About Me

My name is Yingjie Hu. I am an Assistant Professor in the Department of Geography at the University at Buffalo (UB) and the National Center for Geographic Information and Analysis (NCGIA). My major research area is in geographic information science (GIScience), and more specifically in geospatial artificial intelligence, spatial and textual analysis, data-driven geospatial semantics, and geographic information retrieval. I develop and integrate spatial analysis methods, natural language processing, machine learning and deep learning techniques to discover knowledge from various geo data to support disaster response, urban planning, digital humanities, and other applications. I lead the Geospatial Artificial Intelligence (GeoAI) Lab at UB. I also serve as an Advising Faculty for the MS in Computational Linguistics program.

Previously, I served as an Assistant Professor in the Department of Geography at the University of Tennessee, Knoxville (UTK). I hold a PhD from the Department of Geography at the University of California, Santa Barbara (UCSB). I was a member of the Space and Time Knowledge Organization (STKO) Lab at UCSB. I was also a research engineer during summers at the Applications Prototype Lab in Esri Inc., where I helped design the next generation's GIS.

Research Interests

  • GIScience
  • GeoAI
  • Spatial Data Science
  • Spatial and Textual Analysis
  • Geospatial Semantics
  • Geographic Information Retrieval
  • Geographic Information Value
  • Geographic Knowledge Graph
  • Spatial Data Infrastructure
  • Public Participation GIS
  • Nighttime Light Remote Sensing


  • 9/2011 - 6/2016: PhD in Geography, University of California, Santa Babara, USA.
    Major Area: Cartography and GIS (Geospatial Semantics, with an additional emphasis on Cognitive Science)
  • 9/2008 - 6/2011: MS in Geography, East China Normal University, Shanghai, China.
    Major Area: Cartography and GIS (3D GIS and Web GIS)
  • 9/2004 - 6/2008: BS in Geography, East China Normal University, Shanghai, China.
    Major Area: Cartography and GIS (GIS Software Engineering)


See also:

Peer-reviewed Journal Articles: (author with an underscore is my student)

Peer-reviewed Book Chapters:

Peer-reviewed Conference Articles (Full Papers Only):

Peer-reviewed Short Papers or Extended Abstracts:

Professional Presentations:


(Please check GeoAI@UB for the latest projects)


Harvesting Local Place Names

Related paper

Local place names are frequently used by residents living in a geographic region. Such place names may not be recorded in existing gazetteers. In this work, we propose a computational framework for harvesting local place names from geotagged housing posts. We make use of those posts on local-oriented websites, such as Craigslist, where local place names are often mentioned. The proposed framework consists of two stages: natural language processing (NLP) and multi-scale geospatial clustering.

Code: https://github.com/YingjieHu/LocalPlaceName

Place Names and Spatial Locations

Related paper

In this project, we conduct an empirical study based on 112,071 POIs in seven US metropolitan areas extracted from an open Yelp dataset. We propose to adopt term frequency and inverse document frequency in geographic contexts to identify local terms used in POI names and to analyze their usages across different POI types. Our results show an uneven usage of local terms across POI types. We also examine the decaying effect of POI name similarity with the increase of distance among POIs.

Code: https://github.com/YingjieHu/POI_Name

Semantic Relatedness between Cities

Related paper

This project develops a topic modeling based workflow for extracting semantic relatedness between cities from news articles. News articles contain a rich amount of information about cities and their relations. The developed workflow makes use of city co-occurrences in news articles, and employs a topic model, LLDA, to analyze the full texts of news articles and to extract city relatedness. The extracted semantic relatedness can contribute to applications such as urban planning and GIR.

Code: https://github.com/YingjieHu/CityRelatednessViaNews

Information Value for Disaster Response

Related paper

In recent years, online volunteers have played important roles in disaster responses by mapping the disaster-affected areas based on remote sensing images. Typically, the disaster-affected area is divided into a number of cells using a grid-based tessellation. Online volunteers can then select a grid cell to start the mapping task. While such an approach coordinates the efforts from many volunteers, it does not differentiate the priorities of the different cells. In this research, we propose an analytical framework based on information value theory which can prioritize the grid cells based on the value of road network information contained in these cells.

Information Value for Space-Time Tasks

Related paper

While we have access to an increasing amount of information, the newly invented mobile devices, such as smart watches, are often equipped with only small screens. The limited display space restricts the number of information items that can be displayed at each time. Which information should be displayed first? Should it be the weather information, information about traffic conjestions, flight arrival information, meeting schedule, or some others? This work proposes an analytical framework which integrates information value theory with space-time prisms, and quantifies the value of information based on its spatiotemporal impact on the tasks of an individual.

