Posts

In a new research led by PhD student Ryan Zhou, we examined the impacts of the 2021 Texas Winter storm on local communities in three stages and impact disparities. Winter Storm Uri slammed Texas between February 13–17, 2021 and caused widespread power outages. Understanding the impacts of this catastrophic event on local communities has important meaning. In this study, we examine the impacts of this winter storm and its impact disparities on different population groups over three stages of this disaster: the initial-hit stage, power-outage stage, and recovery stage. The study focuses on Harris County, Texas which was severely affected by the winter storm. We leverage home-dwelling time information from anonymized mobile phone location data to study the constrained mobility of people due to the winter storm as a way to quantify its impacts on local communities. Considering that mobile phone location data may be affected by the power outages, we further integrate nighttime light (NTL) images into our analyses to assess disaster impacts during the power-outage stage, and use home-dwelling time to assess the impacts during the other two stages (i.e., the initial-hit stage and recovery stage). The results reveal disparate impacts of this winter storm on local communities in the three stages of this disaster. We also find impact disparities on population groups with different socioeconomic and demographic backgrounds, especially during the initial-hit stage. These results help us better understand the impacts of this catastrophic event, and could inform future response and mitigation efforts in identifying vulnerable communities, allocating resources, and curtailing negative impacts of similar disasters.

More information about this article is at: Ryan Zhenqi Zhou, Yingjie Hu, Lei Zou, Heng Cai, and Bing Zhou. (2024): Understanding the disparate impacts of the 2021 Texas winter storm and power outages through mobile phone location data and nighttime light images. International Journal of Disaster Risk Reduction, 104339. [PDF]

The Annual Meeting of the American Association of Geographers (AAG) in 2023 marked a five-year milestone since the first Geospatial Artificial Intelligence (GeoAI) Symposium was held at AAG in 2018. In the past five years, progress has been made while open questions remain. In this context, we organized an AAG panel and invited five panelists to discuss the advances and limitations in GeoAI research. The panelists commended the successes, such as the development of spatially explicit models, the production of large-scale geographic datasets, and the use of GeoAI to address real-world problems. The panellists also shared their thoughts on limitations in current GeoAI research, which were considered as opportunities to engage theories in geography, enhance model explainability, quantify uncertainty, and improve model generalizability. This article summarizes the presentations from the panellists and also provides after-panel thoughts from the organizers. We hope that this article can make these thoughts more accessible to interested readers and help stimulate new ideas for future breakthroughs.

Full paper is available at: Hu, Y., Goodchild, M., Zhu, A.X., Yuan, M., Aydin, O., Bhaduri, B., Gao, S., Li, W., Lunga, D., & Newsam, S. (2024): A five-year milestone: reflections on advances and limitations in GeoAI research. Annals of GIS, in press.

Figure 1. The GeoAI panel at AAG 2023

Dr. Hu has been invited to join the Editorial Board of Cartography and Geographic Information Science (CaGIS).

CaGIS is the official publication of the Cartography and Geographic Information Society. The Society supports research, education, and practices that improve the understanding, creation, analysis, and use of maps and geographic information. The CaGIS journal implements the objectives of the Society by publishing authoritative peer-reviewed articles that report on innovative research in cartography and geographic information science.

Our recent research on geo-knowledge-guided AI model for disaster response was reported by a number of news outlets:

• Emergency Management Magazine: “How ChatGPT Could Help First Responders During a Disaster”, https://www.govtech.com/em/how-chatgpt-could-help-first-responders-during-a-disaster
• Homeland Security News Wire: “ChatGPT Could Help First Responders During Natural Disasters”, https://www.homelandsecuritynewswire.com/dr20231214-chatgpt-could-help-first-responders-during-natural-disasters
• BNN Breaking: “AI Revolutionizes Emergency Response: GPT Models Extract Location Data from Social Media”, https://bnnbreaking.com/world/us/ai-revolutionizes-emergency-response-gpt-models-extract-location-data-from-social-media/
• Digital Information World: “ChatGPT Enhances Emergency Management by Identifying Distress Locations via Social Media Data”, https://www.digitalinformationworld.com/2023/12/chatgpt-enhances-emergency-management.html
• TS2 Space: “AI Breakthrough: Leveraging ChatGPT for Faster Disaster Response”, https://ts2.space/en/ai-breakthrough-leveraging-chatgpt-for-faster-disaster-response
• ScienceDaily: “How ChatGPT could help first responders during natural disasters”, https://www.sciencedaily.com/releases/2023/12/231207161410.htm
• NewsBreezer, “ChatGPT improves emergency management by identifying emergency locations via social media data”, https://newsbeezer.com/ireland/chatgpt-improves-emergency-management-by-identifying-emergency-locations-via-social-media-data/

It is great to see the wide public interest in our work. Look forward to doing more research that positively impacts on our society.

