DS Ph.D. Dissertation Proposal | Biao Yin | Monday, Dec. 4th @ 11:00am

Monday, December 4, 2023
11:00 am to 12:00 pm

Ph.D. Dissertation Proposal 

Biao Yin, Ph.D. Candidate 

Monday, December 4, 2023 | 11:00AM - 12:00PM, EST 

Zoom Meeting Link:


Dissertation Committee: 

Dr. Elke Rundensteiner, Professor, WPI (Advisor)​ 

Dr. Ziming Zhang, Assistant Professor, WPI​ (Co-Advisor) 

Dr. Jian (Frank) Zou, Associate Professor, WPI ​ 

Dr. Robert Jensen, Team Lead of Materials Data Science, DEVCOM Army Research Lab​ 


Facilitating Scientific Material Discovery via Deep Learning on Small Image Datasets 


Scientific material discovery, important for economic prosperity and well-being from transportation, construction, and security, to healthcare; has traditionally been tackled both by intensive mathematical modeling and extensive physical experimentation. Recently, popular deep learning models have emerged as a promising solution approach; however, challenges remaining include overfitting due to the typically small size of datasets in this domain, tiny but critical pixels, strong false positives, lack of domain knowledge, etc. In this dissertation, I tackle four particular directions of research related to deep learning models on experimental complex data such as images derived from real-world projects for scientific material discovery. In the first part, we designed and developed the first open-source corrosion image dataset, annotated for data-driven automation in scientific corrosion assessment using expert labeling. Using this dataset, we built an AI platform, incorporating our published deep learning model, for corrosion rating, data collection, exchange, and visual analytics. In part 2, we focused on supervised deep-learning models for image-based scientific corrosion assessment on existing alloys. Techniques like augmentation, transfer learning, and self-supervised learning were incorporated into the solution to improve its effectiveness. In particular, we design a deep learning model that is augmented by a novel edge guidance submodel putting attention on high-level edge shapes outperform SOTA methods such as MedTransformer on our small data. In part 3, we propose to use generative supervised learning to improve ordinal regression for long-tailed corrosion assessment on unseen alloys. In part 4, we propose a domain-promptable AlloyGAN model to generate microstructure images of unseen alloys from chemical and manufacturing conditions. By injecting domain knowledge, my research will enable material scientists to better deal with non-existent alloys via real-time and scientifically validated material simulation and assessment.

This work is based on a collaboration with material scientists at the DEVCOM Army Research Laboratory (ARL) - with the later testing and working with the resulting technology. In a 3-way collaboration between ARL, WPI, and ASM, the technology is being transitioned into practice for marketing and release by ASM. In general, the application of AI techniques to material science challenges promises to save time and effort for scientific material discovery. We thank ARL, NSF, and DoE for sponsoring this research.  



Data Science
Contact Person
Kelsey Briggs