Trainees will replace by-hand networks with methods, learning to build more complex model architecture using the TensorFlow library.
Dr. Jiali Wang will also speak about her work on AI applications on climate science.
Tanwi Mallick is an Assistant Computer Science Specialist in the Mathematics and Computer Science Division (MCS) at Argonne National Laboratory. Her research interests include traffic modeling, spatiotemporal forecasting utilizing graph neural networks, natural language processing, scalable data-efficient deep learning and large-scale machine learning on high-performance computing platforms. She previously held a postdoctoral position in the Division of Mathematics and Computer Science. She earned her PhD in computer science from the Indian Institute of Technology Kharagpur. Prior to Argonne, she was a senior data scientist at General Electric.
Dr. Jiali Wang is an atmospheric scientist in Environmental Science Division at Argonne. Dr. Wang received her Ph.D degree in atmospheric science in 2012, and has been working at Argonne since then. She also holds a fellowship member with NAISE at Northwestern University, as well as CASE at University of Chicago. Dr. Wang specializes in physical understanding climate and extreme climate variabilities and their impacts on water/energy, and many other fields (e.g., infrastructure, ecology) through high-resolution numerical modeling, data analysis, as well as machine learning/AI. Extreme events she is interested in and has been working on include: flooding, storms, droughts/wildfires, wind gusts, and heatwaves, focusing on various climate zones of North America, including Great Lakes Region and coastal urban area such as Chicago. Dr. Wang served as a primary investigator and co-investigator for projects supported by AT&T(climate, risk, and resilience), DOD (regional climate modeling and climate extremes), DOE (distributed wind uncertainty quantification; Great Lakes regional modeling), DHS (regional resiliency assessment program) as well as Argonne Laboratory Directed Research and Development (neighborhood scale AI and GPU accelerated modeling).