Title: Trajectory Privacy Protection with Geospatial AI
Abstract: The prevalence of Location-Based Services (LBS) has led to the generation of large amounts of individual-level trajectory data, which offers opportunities to study human mobility patterns, human-environment interactions, disaster responses, and public health issues. However, trajectory big data also pose significant challenges related to geoprivacy protection and broader social and ethical implications. In this talk, we will discuss three main challenges in trajectory privacy protection, namely the trade-off between privacy and utility, data sparsity and imbalance issues, and endogenous privacy risks in centralized structures. We will also introduce some of our recent work to demonstrate the potential of Geospatial AI in addressing these challenges in trajectory privacy protection.
Bio: Dr. Jinmeng Rao is an AI researcher at Google DeepMind. He was an AI researcher at Google[X]. He got his MS in Computer Sciences and PhD in Geography at UW-Madison supervised by Prof. Song Gao. He holds a M.S. and B.S. in Cartography and GIS from Wuhan University. His main research interest is Geospatial AI and geoprivacy. His articles have been published in top journals and conferences, including IJGIS, TGIS, GIScience, ACM SIGSPATIAL, ACM SIGIR, AAAI, etc. He serves as a reviewer or for the program committee for various journals and conferences, including IJGIS, Annals of GIS, TGIS, JAG, Computers & Geosciences, NeurIPS, ACL, etc. He received the 2024 AAG William L. Garrison Award for Best Dissertation in Computational Geography.
Title: Human-centered GeoAI in the era of Generative AI: Perceptions and Creativity
Abstract: The emergence of Generative AI offers numerous opportunities to benefit geospatial intelligence, enabling novel ways to advance our knowledge of human perceptions and creativity. In Dr. Kang’s talk, he will explore the impact of Generative AI on geospatial analytics through two key perspectives. First, he will discuss how a Soundscape-to-Image model could translate and visualize human perceptions of visual and acoustic environments. Second, he will illustrate how generative AI, through the process of data-style separation, can produce not only accurate but also visually appealing maps that adhere to ethical standards in cartography. His talk will delve into the transformative potential of Generative AI in the development of Human-centered GeoAI.
Bio: Dr. Yuhao Kang is a tenure-track Assistant Professor, directing the GISense Lab at the Department of Geography and the Environment, The University of Texas at Austin. He was a postdoctoral researcher at the MIT SENSEable City Lab, received his Ph.D. from the GeoDS Lab, University of Wisconsin-Madison, and obtained his bachelor’s degree from Wuhan University. Before joining UT-Austin, he had working experience at the University of South Carolina, Google X, and MoBike. He was the founder of the non-profit educational organization GISphere that promotes global GIS education. Dr. Kang’s research mainly focuses on Human-centered Geospatial Data Science to understand human experience at place and develop ethical and responsible geospatial artificial intelligence (GeoAI) approaches. He was the recipient of the Waldo-Tobler Young Researcher Award by the Austrian Academy of Sciences, CaGIS Rising Award, CPGIS Education Excellence Award, etc.
Title: Spatial Representation Learning: What, How, and Why
Abstract: Spatial representation learning (SRL) aims at learning general-purpose neural network representations from various types of spatial data (e.g., points, polylines, polygons, networks, images, etc.) in their native formats. Learning good spatial representations is a fundamental problem for various downstream applications such as species distribution modeling, weather forecasting, trajectory generation, geographic question answering, etc. In this presentation, we will discuss several recent works from UT SEAI Lab about spatial representation, including various location encoding models (Space2Vec and Sphere2Vec), an SRL deep learning framework (TorchSpatial), and a SRL-powered geo-foundation model (GAIR). We will discuss 1) WHAT is location representation learning? 2) HOW to develop location representation learning models? and 3) WHY do we need them?
Bio: Dr. Gengchen Mai is currently a Tenure-Track Assistant Professor at the Department of Geography and the Environment, University of Texas at Austin. He got his Ph.D. in GIScience from UCSB Geography. Before becoming a faculty, he was a Postdoc at Stanford Computer Science. Before joining UT, he was an Assistant Professor at the University of Georgia. Dr. Mai’s research is Spatially Explicit Artificial Intelligence, Geo-Foundation Models, Geographic Knowledge Graphs, etc. Dr. Mai’s work has been published not only in many top geography/GIScience/Remote Sensing journals but also in many ML/AI conferences such as NeurIPS, ICML, ICLR, ACM SIGIR, ACM SIGSPATIAL, etc. He is the recipient of many prestigious awards including AAG 2021 Dissertation Research Grants, AAG 2022 William L. Garrison Award for Best Dissertation in Computational Geography, AAG 2023 J. Warren Nystrom Dissertation Award, Top 10 WGDC 2022 Global Young Scientist Award, the Jack and Laura Dangermond Graduate Fellowship, UT MGCE Fellowship, 2025 Geospatial Rising Star Award, etc. He is currently the registration chair of ACM SIGSPATIAL 2025, vice chair of AAG GISS Specialty Group, and PC member for NeurIPS, ICML, ICLR, WWW, AISTATS, ACM SIGIR, ACM SIGSPATIAL, GIScience, etc.
