Posts

Lab members Jiyeon Kim and Ryan Zhou received UB Excellence in Research, Scholarship and Creativity Award for their paper, “Assessment of deep learning models integrated with weather and environmental variables for wildfire spread prediction and a case study of the 2023 Maui fires”, published in the journal Natural Hazards (see full paper here).

Jiyeon presented this paper at UB’s Annual Student Showcase:

Jiyeon and Ryan receiving the awards, along with two outstanding students in UB Geography. In the photo below, from left to right: Festus Adegbola, Jiyeon Kim, Lauren Phung, Ryan Zhenqi Zhou.

Our GeoAI lab members attended the 2026 Annual Meeting of AAG in San Francisco in March 16-20, 2026.

Group member Liyue Zhang presented her work on an online survey of disaster Facebook group during the 2022 Buffalo blizzard. She and four other students won the Jeanne X. Kasperson Student Paper Award from the AAG Hazards, Risks, & Disasters Specialty Group.

Lab member Jiyeon Kim presented her work on GeoAI and wildfire spread prediction.

Yingjie Hu presented in two invited panel sessions:
– Past, present, and future of GIScience
– Movement analytics in the era of big data, AI, and open science

In addition, Yingjie Hu also organized the AAG GISS specialty group Waldo Tobler and TGIS Distinguished Lecture in GIScience, and the GeoAI Symposium panel on Advances and Potential Risks in GeoAI Research.

It’s a great conference. We look forward to the event next year!

Dr. Hu was invited to the NCAR Ideas Lab workshop, and he contributed his expertise in GeoAI and natural hazards to the workshop. This workshop is part of the Faculty Innovator Program of NCAR, which brings together faculty fellows and NCAR scientists to co-develop interdisciplinary and actionable Earth system science projects.

Abstract: Predicting the spread of wildfires is essential for effective fire management and risk assessment. With the fast advancements of artificial intelligence (AI), various deep learning models have been developed and utilized for wildfire spread prediction. However, there is limited understanding of the advantages and limitations of these models, and it is also unclear how deep learning-based fire spread models can be compared with existing non-AI fire models. In this work, we assess the ability of five typical deep learning models integrated with weather and environmental variables for wildfire spread prediction based on over ten years of wildfire data in the state of Hawaii. We further use the 2023 Maui fires as a case study to compare the best deep learning models with a widely-used fire spread model, FARSITE. The results show that two deep learning models, i.e., ConvLSTM and ConvLSTM with attention, perform the best among the five tested AI models. FARSITE shows higher precision, lower recall, and higher F1-score than the best AI models, while the AI models offer higher flexibility for the input data. By integrating AI models with an explainable AI method, we further identify important weather and environmental factors associated with the 2023 Maui wildfires.

For more details, please refer to: Kim, J., Hu, Y., Elhami-Khorasani, N., Sun, K., & Zhou, R.Z. (2025): Assessment of deep learning models integrated with weather and environmental variables for wildfire spread prediction and a case study of the 2023 Maui fires. Natural Hazards, accepted. [PDF]

Our new paper on understanding and modeling cities through texts in the age of AI is published in Nature Cities. It discusses how texts can be leveraged to understand cities and people for applications from urban planning to disaster management.

Urban researchers now have access to vast amounts of textual data—from social media and news to planning documents and property listings. These textual data provide important information about the activities of people and organizations in urban environments. Meanwhile, recent advancements in computational tools, including large language models, have expanded our ability to analyze textual data. This article explores how these tools are reshaping the ways we analyze, understand, and theorize the city through text. By outlining key developments, applications, and challenges, it argues that text is no longer a ‘fringe resource’ but a central component in urban analytics with the potential to connect quantitative and qualitative researchers.

Full paper: https://www.nature.com/articles/s44284-025-00314-x [pdf]

PhD student Ryan Zhenqi Zhou wins this year’s PhD Scholarship from the Cartography and Geographic Information Society (CaGIS): https://cartogis.org/awards/students/

This is a fairly prestigious student award from a national-level society. Congratulations, Ryan!

Two new members joined our lab this Fall 2025. They are:

• Liyue Zhang. Liyue obtained her bachelor degree in Urban and Rural Planning from South China University of Technology. She joined the lab as a new PhD student. Her research interests include GeoAI, urban resilience, and urban computing.

• Mengqi Li. Mengqi received her M.S. in Geographic Information Science from the University of Zurich (UZH) and B.S. from Nanjing University of Information Science and Technology (NUIST). Mengqi joined the lab as a PhD student. Her research interests include GeoAI, urban informatics, disaster resilience, and human mobility.

Welcome Mengqi and Liyue! We hope you enjoy your time here!

Abstract: The 2022 Buffalo blizzard was a catastrophic winter storm that struck Buffalo, New York in the week of Christmas in 2022. It claimed 47 lives and left much of the region stranded for the holiday week. In this disaster, the 311 call service was used by many residents to request help for issues due to the blizzard. This study examines these 311 help requests and their potential disparities across communities. Specifically, we aim to: (1) understand the spatial and temporal distributions of different types of 311 help requests; (2) identify the physical and social vulnerability factors, as well as human behavior factors, that are associated with the use of 311 calls. Methodologically, we leverage both explainable geospatial artificial intelligence (GeoAI) methods and statistical analysis to analyze 311 help requests and their associated factors. Our analysis shows significant spatial disparities in 311 help requests across communities. Results from explainable GeoAI and statistical analysis also reveal complementary insights on key factors associated with 311 help requests, such as historical 311 request behavior and percentage of minority population. These results could inform future disaster management decisions and help mitigate the negative impacts of winter storm disasters.

Full paper is available at: Zhou, R.Z., Hu, Y., Sun, K., Muldoon, R., Clark, S., & Joseph, K., (2025): Explainable GeoAI and statistical analysis reveal complementary insights about disparities of 311 help requests during the 2022 Buffalo blizzard. International Journal of Disaster Risk Reduction, 105635. [PDF]

Dr. Hu introduced geospatial technologies and AI, and the use of these technologies for disaster response in Encyclopedia Britannica.

He did an interview with Encyclopaedia Britannica previously: