Name: Yumeng Wang
Pronouns: she/her/hers
Institution: Missouri University of Science and Technology
Department: Mathematics and Statistics
Biography:
I am a third-year Ph.D. candidate at the Department of Mathematics and Statistics of Missouri University of Science and Technology (Missouri S&T). My research interests include data driven modeling and simulation, and scientific machine learning, for instance generative models, reduced order models in solving PDEs. Before joining Missouri S&T, I obtained my master degree. And i had worked as a data analyst in financial industry for over two years, specializing in risk management with machine learning and data analysis techniques.
Academic Status: PhD Student
Year in program: 3rd
Research Area/Department: Applied Mathematics; Data Science; Machine Learning/AI
Other, specify:
Major/Specialty: Computational and Applied Mathematics
Degrees Earned or in Progress: Doctor of Philosophy in Computational and Applied Mathematics (Expected 2025). Master of Management in Management Science and Engineering (2019). Bachelor of Management in Engineering Management (2015).
What courses or academic preparation have you completed to prepare for a summer internship experience?
I have taken a series of computational and applied mathematics and computer sciences courses, including Machine Learning in Computer Vision, Mathematics of Machine Learning, and Nonlinear Optimization in Machine Learning. Besides taking courses, I have research experience working on two projects. Both of them are related to scientific machine learning.
Have you published any research or worked on research/technical projects? Yes
Where has your research been published or where have you conducted research/technical projects? During my Ph.D. study, I have been working on two projects related to scientific machine learning: (1) Data-driven modeling with generative adversarial networks (2) Learning temporal evolution of parameterized PDEs with convolutional neural networks. Both are in preparation and to be submitted in 2023.
Please describe your research/academic interests:
My research focuses on data-driven modeling and simulation and scientific machine learning, particularly implementing neural networks in differential equations. I specialize in leveraging deep neural networks, generative models, and reduced order models for solving partial differential equations. Additionally, I am also interested in other deep learning techniques like graph neural networks, reinforcement learning, and diffusion models, aiming to implement for future research.
Computational and Data Science Areas:
Applied Mathematics; Computational Science Applications, i.e., Bioscience, Cosmology, Chemistry, Environmental Science, Nanotechnology, Climate, etc.; Data Analytics and Visualization; Machine Learning and AI
Research Synergy:
My research focuses on scientific machine learning, a field that aligns exceptionally well with these techniques. These promising and intriguing algorithms possess significant potential for addressing practical problems that traditional methods may be trapped. It provides a new approach and new perspective and I am into these techniques for new applications. Furthermore, some of these cutting-edge techniques have been developed from top scientists in DOE labs. It’s an invaluable opportunity to collaborate with them.
Motivation:
My motivation to participate in SPR program is threefold. Firstly, I am driven by a strong desire to learn the most cutting-edge algorithms and improve my problem-solving skills. Furthermore, the opportunity to collaborate with top scientists in computational mathematics, machine learning, and data science is invaluable to me. Lastly, I see this program as a chance to broaden my horizons and deepen my understanding of AI in solving practical problems.
Lightning Talk Title: Parametric Model Reduction with Neural Networks