The new “Handbook of Geospatial Artificial Intelligence” edited by Drs. Song Gao (University of Wisconsin-Madison), Yingjie Hu (University at Buffalo), and Wenwen Li (Arizona State University) is now published and is available at the website of Taylor & Francis and a preview of the book is available here.

This handbook covers key fundamental concepts, methods, models, and technologies of GeoAI and discusses the recent advances, research tools, and applications that range from environmental observation and social sensing to public health and disaster responses. We hope this book can provide an organized resource for educators, students, researchers, and practitioners learning and using GeoAI.

Book chapters and their authors:

Section 1: Historical Roots of GeoAI

Chapter 1: Introduction to Geospatial Artificial Intelligence (GeoAI)

By Song Gao, Yingjie Hu, Wenwen Li

Chapter 2: GeoAI’s Thousand-Year History

By Helen Couclelis

Chapter 3: Philosophical Foundations of GeoAI: Exploring Sustainability, Diversity, and Bias in GeoAI and Spatial Data Science

By Krzysztof Janowicz

Section 2: GeoAI Methods

Chapter 4: GeoAI Methodological Foundations: Deep Neural Networks and Knowledge Graphs

By Song Gao, Jinmeng Rao, Yunlei Liang, Yuhao Kang, Jiawei Zhu, Rui Zhu 

Chapter 5: GeoAI for Spatial Image Processing

By Samantha T. Arundel, Kevin G. McKeehan, Wenwen Li, Zhining Gu

Chapter 6: Spatial Representation Learning in GeoAI

By Gengchen Mai, Ziyuan Li, Ni Lao

Chapter 7: Intelligent Spatial Prediction and Interpolation Methods

By Di Zhu, Guofeng Cao

Chapter 8: Heterogeneity-Aware Deep Learning in Space: Performance and Fairness

By Yiqun Xie, Xiaowei Jia, Weiye Chen, Erhu He

Chapter 9: Explainability in GeoAI

By Ximeng Cheng, Marc Vischer, Zachary Schellin, Leila Arras, Monique M. Kuglitsch, Wojciech Samek, Jackie Ma

Chapter 10: Spatial Cross-Validation for GeoAI

By Kai Sun, Yingjie Hu, Gaurish Lakhanpal, Ryan Zhenqi Zhou

Section 3: GeoAI Applications

Chapter 11: GeoAI for the Digitization of Historical Maps

By Yao-Yi Chiang, Muhao Chen, Weiwei Duan, Jina Kim, Craig A. Knoblock, Stefan Leyk, Zekun Li, Yijun Lin, Min Namgung, Basel Shbita, Johannes H. Uhl 

Chapter 12: Spatiotemporal AI for Transportation

By Tao Cheng, James Haworth, Mustafa Can Ozkan 

Chapter 13: GeoAI for Humanitarian Assistance

By Philipe A. Dias, Thomaz Kobayashi-Carvalhaes, Sarah Walters, Tyler Frazier, Carson Woody, Sreelekha Guggilam, Daniel Adams, Abhishek Potnis, Dalton Lunga 

Chapter 14: GeoAI for Disaster Response

By Lei Zou, Ali Mostafavi, Bing Zhou, Binbin Lin, Debayan Mandal, Mingzheng Yang, Joynal Abedin, Heng Cai 

Chapter 15: GeoAI for Public Health

By Andreas Züfle, Taylor Anderson, Hamdi Kavak, Dieter Pfoser, Joon-Seok Kim, Amira Roess 

Chapter 16: GeoAI for Agriculture

By Chishan Zhang, Chunyuan Diao, Tianci Guo 

Chapter 17: GeoAI for Urban Sensing

By Filip Biljecki 

Section 4: Perspectives for the Future of GeoAI

Chapter 18: Reproducibility and Replicability in GeoAI

By Peter Kedron, Tyler D. Hoffman, Sarah Bardin

Chapter 19: Privacy and Ethics in GeoAI

By Grant McKenzie, Hongyu Zhang, Sébastien Gambs

Chapter 20: A Humanistic Future of GeoAI

By Bo Zhao, Jiaxin Feng

Chapter 21: Fast Forward from Data to Insight: (Geographic) Knowledge Graphs and Their Applications

By Krzysztof Janowicz, Kitty Currier, Cogan Shimizu, Rui Zhu, Meilin Shi, Colby K. Fisher, Dean Rehberger, Pascal Hitzler, Zilong Liu, Shirly Stephen 

Chapter 22: Forward Thinking on GeoAI

By Shawn Newsam

Dr. Hu was recently featured in the Alumni Spotlight of the Department of Geography at UCSB. Yingjie is very grateful for the academic training he received from UCSB Geography, and looks forward to continuing contributing to addressing societal challenges, training next-generation scholars, and serving communities.

