John M. Gregoire
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
John M. Gregoire has a total of 381 co-authors. Here are the top co-authors by number of shared publications:
Dan Guevarra
Division of Engineering and Applied Science, California Institute of Technology, Pasadena, CA 91125, USA
31 shared publicationsLan Zhou
California Institute of Technology
29 shared publications- Dan Guevarra
California Institute of Technology
27 shared publications - Joel A. Haber
Division of Engineering and Applied Science, California Institute of Technology, Pasadena, CA 91125, USA
26 shared publications - Lan Zhou
Division of Engineering and Applied Science, California Institute of Technology, Pasadena, CA, USA
25 shared publications Yungchieh Lai
Division of Engineering and Applied Science, California Institute of Technology, Pasadena, CA, USA
23 shared publications
Latest Publications
- Open Access
- 10 September 2026
- Published by American Physical Society (APS) in PRX Intelligence
- Vol. 1 (1) , 013019
Autonomous Materials Exploration Integrates Automated Phase Identification and AI Agents Enhanced by Human Guidance
Autonomous experimentation holds the potential to accelerate materials development by combining artificial intelligence (AI) with modular robotic platforms to explore extensive combinatorial chemical and processing spaces. Such self-driving laboratories can not only increase the throughput of repetitive experiments, but also incorporate human domain expertise to drive the search toward user-defined objectives, including improved materials performance metrics. We present an autonomous materials synthesis extension to SARA, the Scientific Autonomous Reasoning Agent, utilizing phase information provided by an automated probabilistic phase labeling algorithm to expedite the search for targeted phase regions. By incorporating human input into an expanded SARA-H (SARA with human-in-the-loop) framework, we enhance the efficiency of the underlying reasoning process. Using synthetic benchmarks, we demonstrate the efficiency of our AI implementation and show that the human input can contribute to significant improvement in sampling efficiency. We conduct experimental active learning campaigns using robotic processing of thin-film samples of several oxide material systems, including Bi 2 O 3 , SnO x , and Bi − Ti − O , using lateral-gradient laser spike annealing to synthesize and kinetically trap metastable phases. We showcase the utility of human-in-the-loop autonomous experimentation for the Bi − Ti − O system, where we identify extensive processing domains that stabilize δ − Bi 2 O 3 and Bi 2 Ti 2 O 7 , explore dwell-dependent ternary oxide phase behavior, and provide evidence confirming predictions that cationic substitutional doping of TiO 2 with Bi inhibits the unfavorable transformation of the metastable anatase to the ground-state rutile phase. The autonomous methods we have developed enable the discovery of new materials and new understanding of materials synthesis and properties.
- 10 September 2026
- Published by American Physical Society (APS) in PRX Intelligence
- Vol. 1 (1) , 013019
Open AccessAutonomous Materials Exploration Integrates Automated Phase Identification and AI Agents Enhanced by Human Guidance
Autonomous experimentation holds the potential to accelerate materials development by combining artificial intelligence (AI) with modular robotic platforms to explore extensive combinatorial chemical and processing spaces. Such self-driving laboratories can not only increase the throughput of repetitive experiments, but also incorporate human domain expertise to drive the search toward user-defined objectives, including improved materials performance metrics. We present an autonomous materials synthesis extension to SARA, the Scientific Autonomous Reasoning Agent, utilizing phase information provided by an automated probabilistic phase labeling algorithm to expedite the search for targeted phase regions. By incorporating human input into an expanded SARA-H (SARA with human-in-the-loop) framework, we enhance the efficiency of the underlying reasoning process. Using synthetic benchmarks, we demonstrate the efficiency of our AI implementation and show that the human input can contribute to significant improvement in sampling efficiency. We conduct experimental active learning campaigns using robotic processing of thin-film samples of several oxide material systems, including Bi 2 O 3 , SnO x , and Bi − Ti − O , using lateral-gradient laser spike annealing to synthesize and kinetically trap metastable phases. We showcase the utility of human-in-the-loop autonomous experimentation for the Bi − Ti − O system, where we identify extensive processing domains that stabilize δ − Bi 2 O 3 and Bi 2 Ti 2 O 7 , explore dwell-dependent ternary oxide phase behavior, and provide evidence confirming predictions that cationic substitutional doping of TiO 2 with Bi inhibits the unfavorable transformation of the metastable anatase to the ground-state rutile phase. The autonomous methods we have developed enable the discovery of new materials and new understanding of materials synthesis and properties.
