across synthetic benchmarks and application-driven tasks. Specifically, in a case study related to sustainable energy storage, we show that our approach quickly uncovers novel, diverse, and high-performing organic (quinone-based) cathode materials for aqueous redox flow battery applications.
- 21 December 2025
- Published by American Chemical Society (ACS) in Industrial & Engineering Chemistry Research
- Vol. 65 (1) , 628-642
Open AccessGenerative Multiobjective Bayesian Optimization with Scalable Batch Evaluations for Sample-Efficient De Novo Molecular Design
Designing molecules that must satisfy multiple, often conflicting, objectives is a central challenge in molecular discovery. The enormous size of the chemical space and the cost of high-fidelity simulations have driven the development of machine learning-guided strategies for accelerating design with limited data. Among these, Bayesian optimization (BO) offers a principled framework for sample-efficient search, while generative models provide a mechanism to propose novel, diverse candidates beyond fixed libraries. However, existing methods that couple the two often rely on continuous latent spaces, which introduce both architectural entanglement and scalability challenges. This work introduces an alternative, modular “generate-then-optimize” framework for de novo multiobjective molecular design/discovery. At each iteration, a generative model is used to construct a large, diverse pool of candidate molecules, after which a novel acquisition function, qPMHI (multipoint Probability of Maximum Hypervolume Improvement), is used to optimally select a batch of candidates most likely to induce the largest Pareto front expansion. The key insight is that qPMHI decomposes additively, enabling exact, scalable batch selection via only a simple ranking of probabilities that can be easily estimated with Monte Carlo sampling. We benchmark the framework against state-of-the-art latent-space and discrete molecular optimization methods, demonstrating significant improvements across synthetic benchmarks and application-driven tasks. Specifically, in a case study related to sustainable energy storage, we show that our approach quickly uncovers novel, diverse, and high-performing organic (quinone-based) cathode materials for aqueous redox flow battery applications.
- 25 September 2025
- Published by Elsevier in Computers & Chemical Engineering
- Vol. 204
BONSAI: Structure-exploiting robust Bayesian optimization for networked black-box systems under uncertainty
- 25 September 2025
- Published by Elsevier in Computers & Chemical Engineering
- Vol. 204
BONSAI: Structure-exploiting robust Bayesian optimization for networked black-box systems under uncertainty
- Open Access
- 1 September 2025
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 4 (10) , 2910-2926
Adaptive subspace Bayesian optimization over molecular descriptor libraries for data-efficient chemical design
MolDAIS enables data-efficient molecular discovery by adaptively learning sparse, task-relevant subspaces from descriptor libraries, outperforming prior methods in predictive accuracy, optimization efficiency, and interpretability.
- 1 September 2025
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 4 (10) , 2910-2926
Open AccessAdaptive subspace Bayesian optimization over molecular descriptor libraries for data-efficient chemical design
MolDAIS enables data-efficient molecular discovery by adaptively learning sparse, task-relevant subspaces from descriptor libraries, outperforming prior methods in predictive accuracy, optimization efficiency, and interpretability.