Research Interests
My years of industry experience have shown me that remote sensing technology can create broader social and practical value only when it directly addresses real-world challenges. Although remote sensing data are becoming increasingly available through satellites, aerial platforms, UAVs, mobile mapping systems, and LiDAR sensors, the efficient storage, processing, fusion, analysis, and distribution of large-scale multi-source geospatial data remain major bottlenecks. These challenges limit the operational use of remote sensing technologies in industry, environmental management, forestry, and urban applications.
My research focuses on integrating advanced artificial intelligence, deep learning, and geospatial data fusion methods into remote sensing workflows to improve data usability, processing efficiency, and decision-making capability. I am particularly interested in developing scalable AI-driven solutions for forest inventory, individual-tree level analysis, environmental monitoring, wildfire-related applications, and 3D geospatial intelligence. Through this work, I aim to bridge the gap between cutting-edge remote sensing research and practical industrial deployment, enabling remote sensing technologies to better support real-world environmental and societal needs.
Education
- Ph.D. in Geography, University of Waterloo, 2026
- M.Sc. in Geomatics, University of Waterloo, 2016
- B.Sc. in Geographic Information System, Tianjin Normal University, 2011
Selected Publications (2025–2026)
- Wang, L., Guan, H., Lu, D., Zhang, D., *Li, J, 2o26. Exploring transfer learning for individual tree species classification by cross-platform point cloud, International Journal of Applied Earth Observation and Geoinformation, vol. 149, 105247.
- Xu, Z., Wang, L., Cheng, S., Rui, X., Gao, K., Zhu, Y., Heffring, M., Dewis, Z., Taleghanidoozdoozan, S., Greenwood, M., Alkayid, M., Ledingham, Q., He, H., Li, J., Xu, L. Trustworthy data-driven wildfire risk prediction and understanding in Western Canada. https://doi.org/10.48550/arXiv.2601.01677.
- Xu, Z., Wang, L., Zhu, Y., Sun, W., Xu, L, 2026. BC wildfire risk prediction time-series dataset: 2002–2023. ISPRS Annuals, XI-3-2026:951-957, DOI: 10.5194/isprs-annals-XI-3-2026-951-2026.
- Xu, Z., Cheng, S., Wang, L., He, H., Sun, W., Li, J., & Xu, L. L., 2026. BCWildfire: A Long-term Multi-factor Dataset and Deep Learning Benchmark for Boreal Wildfire Risk Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 40(46), 39486–39494. https://doi.org/10.1609/aaai.v40i46.41299.
- Kang, J., Guan, H., Zhang, D., Ma, L., Wang, L., Yu, Y., Xu, L., Li, J., 2026. RPDNet: Street-level road pavement damage detection with a real-time anchor-free network. International Journal of Applied Earth Observation and Geoinformation, vol. 146, 105070.
- Chen, K., Sun, H., Guan, H., Wang, L., Cao, L., Zhao, H., Zhao, F., 2026. Weakly supervised forest canopy extraction and multi-dimensional joint canopy entropy for quantifying canopy structural complexity using large-scale forest UAV LiDAR data, Plant Phenomics, vol 6, no. 1, 100169.
- Xu, Z., Wang, L., He, H., Guan, H., Ma, L., Li, J., Xu, L., 2025. Training-free urban tree counting with multi-modal data. Abstracts of the ICA, 32nd International Cartographic Conference (ICC 2025), 17–22 August 2025, Vancouver, Canada, https://doi.org/10.5194/ica-abs-10-307-2025.
- Chen, D., Kang, J., Wang, L., Yu, Y., Zhou, W., Guan, H., Karim, M., 2025. SACNet: A novel self-supervised learning method for shadow detection from high-resolution remote sensing images. Journal of Geovisualization and Spatial Analysis, vol. 9, 14, https://doi.org/10.1007/s41651-025-00215-6.
- Wang L, Lu D, Xu L, Robinson DT, Tan W, Xie Q, Guan H, Chapman MA, Li J, 2024. Individual tree species classification using low-density airborne multispectral LiDAR data via attribute-aware cross-branch transformer, Remote Sensing of Environment, vol. 315, 114456. DOI: 10.1016/j.rse.2024.114456.
For a complete list of publications, please refer to my full academic CV.