We are very glad to invite you to mark your calendar for joining the forthcoming Geospatial Data Science Speaker Series 2024-2025 events, which are hosted by the GeoDS lab in Geography and co-sponsored by the Data Science Institute @UW-Madison.
The first event of this semester will be jointly with the Geography Yi-Fu Lectures. We will first have Dr. Krzysztof Janowicz, a distinguished University-Named Professor of Geoinformatics at the University of Vienna (Austria), visiting UW-Madison and will present “GeoMachina: What Designing Artificial GIS Analysts Teaches Us About Place Representation” at 3:30 p.m.-4:30p.m., on September 13, 2024 (Friday), Science Hall 180.
Please join us congratulating our senior student Ying Nie, who is currently an undergraduate majoring in computer science as well as a research assistant in the GeoDS Lab under Prof. Song Gao’s mentorship, just got the UW-Madison “Hilldale Undergraduate/Faculty Research Fellowship” and was awarded in the 2024 Chancellor’s Undergraduate Awards Ceremony!
The awarded research project is: Large Language Model for Intelligent Spatial Analysis Workflow Construction
Our GeoDS lab’s students and alumni recently attended the American Association of Geographers (AAG) 2024 Annual Meeting held in Honolulu, HI. It was a great reunion for the GeoDS family at the conference!
Geospatial Artificial Intelligence (GeoAI) is a rapidly evolving interdisciplinary field that integrates geospatial studies with AI advancements. In this webinar editors and authors of the recently published GeoAI Handbook discuss the fundamental concepts, methods, applications, and perspectives of GeoAI. The GeoAI Handbook is an excellent resource for educators, students, practitioners and decision-makers who are interested in utilizing AI technologies in a geospatial context.
Schedule:
20 mins: Round-table Q&A about the GeoAI Handbook: Maria Antonia Brovelli, Andrea Manara, and Song Gao
10 mins: Chapter 5: GeoAI for Spatial Image Processing: Wenwen Li and Samantha Arundel
10 mins: Chapter 7: Intelligent Spatial Prediction and Interpolation Methods: Di Zhu
10 mins: Chapter 10: Spatial Cross-Validation for GeoAI: Yingjie Hu
10 mins: Wrap-up
The GeoAI advancements provide promising solutions to address some of the United Nations SDGs but also pose concerns. For example, Chapter 3 presents some of the fundamental assumptions and principles that could form the philosophical foundation of GeoAI and spatial data science. It highlights the sustainability issue for training GeoAI and foundation models that could cause substantial electricity energy and resource consumptions and generate equivalent carbon emissions. Therefore, we need to call for Green AI for achieving the SDG-13: Climate Action. Chapters 13 and 14 discuss existing and prospective GeoAI tools to support humanitarian assistance practices and disaster responses using geospatial big data and machine learning methods, aiming to address the SDG-10: Reduce Inequality and SDG-11: Sustainable Cities and Communities. Chapter 15 focuses on using GeoAI for infectious disease spread prediction to address the SDG-3: Good Health and Well-Being.
AI technologies are advancing rapidly, and new methods and use cases in GeoAI are constantly emerging. As GeoAI researchers, we should not purely hunt for latest AI technologies but should focus on addressing geographic problems and solving grand challenges facing our society as well as achieving sustainable development goals. We also need research effort toward the development of responsible, unbiased, explainable and interpretable GeoAI models to support geographic knowledge discovery and beyond. This GeoAI Handbook was completed in the middle of 2023. While it cannot summarize all GeoAI research in this one handbook, it provides a snapshot of current GeoAI research landscape and helps stimulate future studies in the coming years.
Greetings! We are very glad to invite you to mark your calendar for joining the forthcoming Geospatial Data Science Speaker Series Spring 2024 events, which are hosted by the GeoDS lab in Geography and co-sponsored by the Data Science Institute @UW-Madison.
