Enhancing High-resolution Terrain Data Model for Improving the Delineation of Multi-scale Hydrological Connectivity
Funded by NSF
The project is to create a new geospatial and hydrological modeling approach that improves the identification of rivers and streams using high-resolution digital elevation models (HRDEMs). Accurate identification of these river and stream networks is necessary for monitoring environmental process such as the transport of nutrients and aquatic species. The results will create an intelligent hydrological model by combining methods in geographic information sciences, artificial intelligence and cyberinfrastructure that will enable multi-scale analysis of river and stream networks. The model, algorithms, and datasets generated from this project will be freely available to the public and benefit a broad scope of natural resources management activities, such as watershed monitoring, wetland conservation, and aquatic species protection. The results of this work will be incorporated into educational curriculums and disseminated to the broader educational community.
News Coverage NSF grant to assist in improving drainage flow path mapping
Publications (+ student advisee, * corresponding author)
Edidem, M.+, B. Xu+, R. Li*, D. Wu+, B. Rekabdar, G. Wang. Identification of Drainage Crossings on High-Resolution Digital Elevation Models Using Explanatory Deep Learning Approaches. Frontiers in Artificial Intelligence (minor revision)
Edidem, M.+, R. Li*, D. Wu+, B. Rekabdar, G. Wang. 2025. GeoAI-based Drainage Crossing Detection for Elevation-derived Hydrographic Mapping. Environmental Modelling and Software. 186, 106338. Full Texts
Wu, D.+, R. Li*, M. Edidem+, G. Wang. 2024, Enhancing Hydrologic LiDAR Digital Elevation Models: Bridging Hydrographic Gaps at Fine Scales. JAWRA Journal of the American Water Resources Association. 60(6), 1253-1269. Full Texts
Nazeri, A., D.W. Godwin, A.M. Panteleaki, I. Anagnostopoulos, M. Edidem, R. Li, T. Shu. 2025. Exploration of TPU Architectures for the Optimized Transformer in Drainage Crossing Detection. Proceedings of 2024 IEEE International Conference on Big Data.
Zhang, Y., D. Pandey, D. Wu+, T. Kundu, R. Li, T. Shu. 2023. Accuracy-Constrained Efficiency Optimization and GPU Profiling of CNN Inference for Detecting Drainage Crossing Locations. The International Conference for High Performance Computing, Networking, Storage, and Analysis (SC23); Denver, CO; Pp. 9. doi: 10.1145/3624062.3624260. Full Text
Li, Y., J. Baik, M.M. Rahman, I. Anagnostopoulos, R. Li, T. Shu. 2023. Pareto Optimization of CNN Models via Hardware-Aware Neural Architecture Search for Drainage Crossing Classification on Resource-Limited Devices. SC23; Denver, CO; Pp. 9. doi: 10.1145/3624062.3624258. Full Texts
Jalalipour, S., S. Ayyalasomayjula, H. Damrah, J. Lin, B. Rekabdar, R. Li. 2023. Deep Learning-Based Spatial Detection of Drainage Structures using Advanced Object Detection Methods. In 2023 International Conference on Transdisciplinary AI; Laguna Hills, CA; p 8. Full Texts
Wu, D.+, R. Li*, C. Talbert, M. Edidem, B. Rekabdar, G. Wang. 2023. Classification of Drainage Crossings on High-resolution Digital Elevation Models: A Deep Learning Approach. GIScience & Remote Sensing. 60:1. https://doi.org/10.1080/15481603.2023.2230706. Full Texts
Bhadra, S.+, R. Li*, D. Wu, G. Wang, B. Rekabdar. 2021. Assessing the Roles of Anthropogenic Drainage Structures on Hydrologic Connectivity Using High-resolution Digital Elevation Models. Transactions in GIS. 25(5), 2596-2611. Full Texts
Talafha, S, D. Wu+, B. Rekabdar, R. Li, G. Wang. 2021. Classification and Feature Extraction for Hydraulic Structures Data Using Advanced CNN Architectures. In 2021 Third International Conference on Transdisciplinary AI, 137–146. Laguna Hills, CA, USA: IEEE https://ieeexplore.ieee.org/document/9565622/. Full Texts
Student Dissertation and Thesis
Ph.D. Dissertation - Di Wu (2024). Improving Hydrologic Connectivity Delineation based on High-Resolution DEMs and Geospatial Artificial Intelligence. Southern Illinois University.
M.S. Thesis - Michael Edidem (2024). Using Deeping Learning Techniques to Enhance the Delineation of Elevation-Derived Hydrographic Features. Southern Illinois University.
Conference Oral/Poster Presentations
Li, R. 2024. Spatial Detection of Stream-Road Crossing Locations with Geospatial Artificial Intelligence. 2024 AWRA/UCOWR/NIWR Joint Water Resources Conference, Sept 30-Oct 2, 2024, St Louis, MO.
Edidem, M. R. Li, D. Wu, G. Wang. Geospatial AI Solutions for Locating Drainage Barriers in Elevation-derived Hydrographic Mapping. AAG Annual Meeting. Apr 16-20, 2024, Honolulu, HI.
Li, R., D. Wu, S. Bhadra, B Rekabdar, G. Wang, 2022. Evaluating LiDAR-based Elevation-derived Hydrography in Low-lying Agricultural Landscapes. AGU Fall Meeting 2022.
Wu, D., R. Li, B. Rekabdar, G. Wang. 2022. GeoAI-based identification of hydraulic structures for improving DEM-based hydrologic delineation, AAG Annual Meeting, Feb 25-Mar 1, 2022, Virtual.
Li, R., D. Wu, S. Bhadra, B Rekabdar, G. Wang, 2020. Enhancing Drainage Delineation Using High-resolution Terrain Data Model and Geospatial Artificial Intelligence. AGU Fall Meeting 2020.
Data Sources and Sharing
GeoAI-based drainage crossing detection for elevation-derived hydrographic mapping
https://github.com/GeoFewLab/Drainage_CrossingDet
https://doi.org/10.6084/m9.figshare.25909453.v1
Deep learning classification of drainage crossings based on high-resolution DEM-derived geomorphological information
Code: https://github.com/GeoFewLab/Drainge_CrossingClassification
Data: https://doi.org/10.6084/m9.figshare.27893382
Enhancing hydrologic LiDAR digital elevation models: Bridging hydrographic gaps at fine scales
Li, R., D. Wu (2025). Enhancing Hydrologic LiDAR Digital Elevation Models: Bridging Hydrographic Gaps at Fine Scales, HydroShare, http://www.hydroshare.org/resource/32119ad130ab47f1982da253241d9c25