A Gilad Kusne

A Gilad Kusne

University of Maryland, Baltimore

H-index: 23

North America-United States

About A Gilad Kusne

A Gilad Kusne, With an exceptional h-index of 23 and a recent h-index of 22 (since 2020), a distinguished researcher at University of Maryland, Baltimore, specializes in the field of Machine Learning, Solid State Physics, Sensors.

His recent articles reflect a diverse array of research interests and contributions to the field:

Human-in-the-loop for Bayesian autonomous materials phase mapping

Artificial Intelligence for Materials

AI for Materials

Live Autonomous Beamline Experiments: Physics In the Loop

Semi and Self Supervised approaches to Space Group and Bravais Lattice Determination

ANDiE the Autonomous Neutron Diffraction Explorer

Learning material synthesis-structure-property relationship by data fusion: Bayesian Co-regionalization N-Dimensional Piecewise Function Learning

aflow plus plus: AC plus plus framework for autonomous materials design

A Gilad Kusne Information

University

University of Maryland, Baltimore

Position

Materials Measurement & Science Division NIST & Materials Science & Engineering

Citations(all)

3883

Citations(since 2020)

3171

Cited By

1762

hIndex(all)

23

hIndex(since 2020)

22

i10Index(all)

31

i10Index(since 2020)

29

Email

University Profile Page

University of Maryland, Baltimore

A Gilad Kusne Skills & Research Interests

Machine Learning

Solid State Physics

Sensors

Top articles of A Gilad Kusne

Human-in-the-loop for Bayesian autonomous materials phase mapping

Authors

Felix Adams,Austin McDannald,Ichiro Takeuchi,A Gilad Kusne

Journal

Matter

Published Date

2024/2/7

Autonomous experimentation combines machine learning and laboratory automation to select and perform experiments toward user goals. Accordingly, materials optimization using autonomous experimentation requires fewer experiments and less time than Edisonian studies. Integrating knowledge from theory, simulations, literature, and human intuition into the machine learning model can further increase this advantage. We present a set of methods for integrating human input into an autonomous materials exploration campaign for composition-structure phase mapping. The methods are demonstrated on X-ray diffraction data collected from a thin-film ternary combinatorial library. During the campaign, the user can provide input by indicating potential phase boundaries or phase regions with their uncertainty or indicate regions of interest. The input is then integrated through probabilistic priors, resulting in a …

Artificial Intelligence for Materials

Authors

Debra J Audus,Kamal Choudhary,Brian L DeCost,A Gilad Kusne,Francesca Tavazza,James A Warren

Published Date

2023

The following sections are included: Introduction AI Allows You to Make a Material Model Application Modalities Autonomous Science Challenges Conclusion and Outlook References

AI for Materials

Authors

Debra Audus,Kamal Choudhary,Brian DeCost,A Gilad Kusne,Francesca Tavazza,James A Warren

Published Date

2023/4/25

The application of artificial intelligence (AI) methods to materials re-search and development (MR&D) is poised to radically reshape how materials are discovered, designed, and deployed into manufactured products. Materials underpin modern life, and advances in this space have the potential to markedly increase the quality of human life, address pressing environmental issues, and provide new, enabling, technologies that can help people realize their potential. This chapter delves into the many ways that AI is currently being applied to accelerate MR&D, the implications of this revolution, and the new frontiers that are now being opened for exploration.

Live Autonomous Beamline Experiments: Physics In the Loop

Authors

A Gilad Kusne,Austin McDannald,Ichiro Takeuchi

Published Date

2023/12/14

In an APS, machine learning (ML) controls automated laboratory equipment, allowing for ML-driven experiment design, execution, and analysis in a closed loop. The ML-driven closed-loop experiment cycle of APS promises to allow researchers to perform the minimum number of experiments necessary to explore the search space and identify improved technology-relevant materials. The pipeline begins with data collection from the experimentfollowed by preprocessing the data to increase its utility for the experiment. Based on closed-loop results of the APS system, the pipeline is re-engineered to improve performance. Designing the machine learning pipeline requires the selection of multiple algorithms. A common first step is to identify easy-to-use, off-the-shelf machine learning tools that can be assembled into a preliminary ML pipeline.