We will first have Dr. Amr Magdy, an Assistant Professor of Computer Science and Engineering and a co-founding faculty member of the Center for Geospatial Sciences at UC Riverside, visiting UW-Madison and will present “Scalable Spatial Data Science for Social Scientists” 12:00 p.m.-1 p.m., on February 13, 2024 (Tue), Science Hall 140. Pizza lunch and coffee will be provided in the events.
We cannot wait to take our AAG 2024 GeoAI Symposium to Hawaii next year! Collaborating with 40+ colleagues across multiple continents, we have put together a series of paper and panel sessions. In the past year, we have been so excited to witness the rapid and continued growth of GeoAI, the advances in its methods and cross-domain applications. This year’s symposium will highlight these advances and will also include critical discussions on the issues of GeoAI and the societal challenges in its use in science and everyday life.
We welcome you to join us to present your papers, co-organize sessions, and serve as a panelist in our symposium. Your participation is key to helping us expand this exciting research community! If you have any questions, please feel free to reach out to the symposium’s lead organizers. The CFP can be found in the attachment.
AAG 2024 GeoAI Symposium organizing team
Lead Organizers: Wenwen Li, Arizona State University Yingjie Hu, University at Buffalo Song Gao, University of Wisconsin, Madison Budhu Bhaduri, Oak Ridge National Laboratory Orhun Aydin, Saint Louis University Shawn Newsam, University of California, Merced Samantha T. Arundel, United States Geological Survey Gengchen Mai, University of Georgia Krzysztof Janowicz, University of Vienna & University of California, Santa Barbara
GeoAI and Deep Learning Symposium: GeoAI for Science and the Science of GeoAI (Panel discussion session; in-person session; The organizing team)
GeoAI and Deep Learning Symposium: GeoAI Foundation Models (Panel discussion session; in-person session; The organizing team)
GeoAI and Deep Learning Symposium: GeoAI for Feature Detection and Recognition (Paper session; In-person session; Contact: Sam Arundel, US Geological Survey; Co-organizer: Wenwen Li, Arizona State University)
GeoAI and Deep Learning Symposium: GeoAI for Spatial Analytics and Modeling (Paper session; In-person session; Contact: Di Zhu, University of Minnesota; Co-organizers: Guofeng Cao, University of Colorado, Boulder; Song Gao, University of Wisconsin, Madison; Chaogui Kang, China University of GeoSciences)
GeoAI and Deep Learning Symposium: Emerging Geo-Data Applications in Human Mobility Analysis (Paper session; In-person session; Contact: Xiao Li, University of Oxford; Co-organizers: Xiao Huang, University of Arkansas, Haowen Xu, Oak Ridge National Laboratory, Yuhao Kang, University of South Carolina; Di Zhu, University of Minnesota)
GeoAI and Deep Learning Symposium: GeoAI for Ecosystem Conservation and and Sustainable Geodesign (Contact: Orhun Aydin, Saint Louis University; Somayeh Dodge, University of California Santa Barbara)
GeoAI and Deep Learning Symposium: GeoAI for Disaster Resilience I (Paper session; In-person session; Contact Bing Zhou, Texas A&M University. Co-organizers: Lei Zou, Texas A&M University;Yingjie Hu, University at Buffalo; Marcela Suárez, Penn State University, Yi Qiang, University of South Florida; Manzhu Yu, Penn State University; Morteza Karimzadeh, University of Colorado Boulder)
GeoAI and Deep Learning Symposium: Urban Visual Intelligence (Paper session; In-person session; Contact: Fan Zhang, Peking University, Co-organizer: Yuhao Kang, University of South Carolina; Filip Biljecki, National University of Singapore)
GeoAI and Deep Learning Symposium: Spatially Explicit Machine Learning and Artificial Intelligence (Paper session; In-person session; Contact: Gengchen Mai, University of Georgia; Co-organizers:Angela Yao, University of Georgia; Yao-Yi Chiang, University of Minnesota-Twin Cities; Krzysztof Janowicz, University of Vienna & UC Santa Barbara; Zhangyu Wang, University of California Santa Barbara; Di Zhu, University of Minnesota-Twin Cities)
GeoAI and Deep Learning Symposium: GeoAI for Cartography and Mapping (Paper session; In-person session; Contact: Yao-Yi Chiang, University of Minnesota-Twin Cities; Co-organizer: Jina Kim, University of Minnesota)