- 7 July 2026
- Published by The Electrochemical Society in ECS Meeting Abstracts
- Vol. MA2026-01 (40) , 2042
Sodium-Mediated Redox Cascade for Electrochemical Ammonia Synthesis
Artificial ammonia synthesis is vital to modern life; however, the Haber-Bosch process, by which most ammonia is synthesized, is capital- and carbon-intensive. Zero-valent-metal-mediated ammonia synthesis is a promising alternative but requires a metal that is both a strong reductant and forms a stable nitride. Only a small number of metals, like lithium, can satisfy these constraints. Therefore, we developed an electrochemical paradigm enabling the use of different reductants by orthogonalizing the roles of the zero-valent metal between sodium metal and a Ti active site. These components are cheaper than lithium by two orders of magnitude. Using a sodium-naphthalene-titanium cascade, we achieved a rate of 475 nmol cm-2 s-1 and a Faradaic efficiency of 24%, and found that the reaction rate depends primarily on current density.
- 7 July 2026
- Published by The Electrochemical Society in ECS Meeting Abstracts
- Vol. MA2026-01 (40) , 2042
Sodium-Mediated Redox Cascade for Electrochemical Ammonia Synthesis
Artificial ammonia synthesis is vital to modern life; however, the Haber-Bosch process, by which most ammonia is synthesized, is capital- and carbon-intensive. Zero-valent-metal-mediated ammonia synthesis is a promising alternative but requires a metal that is both a strong reductant and forms a stable nitride. Only a small number of metals, like lithium, can satisfy these constraints. Therefore, we developed an electrochemical paradigm enabling the use of different reductants by orthogonalizing the roles of the zero-valent metal between sodium metal and a Ti active site. These components are cheaper than lithium by two orders of magnitude. Using a sodium-naphthalene-titanium cascade, we achieved a rate of 475 nmol cm-2 s-1 and a Faradaic efficiency of 24%, and found that the reaction rate depends primarily on current density.
- 7 July 2026
- Published by The Electrochemical Society in ECS Meeting Abstracts
- Vol. MA2026-01 (58) , 2042
Sodium-Mediated Redox Cascade for Electrochemical Ammonia Synthesis
Artificial ammonia synthesis is vital to modern life; however, the Haber-Bosch process, by which most ammonia is synthesized, is capital- and carbon-intensive. Zero-valent-metal-mediated ammonia synthesis is a promising alternative but requires a metal that is both a strong reductant and forms a stable nitride. Only a small number of metals, like lithium, can satisfy these constraints. Therefore, we developed an electrochemical paradigm enabling the use of different reductants by orthogonalizing the roles of the zero-valent metal between sodium metal and a Ti active site. These components are cheaper than lithium by two orders of magnitude. Using a sodium-naphthalene-titanium cascade, we achieved a rate of 475 nmol cm-2 s-1 and a Faradaic efficiency of 24%, and found that the reaction rate depends primarily on current density.
- 7 July 2026
- Published by The Electrochemical Society in ECS Meeting Abstracts
- Vol. MA2026-01 (58) , 2042
Sodium-Mediated Redox Cascade for Electrochemical Ammonia Synthesis
Artificial ammonia synthesis is vital to modern life; however, the Haber-Bosch process, by which most ammonia is synthesized, is capital- and carbon-intensive. Zero-valent-metal-mediated ammonia synthesis is a promising alternative but requires a metal that is both a strong reductant and forms a stable nitride. Only a small number of metals, like lithium, can satisfy these constraints. Therefore, we developed an electrochemical paradigm enabling the use of different reductants by orthogonalizing the roles of the zero-valent metal between sodium metal and a Ti active site. These components are cheaper than lithium by two orders of magnitude. Using a sodium-naphthalene-titanium cascade, we achieved a rate of 475 nmol cm-2 s-1 and a Faradaic efficiency of 24%, and found that the reaction rate depends primarily on current density.
- Open Access
- 4 November 2025
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 4 (12) , 3674-3682
Active learning path-dependent properties using a cloud-based materials acceleration platform
Solid state materials are central to many modern technologies in which a given material may be exposed to a variety of environments. The material properties often vary with the sequence of environments in an irreversible manner, resulting in a quintessential path-dependency in experimental observables. While sequential learning techniques have been effectively deployed for accelerating learning of state properties of materials, they often use a consistent environment path in all experiments. To elevate such techniques for making optimal decisions in experimental investigations of path-dependent properties, we introduce an iterated expected information gain acquisition function that optimizes over entire experimental trajectories. This approach is implemented within a cloud-based Materials Acceleration Platform architecture utilizing an event-driven stateful broker coupled with remote HELAO (Hierarchical Experimental Laboratory Automation and Orchestration) instances and an AI science manager. The platform's efficacy was demonstrated through a case study optimizing multi-step spectro-electrochemical experiments to identify optically stable potential windows in (Co–Ni–Sb)Oz metal oxides. The system successfully integrated AI-driven experiment design, remote laboratory automation, and cloud-based data infrastructure, validating the platform's capability for managing complex, adaptive, path-dependent workflows in materials discovery.