Semi and Self Supervised approaches to Space Group and Bravais Lattice Determination

Authors

William Ratcliff,Satvik Lolla,Ichiro Takeuchi,Aaron Kusne,Haotong Liang

Journal

APS March Meeting Abstracts

Published Date

2023

During this talk, I will discuss our work [1] to use neural networks to automatically classifiy Bravais lattices and space-groups from neutron powder diffraction data. Our work classifies 14 Bravais lattices and 144 space groups. The novelty of our approach is to use semi-supervised and self-supervised learning to allow for training on data sets with unlabelled data as is common at user facilities. We achieve state of the art results with a semi-supervised approach. Our accuracy for our self-supervised training is comparable to that with a supervised approach.

ANDiE the Autonomous Neutron Diffraction Explorer

Authors

Austin McDannald,Matthias D Frontzek,Andrei T Savici,Mathieu Doucet,Efrain E Rodriguez,Kate Meuse,Jessica Opsahl-Ong,Daniel Samarov,Ichiro Takeuchi,William Ratcliff,A Gilad Kusne

Journal

Neutron News

Published Date

2023/4/3

Here, we developed the Autonomous Neutron Diffraction Explorer (ANDiE) to autonomously perform neutron diffraction measurements to discover the magnetic ordering behavior in a material. Neutron diffraction is one of the few techniques that can directly probe the magnetic ordering of the atoms in a material. As such beamtime at neutron diffraction facilities is in high demand.

Learning material synthesis-structure-property relationship by data fusion: Bayesian Co-regionalization N-Dimensional Piecewise Function Learning

Authors

A Gilad Kusne,Austin McDannald,Brian DeCost

Journal

arXiv preprint arXiv:2311.06228

Published Date

2023/11/10

Advanced materials are needed to further next-generation technologies such as quantum computing, carbon capture, and low-cost medical imaging. However, advanced materials discovery is confounded by two fundamental challenges: the challenge of a high-dimensional, complex materials search space and the challenge of combining knowledge, i.e., data fusion across instruments and labs. To overcome the first challenge, researchers employ knowledge of the underlying material synthesis-structure-property relationship, as a material's structure is often predictive of its functional property and vice versa. For example, optimal materials often occur along composition-phase boundaries or within specific phase regions. Additionally, knowledge of the synthesis-structure-property relationship is fundamental to understanding underlying physical mechanisms. However, quantifying the synthesis-structure-property relationship requires overcoming the second challenge. Researchers must merge knowledge gathered across instruments, measurement modalities, and even laboratories. We present the Synthesis-structure-property relAtionship coreGionalized lEarner (SAGE) algorithm. A fully Bayesian algorithm that uses multimodal coregionalization to merge knowledge across data sources to learn synthesis-structure-property relationships.

aflow plus plus: AC plus plus framework for autonomous materials design

Authors

Corey Oses,Marco Esters,David Hicks,Simon Divilov,Hagen Eckert,Rico Friedrich,Michael J Mehl,Andriy Smolyanyuk,Xiomara Campilongo,Axel van de Walle,Jan Schroers,A Gilad Kusne,Ichiro Takeuchi,Eva Zurek,Marco Buongiorno Nardelli,Marco Fornari,Yoav Lederer,Ohad Levy,Cormac Toher,Stefano Curtarolo

Journal

COMPUTATIONAL MATERIALS SCIENCE

Published Date

2023/1/25

The realization of novel technological opportunities given by computational and autonomous materials design requires efficient and effective frameworks. For more than two decades, aflow++ (Automatic -Flow Framework for Materials Discovery) has provided an interconnected collection of algorithms and workflows to address this challenge. This article contains an overview of the software and some of its most heavily -used functionalities, including algorithmic details, standards, and examples. Key thrusts are highlighted: the calculation of structural, electronic, thermodynamic, and thermomechanical properties in addition to the modeling of complex materials, such as high-entropy ceramics and bulk metallic glasses. The aflow++ software prioritizes interoperability, minimizing the number of independent parameters and tolerances. It ensures consistency of results across property sets - facilitating machine learning …