GeoAI and Deep Learning Symposium: Responsible GeoAI: Privacy, Fairness, and Interpretability in Spatial Data Science (Paper session; In-person session; Contact: Hongyu Zhang, McGill University; Co-organizers: Yue Lin, University of Chicago; Jinmeng Rao, Mineral Earth Sciences, Alphabet Inc.; Junghwan Kim, Virginia Tech; Song Gao, University of Wisconsin – Madison)
GeoAI and Deep Learning Symposium: GeoAI for Sustainable and Computational Agriculture (Paper session; In-person session; Contact: Jinmeng Rao, Mineral Earth Sciences, Alphabet Inc.; Co-organizers: Yuchi Ma, Stanford University; Jiahao Fan, University of Wisconsin-Madison; Hongxu Ma, Mineral Earth Sciences, Alphabet Inc.; Gengchen Mai, University of Georgia; Di Zhu, University of Minnesota, Twin Cities)
GeoAI and Deep Learning Symposium: Human-centered Geospatial Data Science (Paper session; In-person session; Contact: Yuhao Kang, University of South Carolina; Co-organizers: Filip Biljecki, National University of Singapore)
GeoAI and Deep Learning Symposium: GeoAI and Social Sensing for Human-Pandemic Dynamics (Paper session; In-person session; Contact: Binbin Lin, Texas A&M University, Mingzheng Yang, Texas A&M University; Co-organizers: Lei Zou, Texas A&M University)
GeoAI and Deep Learning Symposium: GeoHealth Data Science (Paper session; In-person session; Contact: Jiannan Cai, The Chinese University of Hong Kong; Co-organizer: Mei-Po Kwan, The Chinese University of Hong Kong)
GeoAI and Deep Learning Symposium: AI for Earth Observation (Paper session; In-person session; Contact: Bo Peng, PAII, Ping An U.S. Research Lab; Co-organizer: Chenxi Lin, PAII, Ping An U.S. Research Lab ; Beth Tellman, University of Arizona; Bandana Kar, U.S. Department of Energy; Lexie Yang, Oak Ridge National Laboratory; Yanghui Kang, University of California, Berkeley; Qunying Huang, University of Wisconsin-Madison; Di Zhu, University of Minnesota, Twin Cities)
GeoAI and Deep Learning Symposium: Characterization of Place and Human Patterns of Life (Paper session; In-person session; Contact: Junchuan Fan,Oak Ridge National Laboratory; Co-organizer: Joon-Seok Kim, Oak Ridge National Laboratory; Licia Amichi, Oak Ridge National Laboratory)
To present your research in one of these sessions, please register and submit your abstract at https://aag.secure-platform.com/aag2024/. When you receive confirmation of your submission, please forward your confirmation email to the session organizers by Nov. 16, 2023.
Abstract: In recent years we have seen substantial advances in foundation models for artificial intelligence, including language, vision, and multimodal models. Recent studies have highlighted the potential of using foundation models in geospatial artificial intelligence, known as GeoAI Foundation Models or Geo-Foundation Models, for geographic question answering, remote sensing image understanding, map generation, and location-based services, among others. However, the development and application of GeoAI foundation models can pose serious privacy and security risks, which have not been fully discussed or addressed to date. This paper introduces the potential privacy and security risks throughout the lifecycle of GeoAI foundation models and proposes a comprehensive blueprint for preventative and control strategies. Through this vision paper, we hope to draw the attention of researchers and policymakers in geospatial domains to these privacy and security risks inherent in GeoAI foundation models and advocate for the development of privacy-preserving and secure GeoAI foundation models.
Abstract: With the recent rapid advances of revolutionary AI models such as ChatGPT, foundation models have become a main topic for the discussion of future AI. Despite the excitement, the success is still limited to specific types of tasks. Particularly, ChatGPT and similar foundation models have unique characteristics that are difficult to replicate for most geospatial tasks. This paper envisions several major challenges and opportunities in the creation of geospatial foundation (geo-foundation) models, as well as potential future adoption scenarios. We also expect that a major success story is necessary for geo-foundation models to take off in the long term.
Please join us in congratulating our GeoDS lab’s PhD students and undergraduate students’ recent awards and achievements!
Yuhao Kang:
2023 Waldo-Tobler Young Researcher Award in GIScience, by the Austrian Academy of Sciences (ÖAW) Commission for GIScience to encourage scientific advancement in the disciplines of Geoinformatics and/or Geographic Information Science.
