<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=Windows-1252">
<style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} </style>
</head>
<body dir="ltr">
<div id="Signature">
<div>
<div>
<div style="font-family:Calibri,Arial,Helvetica,sans-serif; font-size:12pt; color:rgb(0,0,0)">
<p align="center" style="margin-top: 0px; margin-bottom: 0px;margin:0in 0in 0.0001pt; font-size:12pt; font-family:Times,serif; margin-bottom:12.0pt; text-align:center">
<b><span style="font-size:16.0pt; font-family:"Times New Roman","serif"">Toward Convergence of HPC and Data Science for Seismic Modeling and Inverse Problems</span></b><span style="font-family:"Times New Roman",serif"> </span></p>
<p align="center" style="margin-top: 0px; margin-bottom: 0px;margin:0in 0in 0.0001pt; font-size:12pt; font-family:Times,serif; margin-bottom:12.0pt; text-align:center">
<span style="font-family:"Times New Roman","serif"">Thursday, February 13, 2020</span></p>
<p align="center" style="margin-top: 0px; margin-bottom: 0px;margin:0in 0in 0.0001pt; font-size:12pt; font-family:Times,serif; margin-bottom:12.0pt; text-align:center">
<span style="font-family:"Times New Roman","serif"">10 am, Room 386, the Technology Building (T2)</span></p>
<p style="margin-top: 0px; margin-bottom: 0px;margin:0in 0in 0.0001pt; font-size:12pt; font-family:Times,serif; margin-bottom:12.0pt; text-align:justify">
<b><span style="font-family:"Times New Roman","serif"; color:#100100">Abstract: </span>
</b><span style="">Data science, as a fast-spreading interdisciplinary field, is based on the theories of probability and statistics to extract valuable knowledge and insights from structured and unstructured data directly. Data science has rapidly reshaped
the methodology, workflow, algorithms, and systems used in the industry and scientific community. Deep learning as the major breakthrough in data science, has the advantage of representation learning and building the hierarchical abstractions from big datasets.
These advantages of deep learning achieved significant successes in many fields such as image classifications, image segmentation, natural language processing, gaming, and even scientific computing.</span></p>
<p style="margin-top: 0px; margin-bottom: 0px;margin:0in 0in 0.0001pt; font-size:12pt; font-family:Times,serif; margin-bottom:12.0pt; text-align:justify">
<span style="">Seismic wave propagation simulation and inversion is a classical high-performance computing (HPC) application based on the finite difference or finite element methods to solve the wave equations numerically. The application takes significant
computing resources to generate accurate results. In this talk, I will share our experience in implementing the seismic wave propagation simulation and inversion using the data science software PyTorch and leveraging the deep learning recurrent neural network
(RNN) framework. We use the built-in automatic differentiation function in PyTorch that supports the accurate partial derivatives calculation to tackle the ill-posed inverse problems based on gradient-based optimizations. I will present the performance of
our PyTorch-based implementation of seismic wave simulation and inversion.</span></p>
<p style="margin-top: 0px; margin-bottom: 0px;margin:0in 0in 0.0001pt; font-size:12pt; font-family:Times,serif; margin-bottom:12.0pt; text-align:justify">
<b><span style="font-family:"Times New Roman","serif"; color:#100100">Presenter’s Bio:</span></b><span style="font-family:"Times New Roman","serif"; color:#100100">
</span><span style="">Dr. Lei Huang is an Associate Professor in the Department of Computer Science, Prairie View A&M University (PVAMU), a member of Texas A&M University System, where he is leading research at the Computing Research Lab. He also serves as
the Associate Director of Research in the Center of Excellence in Research and Education for Big Military Data Intelligence at PVAMU sponsored by Department of Defense (DoD). He is currently the Principal Investigator of multiple research projects sponsored
by National Science Foundation (NSF) in the Big Data Analytics, Cloud Computing, and High Performance Computing (HPC) areas. He joined PVMAU in 2011 with research experience in HPC at the University of Houston, and working experience in software R&D. Huang
has earned his Ph.D. from the Computer Science Department at the University of Houston in 2006.</span></p>
</div>
<div id="Signature">
<div class="BodyFragment"></div>
</div>
</div>
</div>
</div>
</body>
</html>