Rajat Sainju

.
CV | Google Scholar | LinkedIn | Github | Email: rajat.sainju@uconn.edu

I am a Ph.D. student in the Department of Material Science and Engineering at the University of Connecticut where I am advised by Professor Yuanyuan Zhu. In my research, I work on developing image processing (deep learning and traditional computer vision) algorithms for automated analysis of in-situ transmission electron microscopy videos/images and establish TEM benchmark datasets. My work also focuses on understanding the material dynamics of metal catalyst nanoparticles in oxidation and reduction conditions, high-temperature oxidation mechanism of refractory metals, and nuclear irradiation effects on reactor structural alloys.

I completed my undergraduate education at Ramapo College majoring in Engineering Physics with minors in Computer Science and Mathematics.

Publications

Materials Science

• DefectTrack: a deep learning-based multi-object tracking algorithm for quantitative defect analysis of in-situ TEM videos in real-time
  Rajat Sainju, Wei‑Ying Chen, Samuel Schaefer, Qian Yang, Caiwen Ding, Meimei Li, and Yuanyuan Zhu*
  Scientific Reports (2022)

• In Situ Studies of Single-Nanoparticle-Level Nickel Thermal Oxidation: From Early Oxide Nucleation to Diffusion-Balanced Oxide Thickening
  Rajat Sainju, Dinithi Rathnayake, Haiyan Tan, George Bollas, Avinash M. Dongare, Steven L. Suib, and Yuanyuan Zhu*
  ACS Nano (2022)

• Automated Quantitative Analysis of Extended Irradiation Defects – Dislocation Lines, Loops, Voids and Precipitates in Neutron Irradiated HT-9 Steel
  in preparation

• Direction observation of tungsten oxidation studied by in situ environmental TEM
  Maanas Togaru, Rajat Sainju, Lichun Zhang, Weilin Jiang, Yuanyuan Zhu.
  Materials Characterization (2021)

• Deep learning for semantic segmentation of defects in advanced STEM images of steels
  Graham Roberts, Simon Y Haile, Rajat Sainju, Danny J Edwards, Brian Hutchinson, Yuanyuan Zhu
  Scientific Reports (2019)

Deep Learning

• Detecting Gender Bias in Transformer-based Models: A Case Study on BERT
  Bingbing Li, Hongwu Peng, Rajat Sainju, Yueuing Liang, Junhuan Yang, Lei Yang, Weiwen Jiang, Binghui Wang, Hang Liu, Caiwen Ding
  arXiv preprint arXiv:2110.15733 (2021)

Conference Proceedings

• Deep Learning-based Computer Vision for Radiation Defect Analysis: from Static Defect Segmentation to Dynamic Defect Tracking
  Rajat Sainju, Wei-Ying Chen, Samuel Schaefer, Graham Roberts, Mychailo Toloczko, Danny Edwards, Meimei Li, Yuanyuan Zhu.
  Microscopy and Microanalysis (2021)

• Tracking and Understanding Nanocatalyst Sintering and Regeneration using Deep Learning-assisted In Situ Environmental TEM
  Rajat Sainju, Steven Suib, Caiwen Ding, Yuanyuan Zhu.
  Microscopy and Microanalysis (2021)

• Towards an End-to-end Radiation Defect Quantitative Characterization Workflow Using Advanced Microscopy Images
  Rajat Sainju, Graham Roberts, Colin Ophus, Brian Hutchinson, Jing Wang, Mychailo B Toloczko, Richard J Kurtz, Charles H Henager, Danny J Edwards, Yuanyuan Zhu
  Microscopy and Microanalysis (2020)

• Automated Quantitative Analysis of Extended Irradiation Defects-Dislocations, Voids and Precipitates in Neutron Irradiated HT-9 Steel
  Rajat Sainju, Colin Ophus, Mychailo B Toloczko, Danny J Edwards, Yuanyuan Zhu.
  Microscopy and Microanalysis (2019)

• DefectNet–A Deep Convolutional Neural Network for Semantic Segmentation of Crystallographic Defects in Advanced Microscopy Images
  Graham Roberts, Rajat Sainju, Brian Hutchinson, Mychailo B Toloczko, Danny J Edwards, Yuanyuan Zhu
  Microscopy and Microanalysis (2019)

Teaching

I have served as a teaching assistant for the following courses at the University of Connecticut.

• MSE 4097: Introduction to Research - Fall 2021
• MSE 3002: Transport Phenomena in Materials Processing - Spring 2020
• MSE 5301: Thermodynamics of Materials - Fall 2019