Data-driven hydrological discharge simulation in the Limpopo River Basin for transboundary water management
Robust hydrological simulation is key for sustainable development, water management strategies, and climate change adaptation. In recent years, deep learning methods have been demonstrated to outperform mechanistic models at the task of hydrological discharge simulation. Adoption of these methods ha...
| Autores principales: | , , , |
|---|---|
| Formato: | Póster |
| Lenguaje: | Inglés |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://hdl.handle.net/10568/179578 |
| _version_ | 1855514642701352960 |
|---|---|
| author | Tlhomole, James Garcia Andarcia, Mariangel Matheswaran, Karthikeyan Borgomeo, E. |
| author_browse | Borgomeo, E. Garcia Andarcia, Mariangel Matheswaran, Karthikeyan Tlhomole, James |
| author_facet | Tlhomole, James Garcia Andarcia, Mariangel Matheswaran, Karthikeyan Borgomeo, E. |
| author_sort | Tlhomole, James |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | Robust hydrological simulation is key for sustainable development, water management strategies, and climate change adaptation. In recent years, deep learning methods have been demonstrated to outperform mechanistic models at the task of hydrological discharge simulation. Adoption of these methods has been catalysed by the proliferation of large sample hydrology datasets, consisting of the observed discharge and meteorological drivers, along with geological and topographical catchment descriptors. Deep learning methods infer rainfall-runoff characteristics that have been shown to generalise across catchments, benefitting from the data diversity in large datasets. Despite this, application to catchments in Africa has been limited. The lack of adoption of deep learning methodologies is primarily due to sparsity or lack of the spatiotemporal observational data required to enable downstream model training. We therefore investigate the application of deep learning models, including LSTMs, for hydrological discharge simulation in the transboundary Limpopo River basin, emphasising application to data scarce regions. We conduct a number of computational experiments primarily focused on assessing the impact of varying the LSTM model input data on performance. Results confirm that data constraints remain the largest obstacle to deep learning applications across African river basins. We further outline the impact of human influence on data-driven modelling which is a commonly overlooked aspect of data-driven large-sample hydrology approaches and investigate solutions for model adaptation under smaller datasets. |
| format | Poster |
| id | CGSpace179578 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2025 |
| publishDateRange | 2025 |
| publishDateSort | 2025 |
| record_format | dspace |
| spelling | CGSpace1795782026-01-09T08:01:33Z Data-driven hydrological discharge simulation in the Limpopo River Basin for transboundary water management Tlhomole, James Garcia Andarcia, Mariangel Matheswaran, Karthikeyan Borgomeo, E. river basins transboundary waters discharge water management neural networks Robust hydrological simulation is key for sustainable development, water management strategies, and climate change adaptation. In recent years, deep learning methods have been demonstrated to outperform mechanistic models at the task of hydrological discharge simulation. Adoption of these methods has been catalysed by the proliferation of large sample hydrology datasets, consisting of the observed discharge and meteorological drivers, along with geological and topographical catchment descriptors. Deep learning methods infer rainfall-runoff characteristics that have been shown to generalise across catchments, benefitting from the data diversity in large datasets. Despite this, application to catchments in Africa has been limited. The lack of adoption of deep learning methodologies is primarily due to sparsity or lack of the spatiotemporal observational data required to enable downstream model training. We therefore investigate the application of deep learning models, including LSTMs, for hydrological discharge simulation in the transboundary Limpopo River basin, emphasising application to data scarce regions. We conduct a number of computational experiments primarily focused on assessing the impact of varying the LSTM model input data on performance. Results confirm that data constraints remain the largest obstacle to deep learning applications across African river basins. We further outline the impact of human influence on data-driven modelling which is a commonly overlooked aspect of data-driven large-sample hydrology approaches and investigate solutions for model adaptation under smaller datasets. 2025-12-15 2026-01-09T07:59:29Z 2026-01-09T07:59:29Z Poster https://hdl.handle.net/10568/179578 en Open Access Tlhomole, J.; Garcia Andarcia, M.; Matheswaran, K.; Borgomeo, E. 2025. Data-driven hydrological discharge simulation in the Limpopo River Basin for transboundary water management. Poster presented at the American Geophysical Union Fall (AGU25) Conference 2025: Where Science Connects Us. New Orleans, USA. 15-19 December 2025. |
| spellingShingle | river basins transboundary waters discharge water management neural networks Tlhomole, James Garcia Andarcia, Mariangel Matheswaran, Karthikeyan Borgomeo, E. Data-driven hydrological discharge simulation in the Limpopo River Basin for transboundary water management |
| title | Data-driven hydrological discharge simulation in the Limpopo River Basin for transboundary water management |
| title_full | Data-driven hydrological discharge simulation in the Limpopo River Basin for transboundary water management |
| title_fullStr | Data-driven hydrological discharge simulation in the Limpopo River Basin for transboundary water management |
| title_full_unstemmed | Data-driven hydrological discharge simulation in the Limpopo River Basin for transboundary water management |
| title_short | Data-driven hydrological discharge simulation in the Limpopo River Basin for transboundary water management |
| title_sort | data driven hydrological discharge simulation in the limpopo river basin for transboundary water management |
| topic | river basins transboundary waters discharge water management neural networks |
| url | https://hdl.handle.net/10568/179578 |
| work_keys_str_mv | AT tlhomolejames datadrivenhydrologicaldischargesimulationinthelimpoporiverbasinfortransboundarywatermanagement AT garciaandarciamariangel datadrivenhydrologicaldischargesimulationinthelimpoporiverbasinfortransboundarywatermanagement AT matheswarankarthikeyan datadrivenhydrologicaldischargesimulationinthelimpoporiverbasinfortransboundarywatermanagement AT borgomeoe datadrivenhydrologicaldischargesimulationinthelimpoporiverbasinfortransboundarywatermanagement |