Learning material synthesis-process-structure-property relationship by data fusion: Bayesian Coregionalization N-Dimensional Piecewise Function Learning

Authors

A Gilad Kusne,Austin McDannald,Brian DeCost

Journal

arXiv e-prints

Published Date

2023/11

Autonomous materials research labs require the ability to combine and learn from diverse data streams. This is especially true for learning material synthesis-process-structure-property relationships, key to accelerating materials optimization and discovery as well as accelerating mechanistic understanding. We present the Synthesis-process-structure-property relAtionship coreGionalized lEarner (SAGE) algorithm. A fully Bayesian algorithm that uses multimodal coregionalization to merge knowledge across data sources to learn synthesis-process-structure-property relationships. SAGE outputs a probabilistic posterior for the relationships including the most likely relationships given the data.

aflow++: A C++ framework for autonomous materials design

Authors

Corey Oses,Marco Esters,David Hicks,Simon Divilov,Hagen Eckert,Rico Friedrich,Michael J Mehl,Andriy Smolyanyuk,Xiomara Campilongo,Axel van de Walle,Jan Schroers,A Gilad Kusne,Ichiro Takeuchi,Eva Zurek,Marco Buongiorno Nardelli,Marco Fornari,Yoav Lederer,Ohad Levy,Cormac Toher,Stefano Curtarolo

Journal

Computational Materials Science

Published Date

2023/1/25

The realization of novel technological opportunities given by computational and autonomous materials design requires efficient and effective frameworks. For more than two decades, aflow++ (Automatic-Flow Framework for Materials Discovery) has provided an interconnected collection of algorithms and workflows to address this challenge. This article contains an overview of the software and some of its most heavily-used functionalities, including algorithmic details, standards, and examples. Key thrusts are highlighted: the calculation of structural, electronic, thermodynamic, and thermomechanical properties in addition to the modeling of complex materials, such as high-entropy ceramics and bulk metallic glasses. The aflow++ software prioritizes interoperability, minimizing the number of independent parameters and tolerances. It ensures consistency of results across property sets — facilitating machine learning …

Scalable multi-agent lab framework for lab optimization

Authors

A Gilad Kusne,Austin McDannald

Journal

Matter

Published Date

2023/6/7

Autonomous materials research systems allow scientists to fail smarter, learn faster, and spend less resources in their studies. As these systems grow in number, capability, and complexity, a new challenge arises—how will they work together across large facilities? We explore one solution—a multi-agent laboratory-control framework. The framework is demonstrated with autonomous materials science labs in mind, where information from diverse research campaigns can be combined to address scientific questions. The framework can (1) account for realistic resource limits, e.g., equipment use; (2) allow for research-campaign-running machine-learning agents with diverse learning capabilities and goals; and (3) facilitate multi-agent collaborations and teams. The multi-agent autonomous facilities scalable framework (MULTITASK) makes possible facility-wide simulations, including agent-instrument and agent-agent …

Autonomous Materials Science

Authors

Aaron Kusne

Journal

APS March Meeting Abstracts

Published Date

2023

The last few decades have seen significant advancements in materials research tools, allowing scientists to rapidly synthesis and characterize large numbers of samples-a major step toward high-throughput materials discovery. Autonomous research systems take the next step, placing synthesis and characterization under control of machine learning. For such systems, machine learning controls experiment design, execution, and analysis, thus accelerating knowledge capture while also reducing the burden on experts. Furthermore, physical knowledge can be built into the machine learning, reducing the expertise needed by users, with the promise of eventually democratizing science. In this talk I will discuss autonomous systems being developed between NIST and collaborators. Examples include the first autonomous discovery of a best-in-class solid-state material, an autonomous system that merges live …

