Journal article · 2025 · Open access

U-NET Deep Learning-based Downscaling to Generate High-resolution Seasonal Forecasts for Small Watersheds: A Case Study of the Nouhao Sub-basin, Burkina Faso

Abdérahim Toguyeni, Ali Doumounia, Moumouni Djibo, Wenceslas Somda, Lucien Damiba, François Zougmoré

International Journal of Environment and Climate Change, 15(12), 195–221 · Published 3 December 2025 · DOI 10.9734/ijecc/2025/v15i125156

Open full textCite this paper

In brief

“U-NET Deep Learning-based Downscaling to Generate High-resolution Seasonal Forecasts for Small Watersheds: A Case Study of the Nouhao Sub-basin, Burkina Faso” is a 2025 journal article by Abdérahim Toguyeni and 5 co-authors, published in International Journal of Environment and Climate Change. OpenAlex counts 0 citations as of 21 November 2026. It is open access: the full text is free to read at International Journal of Environment and Climate Change.

Citations
0
Authors
6

Abstract

Seasonal forecasts at coarse-resolution limit local decision-making and disaster (drought, flood…) preparedness in African small watersheds. To address these limitations, this study designs a Deep Learning-based downscaling framework using the U-Net Convolutional Neural Network (CNN) architecture to transform coarse 1° (~100 km) forecasts into high-resolution 0.05° (~5 km) gridded data. For this, it assesses raw seasonal forecasts of precipitation and temperature from three global models (ECMWF, Météo-France, and CMCC) and their ensemble mean (Ensmean) over Burkina Faso. Forecast skill was assessed against high-resolution reference datasets (CHIRPS for precipitation and CHIRTS for temperature) using standard statistical metrics (r, RMSE and MAE). The raw forecasts showed weak performance in representing spatial variability with biases above 20% for precipitation and more than 5 °C. However, after the downscaling process, the generated high-resolution outputs showed substantial improvements in skill compared to the raw forecasts, with gains of up to sixfold for precipitation and twenty-fold for temperature. A modified Taylor diagram incorporating these metrics was employed to identify ECMWF as the best-performing model for precipitation and METEO-FRANCE for temperature. By producing high-resolution seasonal precipitation and temperature datasets, this study demonstrates the added value of U-Net Deep Learning-based downscaling for Burkina Faso. While the initial application targeted the Nouhao sub-basin for drought modeling, the framework was extended to cover the entire country to make high-resolution data available for broader applications. These results provide new insights into integrating Deep Learning approaches into operational drought and flood prediction frameworks of Burkina Faso’s National Agency of Meteorology (ANAM) and the General Directorate of Water Resources (DGRE). They also contribute to improved understanding of complex seasonal climate hazards across West Africa and thereby enhancing related areas such as hydrological modeling.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Toguyeni, A., Doumounia, A., Djibo, M., Somda, W., Damiba, L., & Zougmoré, F. (2025). U-NET Deep Learning-based Downscaling to Generate High-resolution Seasonal Forecasts for Small Watersheds: A Case Study of the Nouhao Sub-basin, Burkina Faso. International Journal of Environment and Climate Change, 15(12), 195–221. https://doi.org/10.9734/ijecc/2025/v15i125156

MLA 9

Toguyeni, Abdérahim, et al. “U-NET Deep Learning-based Downscaling to Generate High-resolution Seasonal Forecasts for Small Watersheds: A Case Study of the Nouhao Sub-basin, Burkina Faso.” International Journal of Environment and Climate Change, vol. 15, no. 12, 2025, pp. 195–221. https://doi.org/10.9734/ijecc/2025/v15i125156.

Chicago

Toguyeni, Abdérahim, Ali Doumounia, Moumouni Djibo, Wenceslas Somda, Lucien Damiba, and François Zougmoré. 2025. “U-NET Deep Learning-based Downscaling to Generate High-resolution Seasonal Forecasts for Small Watersheds: A Case Study of the Nouhao Sub-basin, Burkina Faso.” International Journal of Environment and Climate Change 15 (12): 195–221. https://doi.org/10.9734/ijecc/2025/v15i125156.

Harvard

Toguyeni, A. et al. (2025) ‘U-NET Deep Learning-based Downscaling to Generate High-resolution Seasonal Forecasts for Small Watersheds: A Case Study of the Nouhao Sub-basin, Burkina Faso’, International Journal of Environment and Climate Change, 15(12), pp. 195–221. doi:10.9734/ijecc/2025/v15i125156.

IEEE

A. Toguyeni, A. Doumounia, M. Djibo, W. Somda, L. Damiba, and F. Zougmoré, “U-NET Deep Learning-based Downscaling to Generate High-resolution Seasonal Forecasts for Small Watersheds: A Case Study of the Nouhao Sub-basin, Burkina Faso,” International Journal of Environment and Climate Change, vol. 15, no. 12, pp. 195–221, 2025, doi: 10.9734/ijecc/2025/v15i125156.

BibTeX

@article{toguyeni2025deep,
  title     = {{U-NET Deep Learning-based Downscaling to Generate High-resolution Seasonal Forecasts for Small Watersheds: A Case Study of the Nouhao Sub-basin, Burkina Faso}},
  author    = {Toguyeni, Abdérahim and Doumounia, Ali and Djibo, Moumouni and Somda, Wenceslas and Damiba, Lucien and Zougmoré, François},
  journal   = {International Journal of Environment and Climate Change},
  year      = {2025},
  volume    = {15},
  number    = {12},
  pages     = {195--221},
  doi       = {10.9734/ijecc/2025/v15i125156},
  url       = {https://doi.org/10.9734/ijecc/2025/v15i125156}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Environmental Science › Environmental Engineering › Hydrological Forecasting Using AI

  • seasonal climate forecasting
  • U-Net
  • precipitation
  • air temperature
  • small watersheds
  • drought forecasting
  • flood forecasting
  • global climate models

Work with this paper

Most-cited papers in Environmental Science

All highly cited Environmental Science papers

Questions about this paper

How do I cite this paper in APA style?

Toguyeni, A., Doumounia, A., Djibo, M., Somda, W., Damiba, L., & Zougmoré, F. (2025). U-NET Deep Learning-based Downscaling to Generate High-resolution Seasonal Forecasts for Small Watersheds: A Case Study of the Nouhao Sub-basin, Burkina Faso. International Journal of Environment and Climate Change, 15(12), 195–221. https://doi.org/10.9734/ijecc/2025/v15i125156

How many times has this paper been cited?

0 times, according to OpenAlex on 21 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at International Journal of Environment and Climate Change: sign in and open the full text from this page.

Who wrote this paper?

Abdérahim Toguyeni, Ali Doumounia, Moumouni Djibo, Wenceslas Somda, Lucien Damiba, François Zougmoré.

What is the DOI of this paper?

10.9734/ijecc/2025/v15i125156, permanently at https://doi.org/10.9734/ijecc/2025/v15i125156. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 21 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.