Semantically-Enabled Data for NSF GeoLink

Related paper

GeoLink is a building block project in the NSF EarthCube program. It leverages the Semantic Web technologies to harmonize and link separate data repositories in geoscience. Seven data repositories (e.g., BCO-DMO and DataONE) have joined this project so far. Modular ontologies have been developed to link the heterogenous data, and a user interface has been designed which allows users to explore the data as tabular forms, maps, and graphs.

URL: http://demo.geolink.org/

Semantic Topics for Metadata Enrichment

Related paper

This project harmonizes the heterogenous metadata in a geoportal based on the ISO 19115 standard. A natural language processing model, Labeled Latent Dirichlet Allocation (LLDA), has been trained based on the metadata from data.gov. The trained LLDA model is then applied to the user-contributed ArcGIS Online data to harmonize the heterogenous metadata. Multiples tabs have been designed which can display the results in each topic.

URL: http://stko-exp.geog.ucsb.edu/linkedportal/

Place Name Disambiguation

Related paper

This project aims to understand the semantics of place names and improve the accuracy of place name disambiguation in short texts. Wikipedia is a data source that has been frequently employed as ground truth descriptions. However, Wikipedia articles do not emphasize the terms which represent important entities. We combine the entities from DBpedia (the semantic web version of Wikipedia) and designed a co-occurance model to improve the disambiguation result.

Code: https://github.com/YingjieHu/Place-Disambiguation

Urban Areas of Interest

Related paper

This project uses geo-tagged Flickr photo data to discover the areas of interest (AOI) within a city. Flickr data from six different cities in the past 10 years have been used for this study. Clusters have been identified at locations where most people took photos. We detect clusters using DBSCAN, and construct polygons using the chi-shape algorithm. In order to understand the semantics of the extracted AOIs, we also extract the distinctive tags and representative photos within these areas.

URL: http://stko-exp.geog.ucsb.edu/urbanAOIs/index.html

Semantic Search for ArcGIS Online

Related paper

We enable semantic search for maps by expanding an input query with related thematic concepts and geographic terms. Related thematic concepts are identified using Latent Semantic Analysis (LSA) and WordNet. Related geographic entities are found using a gazetteer Geonames.

URL: http://stko-exp.geog.ucsb.edu/linkedarcgis/
Video: http://www.youtube.com/watch?v=38ssyXaP7v0

Semantic Web Portal for Web@25

Blog article

This project celebrates the 25th birthday of the Web by building an online portal using Semantic Web technologies. We use the publication data from the WWW conference, and develop three major modules for this portal. The timeline module shows the major topics in the past 10 years. The geographic map module visualizes the spatial distribution of these topics. The self-organization map shows the hierachical relations between research topics and visualizes them using a map metaphor.

URL: http://stko-exp.geog.ucsb.edu/web25portal/

Point of Interest (POI) Pulse

Related paper

This project reclassifies the categories of Point of Interest (POIs) from Foursquare using support vector machine. One POI is classified into multiple categories based on its spatial, temporal, and thematic characteristics. We visualize a large amount of POI data using HTML5 and javascript, and discovered a tipping point to switch between vector and raster representations. This project also enables one to explore the dynamics or pulse of a city by visualing real-time user activities on Foursquare.

URL: http://stko-poi.geog.ucsb.edu/prod/lapulse/

Scientometrics Portal for Learning Analytics

Related paper

This is a project developed for the Learning Analytics and Knowledge (LAK) Challenge. We make use of the LAK community's publication data, and visualize the geographic collaboration patterns, coauthor networks, and citation distributions of academic papers. We have also designed a tool for reviewer recommendation. We won the Second Prize Award in this LAK Challenge.

URL: http://stko-exp.geog.ucsb.edu/lak/
Video: http://www.youtube.com/watch?v=g_Bsm_fEJkA

Semantic Web Journal Portal

Related paper

A project for the Semantic Web Journal to improve the analysis of the journal’s publication data, including the number of publications, citations for each author. Analysis results are then visualized using techniques such as D3.

URL: http://semantic-web-journal.com/SWJPortal/
Video: http://www.youtube.com/watch?v=LPWVfLaC6Co

Citation Map

Related paper

A project for the AAG Mashup Competition that visualizes the citation data on a global scale map. This application locates the first author of a paper, and then searches all researchers who have cited this paper in their work. Finally, the locations of these researchers are visualized on a map. We won the Finalist Award.

URL: http://stko-work.geog.ucsb.edu:8080/map/
Video: http://www.youtube.com/watch?v=eC309dGdJM0

Space-Time Contexts for File Management

Related paper

This project proposes to augment file management systems with space-time contexts, so that locations and time are attached to digital files that we use everyday on laptops, smartphones, and other mobile devices. Such addtional indices allow users to search files based on not only traditional folder hierachies but also the space-time contexts in which files have been used. For example, finding a document you opened in Washington DC during a conference last month.