A framework for materials informatics education through workshops

Authors

Arun Mannodi-Kanakkithodi,Austin McDannald,Shijing Sun,Saaketh Desai,Keith A Brown,A Gilad Kusne

Published Date

2023/5

The burgeoning field of materials informatics necessitates a focus on educating the next generation of materials scientists in the concepts of data science, artificial intelligence (AI), and machine learning (ML). In addition to incorporating these topics in undergraduate and graduate curricula, regular hands-on workshops present the most effective medium to initiate researchers to informatics and have them start applying the best AI/ML tools to their own research. With the help of the Materials Research Society (MRS), members of the MRS AI Staging Committee, and a dedicated team of instructors, we successfully conducted workshops covering the essential concepts of AI/ML as applied to materials data, at both the Spring and Fall Meetings in 2022, with plans to make this a regular feature in future meetings. In this article, we discuss the importance of materials informatics education via the lens of these workshops …

Scalable Multi-Agent Framework for Optimizing the Lab and Warehouse.

Authors

A Gilad Kusne,Austin McDannald

Journal

arXiv e-prints

Published Date

2022/8

Autonomous materials research systems allow scientists to fail smarter, learn faster, and spend less resources in their studies. As these systems grow in number, capability, and complexity, a new challenge arises-how will they work together across large facilities? We explore one solution to this question-a multi-agent laboratory control frame-work. We demonstrate this framework with an autonomous material science lab in mind-where information from diverse research campaigns can be combined to ad-dress the scientific question at hand. This framework can 1) account for realistic resource limits such as equipment use, 2) allow for machine learning agents with diverse learning capabilities and goals capable of running re-search campaigns, and 3) facilitate multi-agent collaborations and teams. The framework is dubbed the MULTI-agent auTonomous fAcilities-a Scalable frameworK aka MULTITASK. MULTITASK …

The LEGOLAS Kit: A low-cost robot science kit for education with symbolic regression for hypothesis discovery and validation

Authors

Logan Saar,Haotong Liang,Alex Wang,Austin McDannald,Efrain Rodriguez,Ichiro Takeuchi,A Gilad Kusne

Published Date

2022/9

The need for robotic science is growing rapidly, as exemplified by a central challenge of materials discovery. Advances in technology often require better materials. However, scientists are quickly exhausting the materials that are simpler to make, that is, materials of simple stoichiometry (few elements) and few processing steps. As a result, scientists are driven to explore materials of greater complexity. With each new synthesis or processing parameter, the number of possible materials grows exponentially. This growing number of materials holds great promise but comes with a significant challenge—a rapidly growing number of materials to explore. The traditional Edisonian search for better materials consists of one-by-one materials synthesis, characterization, and data analysis.This approach to materials discovery becomes infeasible as the search space grows. High-throughput methods 1 and machine learning …

Teaching machine learning to materials scientists: Lessons from hosting tutorials and competitions

Authors

Shijing Sun,Keith Brown,A Gilad Kusne

Journal

Matter

Published Date

2022/6/1

The growing field of data-driven materials research poses a challenge to educators: teaching machine learning to materials scientists. We share our recent experiences and lessons learnt from organizing educational sessions at the fall 2021 meeting of the Materials Research Society.

Benchmarking active learning strategies for materials optimization and discovery

Authors

Alex Wang,Haotong Liang,Austin McDannald,Ichiro Takeuchi,Aaron Gilad Kusne

Journal

Oxford Open Materials Science

Published Date

2022

Autonomous physical science is revolutionizing materials science. In these systems, machine learning (ML) controls experiment design, execution and analysis in a closed loop. Active learning, the ML field of optimal experiment design, selects each subsequent experiment to maximize knowledge toward the user goal. Autonomous system performance can be further improved with the implementation of scientific ML, also known as inductive bias-engineered artificial intelligence, which folds prior knowledge of physical laws (e.g. Gibbs phase rule) into the algorithm. As the number, diversity and uses for active learning strategies grow, there is an associated growing necessity for real-world reference datasets to benchmark strategies. We present a reference dataset and demonstrate its use to benchmark active learning strategies in the form of various acquisition functions. Active learning strategies are used to …

A semi-supervised deep-learning approach for automatic crystal structure classification

Authors

Satvik Lolla,Haotong Liang,A Gilad Kusne,Ichiro Takeuchi,William Ratcliff

Journal

Journal of Applied Crystallography

Published Date

2022/8/1

The structural solution problem can be a daunting and time-consuming task. Especially in the presence of impurity phases, current methods, such as indexing, become more unstable. In this work, the novel approach of semi-supervised learning is applied towards the problem of identifying the Bravais lattice and the space group of inorganic crystals. The reported semi-supervised generative deep-learning model can train on both labeled data, i.e. diffraction patterns with the associated crystal structure, and unlabeled data, i.e. diffraction patterns that lack this information. This approach allows the models to take advantage of the troves of unlabeled data that current supervised learning approaches cannot, which should result in models that can more accurately generalize to real data. In this work, powder diffraction patterns are classified into all 14 Bravais lattices and 144 space groups (the number is limited due to …

On-the-fly autonomous control of neutron diffraction via physics-informed Bayesian active learning

Authors

Austin McDannald,Matthias Frontzek,Andrei T Savici,Mathieu Doucet,Efrain E Rodriguez,Kate Meuse,Jessica Opsahl-Ong,Daniel Samarov,Ichiro Takeuchi,William Ratcliff,A Gilad Kusne

Journal

Applied Physics Reviews

Published Date

2022/6/1

We demonstrate the first live, autonomous control over neutron diffraction experiments by developing and deploying ANDiE: the autonomous neutron diffraction explorer. Neutron scattering is a unique and versatile characterization technique for probing the magnetic structure and behavior of materials. However, instruments at neutron scattering facilities in the world is limited, and instruments at such facilities are perennially oversubscribed. We demonstrate a significant reduction in experimental time required for neutron diffraction experiments by implementation of autonomous navigation of measurement parameter space through machine learning. Prior scientific knowledge and Bayesian active learning are used to dynamically steer the sequence of measurements. We show that ANDiE can experimentally determine the magnetic ordering transition of both MnO and Fe1. 09Te all while providing a fivefold …

Novel Nanocomposite Phase-Change Memory Materials and Design and Selection of the Same

Published Date

2022/12/22

Provided herein are novel materials, such as novel phase change memory materials providing superior characteristics, and methods of discovering/selecting such novel materials via machine learning, such as Bayesian active learning. An exemplary material provided by the inventive concept is the nanocomposite phase-change memory material Ge_Sb Ten, selected using closed-loop autonomous materials explora tion and optimization (CAMEO).

See List of Professors in A Gilad Kusne University(University of Maryland, Baltimore)

A Gilad Kusne FAQs

What is A Gilad Kusne's h-index at University of Maryland, Baltimore?

The h-index of A Gilad Kusne has been 22 since 2020 and 23 in total.

What are A Gilad Kusne's top articles?

The articles with the titles of

Human-in-the-loop for Bayesian autonomous materials phase mapping

Artificial Intelligence for Materials

AI for Materials

Live Autonomous Beamline Experiments: Physics In the Loop

Semi and Self Supervised approaches to Space Group and Bravais Lattice Determination

ANDiE the Autonomous Neutron Diffraction Explorer

Learning material synthesis-structure-property relationship by data fusion: Bayesian Co-regionalization N-Dimensional Piecewise Function Learning

aflow plus plus: AC plus plus framework for autonomous materials design

...

are the top articles of A Gilad Kusne at University of Maryland, Baltimore.

What are A Gilad Kusne's research interests?

The research interests of A Gilad Kusne are: Machine Learning, Solid State Physics, Sensors

What is A Gilad Kusne's total number of citations?

A Gilad Kusne has 3,883 citations in total.

    academic-engine

    Useful Links