Department of Land Economy home

Home Institution

Ghent University

Supervisor

Elisabete A Silva

Research Topic

GeoAI, Human mobility, urban analytics, and computational urban science

Bio

Xucai Zhang is a Ph.D. candidate at Ghent University, Belgium, majoring in Geomatics. He is currently a Visiting Scholar under the supervision of Professor Elisabete A Silva at the Land Economy Department, Cambridge University. He is focusing on developing geospatial artificial intelligence (GeoAI) techniques, with applications in human mobility, land use and urban analytics. My dissertation aims to propose a series of deep learning methods integrated with geographic knowledge and concepts, which will be integrated into a generic framework to illustrate how we can integrate geographic concepts into deep learning for enhancing model performance, reducing training costs, and mining potential and meaningful knowledge.

Publications

  1. Zhang, X., Liu, X., Chen, K., Guan, F., Luo, M., & Huang, H. (2023). Inferring building function: A novel geo-aware neural network supporting building-level function classification. Sustainable Cities and Society. doi: 10.1016/j.scs.2022.104349
  2. Zhang, X., Sun, Y., Guan, F., Chen, K., Witlox, F., & Huang, H. (2022). Forecasting the crowd: An effective and efficient neural network for citywide crowd information prediction at a fine spatio-temporal scale. Transportation Research Part C: Emerging Technologies. doi: 10.1016/j.trc.2022.103854
  3. Zhang, X., Sun, Y., Chan, T. O., Huang, Y., Zheng, A., & Liu, Z. (2021). Exploring impact of surrounding service facilities on urban vibrancy using Tencent location-aware data: A case of Guangzhou. Sustainability. doi: 10.3390/su13020444.
  4. Zhang, X., Sun, Y., Zheng, A., & Wang, Y. (2020). A new approach to refining land use types: Predicting point-of-interest categories using Weibo check-in data. ISPRS International Journal of Geo-Information. doi: 10.3390/ijgi9020124.

Working papers

Zhang, X., Jin, T., Wei, X., N. Van de Weghe., Witlox, F & Huang, H. An Adaptive Gravity Model for Generating Mobility Flows without Historical Flow Data.

Zhang, X., Jin, T., N. Van de Weghe., Witlox, F & Huang, H. A Novel Neural Network Considering Regional Heterogeneity for Citywide Traffic Volume Prediction.

Research Grants/Projects

EIT Urban Mobility