As part of the transition to Digication, Portfolio is going away! Portfolio will be fully decommissioned on July 1, 2024. As of July 1, 2023, there will be a new content freeze in Portfolio. You will not be able to add new pieces of content to your personal or organizational Portfolio. Existing content is still editable. Please continue to migrate your existing content from Portfolio to Digication. For more information about Digication, click here. For a discussion of options for transitioning your content on Portfolio, click here. To learn more about using Digication in your courses, click here.
  • Publications


     (*Student co-author)

    1. Li J., Wang X., He Z*., Zhang T., 2021. A personalized activity-based spatiotemporal risk mapping approach to COVID-19 Pandemic. Cartography and Geographic Information Science.
    2. Li J., Wang X., Zhang T., 2021 Sequence-based centrality measures in maritime transportation networks. IET Intelligent Transport Systems. 14(14), p. 2042-2051.
    3. Yu, M., Bambacus, M., Cervone, G., Clarke, K., Duffy, D., Huang, Q., Li, J., Li, W., Li, Z., Liu, Q. and Resch, B., 2020. Spatiotemporal event detection: a review. International Journal of Digital Earth, doi: 10.1080/17538947.2020.1738569.
    4. Wang X*., Li J., Zhang T., 2019 A Machine-Learning Model for Zonal Ship Flow Prediction Using AIS Data: A Case Study in the South Atlantic States Region. Journal of Marine Science and Engineering, 7(12), 463.
    5. Li J., Xu Y*., Macrander H*., Atkinson L*., Thomas T*., Lopez M., 2019. GPU-based lightweight parallel processing toolset for LiDAR data for terrain analysis. Environmental Modeling and Software. 117: 55-68.
    6. Zhang, T., Zeng, Z., Li, J. 2019. Reinforcement learning-driven address mapping and caching for flash-based remote sensing image processing. Journal of Systems Architecture.
    7. Wang, X*., Rafa, M., Moyer, J. D., Li, J., Scheer, J., Sutton, P. 2019. Estimation and Mapping of Sub-National GDP in Uganda Using NPP-VIIRS Imagery. Remote Sensing, 11(2), 163.
    8. Zhang, T., Li, Y., Yang, H., Cui, C., Li, J., Qiao, Q. 2018. Identifying primary public transit corridors using multi-source big transit data. International Journal of Geographical Information Science, 1-25.
    9. Zhang T., Li J., 2018. Automatic cloud resource provisioning and management for interactive remote geovisualization using reinforcement learning. Transactions in GIS. 22(6): 1437-1461.
    10. Li J., Wang X., Zhang T., Xu Y., 2018. Efficient K Best Connected Trajectory (K-BCT) query on GPGPUs: a combinatorial min-distance and progressive bounding box approach. ISPRS International Journal of Geo-Information. 7(7):239.
    11. Zhang T., Luo P., Li J., Cheng Z., 2018. Efficient flash-aware page-mapping cache management for on-board remote sensing image processing. Journal of Systems Architecture. 88, 1-12.
    12. Zhang T., Dong. S., Zeng Z., Li J., Quantifying multi-modal public transit accessibility for large metropolitan areas: a time-dependent reliability modelling approach. International Journal of Geographic Information Science. 32(8):1-28.
    13. Li J., Finn M., Blanco-Castano M*. 2017. A lightweight CUDA-based parallel map reprojection method for raster datasets of continental to global Extent. ISPRS International Journal of Geo-Information. 6(4), 92.
    14. Huang Q., Li J., Li Z. 2017. A hybrid cloud platform framework based on multi-sourced computing and model resources for Geosciences. International Journal of Digital Earth. 4, 1-21.
    15. Li J., Zhang T., Liu Q*., Yu   2017. Predicting visualization intensity for interactive spatiotemporal visual analytics: A data-driven view-dependent approach. International Journal of Geographic Information Science. 31(1), 168-189.
    16. Li J., Zhang T., Wong D., Mooney M*. 2016. A view-dependent spatiotemporal saliency-driven approach for remote geovisualization. Computers, Environment and Urban Systems. 59, 64-77.
    17. Zhang T., Li J., Liu Q*., Huang Q. Cloud-enabled remote visualization for time-varying climate data analytics. Environmental Modeling and Software. 75:513-518.
    18. Zhang T., Zeng Z., Tao J., Li J. Examining the amenability of urban street networks for locating facilities. Physica A: Statistical Mechanics and its Applications. 457, 469-479.
    19. Zhang T., Yan W., Li J. Chen J. 2016. Multi-class labeling of very high-resolution remote sensing imagery by enforcing non-local shared constraints in multi-level conditional random field models. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. PP (99):1-14.
    20. Zhang T., Li J. Online task scheduling for LiDAR data preprocessing on hybrid GPU/CPU devices: A reinforcement learning approach.  IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 8(1): 386-397.


