University of Texas at Austin

Upcoming Event: Oden Institute Seminar

Path Loss Prediction with Physics-Informed Neural Networks

Jian Tao, Assistant Director, Project Development, Texas A&M Institute of Data Science and Professor, School of Performance, Visualization & Fine Arts, Texas A&M University

3:30 – 5PM
Tuesday Dec 6, 2022

POB 6.304 & Zoom

Abstract

The mobile data traffic that relies on the propagation of radio waves plays an ever-growing important role in our daily life. Scientists and engineers have been using theory-driven propagation models to help design and optimize wireless network systems by predicting path characteristics and losses in a given environment. However, for practical cases, traditional path loss models are usually not so accurate and/or compute expensive. In this talk, I will present our work to develop a path loss simulator with physics-informed neural networks and its potential applications in a test bed for communication devices. More background about the research can be found at https://tx.ag/nistpsiap2022.

Biography

Dr. Jian Tao is an Assistant Professor in the School of Performance, Visualization and Fine Arts at Texas A&M University and the Assistant Director for Project Development at the Texas A&M Institute of Data Science. Tao received his Ph.D. in Computational Astrophysics from Washington University in St. Louis in 2008 and worked on computational frameworks for numerical relativity, computational fluid dynamics, coastal modeling, and other applications at Louisiana State University before he joined Texas A&M in 2016. In 2018, Tao led the Texas A&M team to the final of both the ASC18 and SC18 student cluster competitions. He currently serves as a faculty advisor of the Texas A&M 12th Unmanned Team for the SAE/GM AutoDrive Challenge Competition and leads a project funded by the Department of Commerce to build a digital twin for the Disaster City at Texas A&M University. Tao is an NVIDIA DLI University Ambassador and XSEDE Campus Champion at Texas A&M and a contributor to the SPEC CPU 2017 benchmark suite. His research interests include numerical modeling, machine learning, data analytics, distributed computing, visualization, digital twin, and workflow management.

https://cmse.msu.edu/directory/faculty/yang-yang/

 

 

Path Loss Prediction with Physics-Informed Neural Networks

Event information

Date
3:30 – 5PM
Tuesday Dec 6, 2022
Location POB 6.304 & Zoom
Hosted by Clint Dawson