Anon Photo

Pawan Tripathi

Research Assistant Professor, Materials Science and Engineering

Develop data analysis techniques, tools, and pipelines for high dimensional datasets in materials science such as synchrotron XRD, XCT, and advanced manufacturing to reveal insights, and correlations and improve predictive modeling leveraging deep learning, artificial intelligence, and statistical methods.

Materials Data Science, Advanced Manufacturing, Synchrotron Data Analysis, Image Processing, Deep Learning, Artificial Intelligence, Uncertainty Quantification, Atomistic Simulation

Office: 550, White Building
Delivery Address: 550 White Building 10900 Euclid Ave, Cleveland, OH, USA 44106

Education

Ph.D, Dual Degree, Materials Science and Engineering, Indian Institute of Technology Kanpur, India and National Chiao Tung University Taiwan , 2021
M.Tech, Metallurgical and Materials Science and Engineering, Indian Institute of Technology, Roorkee, India, 2014

Research Interests

My current research interests are in Materials Data Science and advanced analytical techniques, focusing on spatio-temporal analytics of synchrotron beamline X-ray diffraction (XRD) and X-ray computed tomography (XCT) data. I develop automated analysis pipelines to expedite processing and interpretation of complex datasets from synchrotron experiments. Utilizing image processing and machine-learning models, I extract scientific insights, with emphasis on semantic segmentation using deep learning architectures like UNet. Additionally, I advance Materials Data Science in Advanced Manufacturing, employing methodologies to uncover correlations and enhance predictive modeling on high-dimensional datasets through image processing, deep learning, and statistical modeling. I ensure adherence to FAIR principles in Materials Data-FAIRification, developing ontologies and schemas for various domains, including additive manufacturing, XCT analysis, and XRD analysis. Furthermore, I explore Atomistic Simulation using High-Performance Computing for investigating phase transformation and deformation behavior at the atomic scale, employing large-scale molecular dynamics simulations in LAMMPS and density functional theory in VASP and Quantum-Espresso to understand material properties. Through multidisciplinary research, I aim to contribute to materials science and engineering, addressing challenges in manufacturing, characterization, and computational modeling.

Teaching Interests

DSCI 352/452 Applied Data Science Project-Based Course; DSCI 351/451 Exploratory Data Analysis - Guest Lecturer; CSDS: Intro to Data Science- Guest Lecturer

Job Description