- 4 November 2025
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 4 (12) , 3674-3682
Open AccessActive learning path-dependent properties using a cloud-based materials acceleration platform
Solid state materials are central to many modern technologies in which a given material may be exposed to a variety of environments. The material properties often vary with the sequence of environments in an irreversible manner, resulting in a quintessential path-dependency in experimental observables. While sequential learning techniques have been effectively deployed for accelerating learning of state properties of materials, they often use a consistent environment path in all experiments. To elevate such techniques for making optimal decisions in experimental investigations of path-dependent properties, we introduce an iterated expected information gain acquisition function that optimizes over entire experimental trajectories. This approach is implemented within a cloud-based Materials Acceleration Platform architecture utilizing an event-driven stateful broker coupled with remote HELAO (Hierarchical Experimental Laboratory Automation and Orchestration) instances and an AI science manager. The platform's efficacy was demonstrated through a case study optimizing multi-step spectro-electrochemical experiments to identify optically stable potential windows in (Co–Ni–Sb)Oz metal oxides. The system successfully integrated AI-driven experiment design, remote laboratory automation, and cloud-based data infrastructure, validating the platform's capability for managing complex, adaptive, path-dependent workflows in materials discovery.
- Open Access
- 24 May 2025
- Published by Springer Nature in npj Computational Materials
- Vol. 11 (1) , 1-13
Probabilistic phase labeling and lattice refinement for autonomous materials research
- 24 May 2025
- Published by Springer Nature in npj Computational Materials
- Vol. 11 (1) , 1-13
Open AccessProbabilistic phase labeling and lattice refinement for autonomous materials research
- 22 August 2024
- Published by Royal Society of Chemistry (RSC) in Journal of Materials Chemistry A
- Vol. 12 (35) , 23122-23124
Advancing energy materials through high throughput experiments and computation
Moran Balaish, Helge S. Stein, Arghya Bhowmik, and John M. Gregoire introduce the Journal of Materials Chemistry A themed collection on advancing energy materials through high throughput experiments and computation.
- 22 August 2024
- Published by Royal Society of Chemistry (RSC) in Journal of Materials Chemistry A
- Vol. 12 (35) , 23122-23124
Advancing energy materials through high throughput experiments and computation
Moran Balaish, Helge S. Stein, Arghya Bhowmik, and John M. Gregoire introduce the Journal of Materials Chemistry A themed collection on advancing energy materials through high throughput experiments and computation.
- Open Access
- 5 August 2024
- Published by Royal Society of Chemistry (RSC) in Chemical Communications
- Vol. 60 (71) , 9554-9557
Automated monitoring of electrocatalyst corrosion as a function of electrochemical history and electrolyte formulation
We present an automated platform for studying electrode corrosion as a function of electrochemical history and electrolyte composition using Pt ORR as a proof-of-concept relevant to next-generation phosphoric acid fuel cells.
- 5 August 2024
- Published by Royal Society of Chemistry (RSC) in Chemical Communications
- Vol. 60 (71) , 9554-9557
Open AccessAutomated monitoring of electrocatalyst corrosion as a function of electrochemical history and electrolyte formulation
We present an automated platform for studying electrode corrosion as a function of electrochemical history and electrolyte composition using Pt ORR as a proof-of-concept relevant to next-generation phosphoric acid fuel cells.
- Open Access
- 30 April 2024
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 3 (6) , 1144-1149
Accelerated screening of gas diffusion electrodes for carbon dioxide reduction
Electrochemical reactors based on gas diffusion electrodes (GDE) enable high current densities for reactions such as CO2 reduction. AutoGDE is a platform for automating GDE experiments to accelerate catalyst discovery and reaction engineering.
- 30 April 2024
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 3 (6) , 1144-1149
Open AccessAccelerated screening of gas diffusion electrodes for carbon dioxide reduction
Electrochemical reactors based on gas diffusion electrodes (GDE) enable high current densities for reactions such as CO2 reduction. AutoGDE is a platform for automating GDE experiments to accelerate catalyst discovery and reaction engineering.
- Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (1) , 283-291
Conformal Crystal Graph Transformer with Robust Encoding of Periodic Invariance
Machine learning techniques, especially in the realm of materials design, hold immense promise in predicting the properties of crystal materials and aiding in the discovery of novel crystals with desirable traits. However, crystals possess unique geometric constraints—namely, E(3) invariance for primitive cell and periodic invariance—which need to be accurately reflected in crystal representations. Though past research has explored various construction techniques to preserve periodic invariance in crystal representations, their robustness remains inadequate. Furthermore, effectively capturing angular information within 3D crystal structures continues to pose a significant challenge for graph-based approaches. This study introduces novel solutions to these challenges. We first present a graph construction method that robustly encodes periodic invariance and a strategy to capture angular information in neural networks without compromising efficiency. We further introduce CrystalFormer, a pioneering graph transformer architecture that emphasizes angle preservation and enhances long-range information. Through comprehensive evaluation, we verify our model's superior performance in 5 crystal prediction tasks, reaffirming the efficiency of our proposed methods.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (1) , 283-291
Open AccessConformal Crystal Graph Transformer with Robust Encoding of Periodic Invariance
Machine learning techniques, especially in the realm of materials design, hold immense promise in predicting the properties of crystal materials and aiding in the discovery of novel crystals with desirable traits. However, crystals possess unique geometric constraints—namely, E(3) invariance for primitive cell and periodic invariance—which need to be accurately reflected in crystal representations. Though past research has explored various construction techniques to preserve periodic invariance in crystal representations, their robustness remains inadequate. Furthermore, effectively capturing angular information within 3D crystal structures continues to pose a significant challenge for graph-based approaches. This study introduces novel solutions to these challenges. We first present a graph construction method that robustly encodes periodic invariance and a strategy to capture angular information in neural networks without compromising efficiency. We further introduce CrystalFormer, a pioneering graph transformer architecture that emphasizes angle preservation and enhances long-range information. Through comprehensive evaluation, we verify our model's superior performance in 5 crystal prediction tasks, reaffirming the efficiency of our proposed methods.
- Open Access
- 11 March 2024
- Published by American Chemical Society (ACS) in ACS Energy Letters
- Vol. 9 (4) , 1440-1445
Electrode Surface Heating with Organic Films Improves CO2 Reduction Kinetics on Copper
Management of the electrode surface temperature is an understudied aspect of (photo)electrode reactor design for complex reactions, such as CO2 reduction. In this work, we study the impact of local electrode heating on electrochemical reduction of CO2 reduction. Using the ferri/ferrocyanide open circuit voltage as a reporter of the effective reaction temperature, we reveal how the interplay of surface heating and convective cooling presents an opportunity for cooptimizing mass transport and thermal assistance of electrochemical reactions, where we focus on reduction of CO2 to carbon-coupled (C2+) products. The introduction of an organic coating on the electrode surface facilitates well-behaved electrode kinetics with near-ambient bulk electrolyte temperature. This approach helps to probe the fundamentals of thermal effects in electrochemical reactions, as demonstrated through Bayesian inference of Tafel kinetic parameters from a suite of high throughput experiments, which reveal a decrease in overpotential for C2+ products by 0.1 V on polycrystalline copper via 60 °C surface heating.
- 11 March 2024
- Published by American Chemical Society (ACS) in ACS Energy Letters
- Vol. 9 (4) , 1440-1445
Open AccessElectrode Surface Heating with Organic Films Improves CO2 Reduction Kinetics on Copper
Management of the electrode surface temperature is an understudied aspect of (photo)electrode reactor design for complex reactions, such as CO2 reduction. In this work, we study the impact of local electrode heating on electrochemical reduction of CO2 reduction. Using the ferri/ferrocyanide open circuit voltage as a reporter of the effective reaction temperature, we reveal how the interplay of surface heating and convective cooling presents an opportunity for cooptimizing mass transport and thermal assistance of electrochemical reactions, where we focus on reduction of CO2 to carbon-coupled (C2+) products. The introduction of an organic coating on the electrode surface facilitates well-behaved electrode kinetics with near-ambient bulk electrolyte temperature. This approach helps to probe the fundamentals of thermal effects in electrochemical reactions, as demonstrated through Bayesian inference of Tafel kinetic parameters from a suite of high throughput experiments, which reveal a decrease in overpotential for C2+ products by 0.1 V on polycrystalline copper via 60 °C surface heating.