Deep learning for spatiotemporal data in scientific applications

September 23, 2024 in Seminar

Zhe Jiang, Ph.D., Associate Professor, Department of Computer & Information Science & Engineering, University of Florida

Join us for the livestream September 25th, 11:45am ET: https://youtube.com/live/WmSGfotL7yk?feature=share

(Please visit our YouTube channel main page for the stream if there are any issues with the direct link.)

ABSTRACT

Artificial intelligence (AI) has achieved tremendous success in computer vision and natural language processing. With a rapidly growing amount of spatiotemporal data being collected from various sources (e.g., cellphone locations, satellite imagery, climate simulations), there is a growing anticipation of similar accomplishments of AI in geospatial domains (a.k.a. GeoAI). However, developing AI for Geo-domains faces significant technical challenges, including implicit sample dependency in continuous space, spatiotemporal non-stationarity, existence of domain knowledge and constraints, paucity of ground truth. In this talk, he will introduce his recent research to address some of the above challenges, including a hierarchical transformer for massive spatial point observations in environmental applications and knowledge-infused spatial deep learning framework for hydrological applications.

BIO

Dr. Zhe Jiang is an associate professor in the Department of Computer & Information Science & Engineering at the University of Florida, where he is also affiliated with the Center for Coastal Solutions. He received his Ph.D. in Computer Science from the University of Minnesota in 2016 and a B.E. in Electrical Engineering from the University of Science and Technology of China in 2010. His research interests include data mining, machine learning, and artificial intelligence, with a particular focus on spatiotemporal data mining for interdisciplinary applications in Earth sciences (hydrology, natural disaster, coastal hazards), agriculture, transportation, health and medicine, etc. His research has been sponsored by multiple federal agencies (e.g., NSF, USGS, NOAA, UCAR) and industry companies. He received the Best Paper Award in ACM SIGSPATIAL 2023 and Best Paper Runner-Up Award in the Blue-Sky Vision Track of SIAM Data Mining 2024. He has served as a Senior Program Committee member (or Area Chair) for AAAI, ICDM, ICML, ACM SIGSPATIAL, SDM, and PAKDD. He is a senior member of ACM and IEEE. (His homepage: www.jiangteam.org).

POSTCARD