Together with the GeoAI Symposium, this session focuses on "statistical methods and machine learning for trajectory data analysis". We look for new efforts on advancing computational movement data analysis with statistical and machine learning methods, domain applications and practices, ongoing research, industry demos, and vision papers are also welcome! Please contact co-organizers for any questions.
Sean C. Ahearn, Hunter College – CUNY, email@example.com
Somayeh Dodge, University of California – Santa Barbara, firstname.lastname@example.org
Song Gao, University of Wisconsin – Madison, email@example.com
Chaogui Kang, Wuhan University, firstname.lastname@example.org
In today’s era of big data, advanced algorithms, and immense computational power, artificial intelligence (AI) is bringing tremendous opportunities and challenges to geospatial research. Big data enables computers to observe and learn the world from many angles, while high performance machines support the training development and application deployment of AI models within a reasonable amount of time. Recent years have witnessed significant advances in the integration of geography and AI in both academia and industry, and the outcome is an exciting and transdisciplinary area -- GeoAI. There have already been many successful studies. Focusing on modeling the physical nature, a recent publication in PNAS has shown that deep learning can improve the representation of clouds that are smaller than the grid resolutions of climate models. Examining the human society, AI and natural language processing methods, such as word embeddings, are helping quantify changes in stereotypes and attitudes toward women and ethnic minorities over 100 years in the United States. There are also many other applications that effectively integrate AI with problems in geospatial studies, such as vehicle trajectory prediction and high-definition mapping, indoor navigation, historical map digitizing, gazetteer conflation, geographic feature extraction, geo-ontologies, and place understanding.
Building on the great success of the 1st and 2nd symposiums at AAG, we are organizing the 3rd AAG Symposium on GeoAI and Deep Learning for Geospatial Research focusing on the current status, recent advances, and possible future directions of this exciting research theme at the 2020 AAG Annual meeting, Denver, Colorado, April 6-10, 2020. We aim to bring together geographers, GI scientists, spatial modeling experts, computer scientists, spatial data scientists, epidemiologists, urban planners, transportation professionals, and many others to discuss this rapidly developing research frontier. In particular, we hope to provide a venue for researchers from all geospatial disciplines to start the dialog on how to fertilize this exciting field of GeoAI, how can we better prepare our students with essential knowledge and skills, and how can we foster cross-discipline collaborations.
Together with the GeoAI Symposium, this session focuses on "statistical methods and deep learning for trajectory data analysis". We look for new efforts on advancing computational movement data analysis with statistical and machine learning methods, domain applications and practices, ongoing research, industry demos, and vision papers are also welcome! Please contact co-organizers for any questions.
|Presenter||Hyowon Ban*, California State University, Long Beach, Movement Analysis and Visualization of Choreographic Information||15||1:45 PM|
|Presenter||Rongxiang Su*, University of California - Santa Barbara, Elizabeth C. McBride, University of California - Santa Barbara, Konstadinos G. Goulias, University of California - Santa Barbara, California Sequence-Based Fragmentation of Activity and Travel, Taxonomy of Daily Time Use Patterns, and Differences Between Men and Women||15||2:00 PM|
|Presenter||Rebecca Loraamm*, University of Oklahoma, Simulating visit probabilities in space-time prisms using a constrained agent based model||15||2:15 PM|
|Presenter||Sean Ahearn*, Hunter College - City University, Trajectory Analysis and Deep Learning: Problems and Prospects||15||2:30 PM|
|Discussant||Somayeh Dodge University of California||15||2:45 PM|
To access contact information login