Scientific Machine Learning for Nuclear Engineering Applications

Price: $49

Westinghouse Electric Company recognizes the importance of supporting students pursuing a career in reactor physics. For this reason, Westinghouse will be sponsoring the first 100 student workshop registrants by covering their fees. Contact registrar@ans.org for a discount code before registering. Limited space available in each workshop. Once these seats are filled, you will be put on a waitlist. You must request a discount code before registering. No refunds will be made if you do not contact us before registering.

Organizer: Xu Wu, North Carolina State University

Machine Learning (ML) is a subset of Artificial Intelligence (AI) that studies computer algorithms which improve automatically through experience (data). ML algorithms typically build a mathematical model based on training data and then make predictions without being explicitly programmed to do so. Its performance increases with experience, in other words, the machine learns. AI/ML have achieved tremendous success in tasks such as computer vision, natural language processing, speech recognition, and audio synthesis, where the datasets are in the format of images, text, spoken words and videos. Meanwhile, their applications in engineering disciplines mostly focus on scientific data, which resulted in a burgeoning discipline called scientific machine learning (SciML) that blends scientific computing and ML. SciML brings together the complementary perspectives of computational science and computer science to craft a new generation of ML methods for complex applications across science and engineering. Examples of SciML include physics-informed ML, surrogate modeling & model reduction, Bayesian inverse problems, digital twins, and ML-based uncertainty, sensitivity, assimilation, and validation analysis.

The “SciML for Nuclear Engineering Applications” workshop series has been organized in M&C and PHYSOR conferences since 2021. The goal of this workshop series is to present the most recent advances on SciML applications in Nuclear Engineering, as well as to provide training on essential SciML research topics. We hope to augment the applications of AI/ML in scientific computing and preparing the students for driving the next wave of data-driven scientific discovery in Nuclear Engineering. In this workshop, we will have five presentations that cover a wide range of topics, from fundamental SciML topics on an educational perspective to most recent research developments in SciML in various Nuclear Engineering areas. Participants do not need a laptop for this workshop.

Agenda:

• Latent Neural Controlled Differential Equations for Time Series Forecasting (William Gurecky, ORNL)
• Sparse Sensing and Sparse Learning for Nuclear Digital Twins (Mohammad Abdo, INL)
• Neutron Flux Measurement and Thermal Limits modeling: Impact on operational performance (Thomas Gruenwald, Blue Wave AI Labs)
• Physics-informed, data-driven reduced-order models for nuclear applications (Jean Ragusa, TAMU)
• Causal inference as a bridge between simulation models and observed phenomena (Diego Mandelli, INL)

Resources

To access session resources, you must be logged in and registered for the meeting.

Register NowLog In

Discussion

To join the conversation, you must be logged in and registered for the meeting.

Register NowLog In