Spotlight: GeoAI Lab@UB
Information provided by Professor Yingjie Hu, head of the GeoAI Lab at the University at Buffalo
Nov. 21, 2022
Please briefly introduce yourself and your lab.
My name is Yingjie Hu. I am an assistant professor in the Department of Geography at the University at Buffalo (UB) and an affiliated professor of the UB AI and Data Science Institute. My major research area is in geographic information science (GIScience), and more specifically in geospatial artificial intelligence (GeoAI) and spatial data science. I lead the GeoAI Lab at UB, where we integrate geospatial data, spatial analysis, and AI methods to understand geographic phenomena and to address some of the challenging problems facing our society, such as those related to natural disasters, public health, ecosystem conservation, and sustainable development.
Describe the overall 5–10 year vision and/or mission of your lab.
In 5–10 years, I hope that our work can advance knowledge in disaster response, public health, and ecosystem conservation, and make a small contribution to help society better achieve sustainable development. I also hope to improve methods in GIS and GeoAI to help us better analyze geospatial data and find hidden patterns.
Whom do you collaborate with (people and/or organizations), and in what ways?
We collaborate a lot with domain experts in disaster response, public health, and ecosystem conservation. We bring in expertise in geospatial data and GeoAI methods, while domain experts bring in their domain knowledge.
Name one (or more) person or organization whose work has influenced your thinking.
My doctoral committee members, Drs. Krzysztof Janowicz and Helen Couclelis, have substantially influenced my thinking in GIScience and spatial data science. UCSB Geography is also a spatial and special place that exposed me to interdisciplinary research during my early years as a PhD student there.
Do you consider your lab/work to be interdisciplinary? If so, how?
Yes, I consider the work of my lab highly interdisciplinary in which we integrate geospatial data and AI with three research domains.
Do you consider your lab diverse? In what ways? Are there ways in which you would like to become more (or less) diverse?
Yes, I consider my lab diverse, with students coming from different population groups and academic backgrounds. If possible, I would like my lab to become more diverse. I believe the unique backgrounds, perspectives, expertise, and life experiences brought by different students are critical for achieving true excellence in scholarship.
What are some notable examples of student/postdoc research topics in your lab?
Some examples of student-led research in my lab include using GeoAI to extract location descriptions from disaster-related social media messages, predicting public health issues based on human–place interactions, and forecasting vegetation changes in a global biodiversity hotspot.
What backgrounds, in terms of education and/or experience, are useful to have for students/postdocs in your lab?
Students can come from different fields, such as geography, computer science, public health, ecology, and civil engineering. It is useful for students/postdocs to have some experience in spatial data science and be open to interdisciplinary research. Some experience in deep learning is helpful for students, too.
What are you looking for in a student/postdoc, and how can they reach out to you?
Ideally, a student should be self-motivated and willing to drive their own research. They would also have a relatively clear goal for pursuing a master’s or a PhD degree. A good student should also be able to communicate and collaborate well with their advisor and other group members. Students can reach out to me through my email at: yhu42@buffalo.edu.
