University of Wisconsin-Madison, United States
Lane E. Schultz, Ph.D. is a materials scientist and engineer specializing in computational materials science, with a focus on machine learning applications in materials research. He recently completed his Ph.D. at the University of Wisconsin-Madison and has a robust portfolio in high-performance computing, metallic glass research, and advanced simulations. Lane is skilled in various programming languages and tools, such as Python, C++, Docker, and Linux, contributing to his success in both academic and industry projects.
Profile
Scopus
Orcid
Education 🎓
Lane earned his Ph.D. in Materials Science and Engineering from the University of Wisconsin-Madison in 2024, with a GPA of 3.70/4.0. Prior to that, he completed his M.S. in Materials Science and Engineering at the same institution in 2020, also with a 3.70 GPA. He began his academic career with a B.S. in Engineering from Fort Lewis College in 2017, graduating with a stellar GPA of 3.99/4.0. Lane’s academic journey has been marked by excellence, earning multiple awards for his scholarly achievements.
Experience 🛠️
Lane has extensive research experience, including a pivotal role as a Research Assistant at the Computational Materials Group at UW-Madison (2018-2024). During this time, he contributed to the development of a domain of applicability method for machine learning models in materials science, enabling better prediction of material properties. Additionally, he was instrumental in constructing and managing scientific computing clusters and developed a high-throughput workflow to model metallic glass forming ability. Lane’s experience also extends to hands-on experimental work during his Summer Undergraduate Research Fellowships at Purdue and Fort Lewis College, where he developed Python tools and designed sensor packages.
Research Interests 🔬
1. Machine Learning for Materials Property Prediction & Applicability Domain Assessment
Lane’s research focuses on integrating machine learning techniques to predict material properties more accurately and efficiently. A significant part of his work involves developing methods to assess the applicability domain of these machine learning models, ensuring that predictions are reliable and robust across different datasets. This approach helps identify the boundaries within which models can make accurate predictions, enhancing the trustworthiness of AI-driven materials science.
2. High-Throughput Simulations for Metallic Glass Formation
Lane specializes in using high-throughput simulations to explore the formation of metallic glasses. By leveraging large-scale computational models, he aims to predict critical cooling rates and other factors that influence glass formation. His work in this area contributes to a deeper understanding of the atomic-level behaviors that dictate the properties of metallic glasses, which are essential for developing new materials with unique mechanical and thermal properties.
3. Materials Informatics for Data-Driven Methodologies
Combining his expertise in computational materials science and informatics, Lane develops data-driven methodologies to accelerate materials discovery. His research in materials informatics involves building algorithms that can extract patterns and insights from extensive materials datasets. By applying these insights, Lane helps streamline the process of identifying novel materials with desirable properties, pushing the boundaries of what’s possible in materials engineering.
Awards 🏆
PPG Fellowship, University of Wisconsin-Madison
Ying Yu Chuang Graduate Support Award, UW-Madison
Sigma Pi Sigma, Physics Honor Society
Order of the Engineer, Fort Lewis College
Dean’s Council Freshman 4.0 Award, Fort Lewis College
Publications Top Notes 📚
Machine learning metallic glass critical cooling rates through elemental and molecular simulation-based featurization. Journal of Materiomics (2024). Link
Molecular dynamic characteristic temperatures for predicting metallic glass forming ability. Computational Materials Science (2022). Link
Accelerating ensemble uncertainty estimates in supervised materials property regression models. Computational Materials Science (2025). Link
Foundry-ML - Software and Services to Simplify Access to Machine Learning Datasets in Materials Science. Journal of Open Source Software (2024). Link
Machine Learning Prediction of the Critical Cooling Rate for Metallic Glasses from Expanded Datasets and Elemental Features. Chemistry of Materials (2022). Link