    1. Wang X*., Li J., Zhang T., 2020. Building a GPU-enabled analytical workflow for maritime pattern discovery using Automatic Identification System data. In: Tang W., Wang S., eds. High Performance Computing for Geospatial Applications. Springer.
    2. Huang Q., Li J., Zhang T., 2020. Domain Application of High Performance Computing in Earth Science -- An Example of Dust Storm Modeling and Visualization. In: Tang W., Wang S., eds. High Performance Computing for Geospatial Applications. Springer.
    3. Li J., Kai L., Huang Q. 2016. Utilizing cloud computing to support scalable atmospheric modeling: A case study of cloud-enabled ModelE. In: Vance T., Merati N., Yang C., Yuan M., eds. Cloud Computing for the Ocean and Atmospheric Sciences. Elsevier, pp. 347-363.



    1. “A grid-based hierarchical decomposition strategy for memory-efficient LiDAR processing with GPUs”. AGU Fall Meeting 2019, San Francisco, December 9 -13, 2019
    2. “A visual based spatiotemporal sequence mining approach to maritime transportation”, 115th AAG Annual Meeting, Washington DC, April 3- 7, 2019.
    3. “Building a CUDA-Based Parallel Processing Library for 3DEP”, 114th AAG Annual Meeting, New Orleans, April 9 - April 13, 2018.
    4. “Intensive Spatiotemporal Visual Analytics in Collaborative Computing Environment”, 1st International Symposium on Spatiotemporal Computing, Fairfax, Virginia, July 13 – 15, 2015.


    FUNDED PROJECTS  (Since 2015)

    1. Towards developing a GPU cloud based visual analytics framework for large scale Earth science data. Microsoft. 2018, 2019.
    2. Earth on AWS Cloud Credits for Research Application, Amazon Web Service (AWS). 2017.
    3. AB105 Security-enabled desktop client (EOC Desktop Client) for Open Geospatial Consortium (OGC) Testbed 13. Open Geospatial Consortium (OGC).  2017.
    4. Develop a GPU-based remote data processing prototype system to support the 3D Elevation Program (3DEP). US Geological Survey (USGS), Center of Excellence in GIS (CEGIS). 2016.
  • Research projects


    • Urban Environment: Build AI methods to predict fine level air quality in cities.
    • Transportation: Apply AI to analyze movement patterns and predict resource usage, such as public transit, for better planning.
    • Health: Use travel logs and AI to evaluate individuals' air pollutant exposure and possible health outcomes.

    (Left: Major corridors identified from public transit systems using smart card data; Right: Community transmission of COVID-19 on 04/12/2020 in Denver Metro, two weeks after Stay@Home order issued )



    • Develop novel geovisualization algorithms to represent multidimensional geospatial data that capture dynamic environmental processes (e.g., wind, dust movement).
    • Discover the spatiotemporal principles in governing the efficiency and the effectiveness of geovisualization.
    • Design computational solutions that leverage the state-of-the-art computing solutions(e.g., Cloud computing) to improve the performance of geovisulaization.

    (Left: Isovolume of wind speed from model simulations; Right: Backbone network extracted from ship trajectories)

     Online Link:



    • Leverage cloud computing and GPU computing techniques to improve computing-intensive problems (e.g., LiDAR processing, interactive visualization)
    • Design methods to improve  cloud-based task scheduling and resource allocation to support geospatial computing

    (Left: An example of Kernel Density Estimation-KDE; Right: Time costs of running parallel processing algorithms)

    Online link:

This portfolio last updated: 02-Feb-2023 2:29 PM