Videos: https://www.youtube.com/watch?v=qFhPhj5gObI

3D GIS for Public Participation

Related paper

This system supports the collaborations of participants in different stages of decision making in contexts such as urban planning. Participants can not only provide comments and feedbacks on existing plans, but also engage in intensive discussions and real-time design. This system integrates the concept of GeoDesign and helps to answer the "what if" questions in many applications.

Code: https://github.com/YingjieHu/PPGIS

3D GIS for Agriculture Management

A 3D GI system developed for Chongming, Shanghai, China. This system has been designed to provide local farmers with easy access to agricultural information and help them better manage their lands and crops.

Video: https://www.youtube.com/watch?v=LifF-0Rghtg

3D GIS for Pollution Mornitoring

A 3D GI system developed for pollution mornitoring in Shanghai, China. This system was designed for Shanghai Environmental Protection Agency (EPA) to help manage the information about electricity and sewage plants. Alerts will be issued when real-time pollution exceeds a threshold level.

Video: https://www.youtube.com/watch?v=wiuJLIOrXqI

3D GIS for Greenspace Planning

A 3D GI system developed for planning greenspace in Shanghai, China. This system allows users to plan the greenspace in different ways by choosing grass types and tree species. It then visualizes the possible results to the users.

Video: https://www.youtube.com/watch?v=ATphYE3NPQQ


Courses Taught at UB:

  • GEO 281: Web-based Geographic Information Systems
  • GEO 481/506: Geographic Information Systems
  • GEO 503F: GIS and Machine Learning
  • GEO 503S: AI for Geospatial Applications

Courses Taught at UTK:

  • GEOG 411: Intermediate Geographic Information Science
  • GEOG 414: Geodatabase and Spatial Data Management
  • GEOG 509: Geospatial Semantics

Courses Taught at UCSB:

  • GEOG 12: Maps and Spatial Reasoning
  • GEOG 176A: Introduction to Geographic Information Science
  • GEOG 176B: Technical Issues in GIS
  • GEOG 176C: GIS Project Management


Peer Reviewer for Academic Journals

Committee Services

Memberships of Professional Associations


  • Waldo-Tobler GIScience Young Researcher Award, by Austrian Academy of Sciences, 2020
  • Best GIScience Full Paper Award, by GIScience Conference Organization Committee, 2018
  • Professional and Scholarly Development Award, by the University of Tennessee Knoxville, 2017
  • Doctoral Scholarship, by the Cartography and Geographic Information Society, 2016
  • Excellence in Research Award, by UCSB Geography, 2016
  • National Award for Outstanding Chinese PhD Students Studying Abroad, by China Scholarship Council, 2016
  • Graduate Scholarship, by Chinese-American Engineers and Scientists Association, 2016
  • Graduate Dissertation Fellowship, by UCSB Graduate Division, 2015
  • Dissertation Fellowship, by UCSB Affiliates, 2015
  • Early Career Scholar Travel Grant, by NSF EarthCube Program, 2015
  • Graduate Travel Grant, by UCSB Graduate Division, 2015
  • International Geographic Information Fund Award, by the Association of American Geographers (AAG), 2015
  • Graduate Travel Grant, by UCSB Graduate Student Association, 2015
  • 2nd Prize for Learning Analytics and Knowledge (LAK) Data Challenge, by the LAK Challenge Organization Committee, 2014
  • Jack Dangermond Graduate Fellowship, by UCSB Geography, 2013
  • Finalist Prize for AAG Robert Raskin Mashup Mapping Competition, by the Competition Organization Committee, 2013
  • Jack Dangermond Travel Award, by UCSB Geography, 2012, 2013, 2014, 2015
  • NSF Travel Award for the 20th ACM SIGSPATIAL conference, by the Conference Organization Committee, 2012
  • NSF Travel Award for the 6th RR Conference, by the Conference Organization Committee, 2012
  • Doctoral Scholars Fellowship, by UCSB Geography, 2011
  • Excellent Master Thesis, by East China Normal University (ECNU) Geography, 2011
  • Graduate Fellowship, by ECNU Geography, 2010, 2011
  • Excellent Graduate, by Shanghai Municipal Education Commission, 2008
  • Excellent Bachelor Thesis, by ECNU Geography, 2008
  • Undergraduate Fellowship, by ECNU Geography, 2005, 2007

Media Coverage


Yingjie Hu

Email: yhu42 at buffalo dot edu
Follow me on:

Yingjie Hu Yingjie Hu 1985-11-20 Assistant Professor Male Yingjie Hu is an Assistant Professor of Geography.