Organizers: Rafael Pires de Lima, rlima@colorado.edu, University of Colorado Boulder; Co-organizers: Morteza Karimzadeh, University of Colorado Boulder, Guofeng Cao, University of Colorado Boulder, Andong Ma, University of Colorado Boulder
Organizers: Yingjie Hu, Song Gao, Wenwen Li, Dalton Lunga, Orhun Aydin, and Shawn Newsame
Panelists: Michael Goodchild, University of California Santa Barbara, A-Xing Zhu, University of Wisconsin, Madison, May Yuan, University of Texas Dallas, Orhun Aydin, Saint Louis University, Budhendra Bhaduri, Oak Ridge National Laboratory)
Organizers: Xiao Li, xiao.li@ouce.ox.ac.uk, University of Oxford; Co-organizers: Xiao Huang, University of Arkansas, Haowen Xu, Oak Ridge National Laboratory, Yuhao Kang, University of Wisconsin, Madison
Organizers: Gengchen Mai, gengchen.mai@gmail.com, University of Georgia; Co-organizers:Angela Yao, University of Georgia; Yao-Yi Chiang, University of Minnesota-Twin Cities; Zhangyu Wang, University of California Santa Barbara
Organizers: Gengchen Mai, gengchen.mai@gmail.com, University of Georgia; Co-organizers:Angela Yao, University of Georgia; Yao-Yi Chiang, University of Minnesota-Twin Cities; Zhangyu Wang, University of California Santa Barbara
Organizers: Gengchen Mai, gengchen.mai@gmail.com, University of Georgia; Co-organizers:Angela Yao, University of Georgia; Yao-Yi Chiang, University of Minnesota-Twin Cities; Zhangyu Wang, University of California Santa Barbara
Organizers: Di Zhu, dizhu@umn.edu, University of Minnesota; Co-organizer: Guofeng Cao, University of Colorado, Boulder; Song Gao, University of Wisconsin, Madison
Organizers: Bing Zhou, spgbarrett@tamu.edu, Texas A&M University. Co-organizers: Lei Zou, Texas A&M University;Yingjie Hu, University at Buffalo; Marcela Suárez, Penn State University
Organizers: Yuhao Kang, yuhao.kang@wisc.edu, University of Wisconsin, Madison; Co-organizer: Fan Zhang, cefzhang@ust.hk, Hong Kong University of Science and Technology
Greetings! I am very glad to invite you to mark your calendar for joining the forthcoming Geospatial Data Science Speaker Series Spring 2023 events, which are hosted by the GeoDS lab in Geography and co-sponsored by the Data Science Institute, UniverCity Alliance, and GISPP @UW-Madison. We will have Dr. Filip Biljecki, the Director of Urban Analytics Lab from the National University of Singapore visit UW-Madison 11:45 a.m.-1 p.m., on March 28, 2023 (Tue), Science Hall 110and Dr. Fabio Duarte from the MIT Senseable City Lab on April 13 (Thur), Science Hall 140. Pizza lunch and coffee will be provided in the events.
Recently, Prof. Song Gao was invited to join the Associate Editors team ofInternational Journal of Geographical Information Science(IJGIS), which is a flagship international journal for publishing geographic information systems/science related research. Dr. Gao’s service term starts from January 1st, 2023.
Aims and Scope
The aim of International Journal of Geographical Information Science is to provide a forum for the exchange of original ideas, approaches, methods and experiences in the field of GIScience.
International Journal of Geographical Information Science covers the following topics:
Innovations and novel applications of GIScience in natural resources, social systems and the built environment
Relevant developments in computer science, cartography, surveying, geography, and engineering
Fundamental and computational issues of geographic information
The design, implementation and use of geographical information for monitoring, prediction and decision making
Prof. Song Gao is on this year’s list of Global Highly Cited Researchers List of 2022 and the only scholar from UW-Madison listed in the category of Social Sciences. Kudos to his colleagues, students, and mentors!
On November 15 2022, Clarivate revealed its 2022 list of Highly Cited Researchers™ – individuals at universities, research institutes and commercial organizations who have demonstrated a disproportionate level of significant and broad influence in their field or fields of research. The methodology draws on data from the Web of Science™ citation index, together with analysis performed by bibliometric experts and data scientists at the Institute for Scientific Information (ISI)™ at Clarivate. ISI analysts have awarded Highly Cited Researcher 2022 designations to 6,938 researchers from across the globe who demonstrated significant influence in their chosen field or fields over the last decade. ISI analyzed all papers published and cited between 2011 and 2021, determining which authors ranked in thetop 1% of cited papers in each field. The list is truly global, spanning 69 countries or regions and spread across a diverse range of research fields in the sciences and social sciences.
Prof. Gao is also on the list oftop 2% highly cited scientists based on Stanford University’s analysis of Scopus data provided by Elsevier.