Dr. Yingjie Hu was invited to join the editorial board of the International Journal of Geographical Information Science (IJGIS). IJGIS is a flagship journal for GIScience research, and it covers research topics including:

• 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

Yingjie looks forward to continuing contributing to IJGIS and the GIScience community!

Social media messages posted by people during natural disasters often contain important location descriptions, such as the locations of victims. Recent research has shown that many of these location descriptions go beyond simple place names, such as city names and street names, and are difficult to extract using typical named entity recognition (NER) tools. While advanced machine learning models could be trained, they require large labeled training datasets that can be time-consuming and labor-intensive to create.

GPT models, such as GPT-3, ChatGPT, and GPT-4, are large-scale language models (LLMs) and foundation models that have received substantial attention recently. Taking just a few examples as the instruction (called a prompt), a GPT model is able to generate text that reads as if it was written by humans. While they are powerful, the current applications of GPT models are largely limited to conversation and text generation, and their social implications are controversial.

In this work, we aim to harness the power of GPT models for social good and propose a method that fuses geo-knowledge of location descriptions and a GPT model, such as ChatGPT and GPT-4. The result is a geo-knowledge-guided GPT model that can accurately extract location descriptions from disaster-related social media messages. Also, only 22 training examples encoding geo-knowledge are used in our method. We conduct experiments to compare this method with nine alternative approaches on a dataset of tweets from Hurricane Harvey. Our method demonstrates an over 40% improvement over typically used NER approaches. The experiment results also show that geo-knowledge is indispensable for guiding the behavior of GPT models. The extracted location descriptions can help disaster responders reach victims more quickly and may even save lives.

More details are available in the full paper: Hu, Y., Mai, G., Cundy, C., Choi, K., Lao, N., Liu, W., Lakhanpal, G., Zhou, R.Z., & Joseph, K. (2023): Geo-knowledge-guided GPT models improve the extraction of location descriptions from disaster-related social media messages. International Journal of Geographical Information Science, in press. [pdf]

The PhD program of UB Geography has officially been classified as a STEM program under the category “Geography and Environmental Studies” (30.4401). According to the definition from the U.S. government, this category refers to a program “that focuses on interactions between people and the natural and built environments. Includes instruction in climate science, sustainability, environmental science and policy, research methods, geographic information systems (GIS), human geography, physical geography, remote sensing, and public policy.“

Being classified as STEM allows our program to encourage more students to participate in STEM-related research. International students graduating from our PhD program will also have 36 months OPT which allows them to further hone their research and technical skills in the U.S. after graduation. Our Master’s in GIS program is in STEM too. If you are interested in applying for the graduate programs of UB Geography, please apply at: https://www.buffalo.edu/cas/geography/about-us/admissions.html

In collaboration with Dr. Dane Taylor (Mathematics; PI), GeoAI lab receives a new NSF award that integrates big geospatial data, GeoAI methods, and network modeling to study anomalies in spatio-temporal multilayer networks encoding human mobility: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2319250

Human mobility data from anonymized mobile phone devices are becoming increasingly available, enabling the detection of anomalies and potential threats from human movements. Due to the massive scale of data, it is difficult to detect anomalies that occur at different spatial and temporal resolutions. In addition, human movements are often associated with different categories of places (e.g., grocery stores and schools), and anomalies that are evident in one category may be obscure in another. This project will furnish new mathematical models and theories for encoding different categories of human movements as spatial-temporal multilayer networks. It will develop new algorithms to detect movement-pattern anomalies, which can help better forewarn anomalous events concerning national security. It will also advance our understanding of the impacts of anomalous and disastrous events on different categories of human movements. This project will contribute toward education by supporting graduate students and will facilitate interdisciplinary research between mathematics and geography. Open-source software tools will be implemented and publicly shared to help researchers and decision makers better predict, detect, and plan responses to future anomalous events.

To represent human movements in different categories and effectively detect the associated anomalies, the investigators will pursue three targets in this project. Target 1 will develop spatial-temporal multilayer network models encoding anonymized mobile phone location data of the United States. The network-structural properties associated with both normal and expected anomalous situations (e.g., holidays) will be extensively examined to develop a family of realistic generative models. Target 2 will build algorithms to detect and characterize movement-pattern anomalies based on the multilayer network models using unsupervised spectral algorithms. Random matrix theory will be employed to obtain theoretic guidelines for how to optimally preprocess data to maximize the “detectability” of anomalies at different spatial and temporal resolutions. Target 3 will apply the developed multilayer network models and anomaly detection algorithms to two case studies, to further refine our models and algorithms and to gain new insights into the evolutions and impacts of the two important events.