Downscaling precipitation over High-mountain Asia using multi-fidelity Gaussian processes: improved estimates from ERA5

Tazi, Kenza; Orr, Andrew; Hernandez-González, Javier; Hosking, Scott; Turner, Richard E.

doi:https://doi.org/10.5194/hess-28-4903-2024

Articles | Volume 28, issue 22

https://doi.org/10.5194/hess-28-4903-2024

© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.

Special issue:

Hydrological response to climatic and cryospheric changes...

https://doi.org/10.5194/hess-28-4903-2024

© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 28, issue 22

Research article

|

18 Nov 2024

Research article |

| 18 Nov 2024

Downscaling precipitation over High-mountain Asia using multi-fidelity Gaussian processes: improved estimates from ERA5

Kenza Tazi, Andrew Orr, Javier Hernandez-González, Scott Hosking, and Richard E. Turner

Data sets

Downscaled ERA5 monthly precipitation data using Multi-Fidelity Gaussian Processes between 1980 and 2012 for the Upper Beas and Sutlej Basins, Himalayas Kenza Tazi https://doi.org/10.5285/b2099787-b57c-44ae-bf42-0d46d9ec87cc

ERA5 monthly averaged data on single levels from 1940 to present Copernicus Climate Change Service https://doi.org/10.24381/cds.f17050d7

VALUE ECA&D local observations VALUE http://www.value-cost.eu/data

GMTED2010 elevation data at different resolutions, Tropospheric Emission Monitoring Internet Service TROPOMI https://www.temis.nl/data/gmted2010/index.php

Global multi-resolution terrain elevation data 2010 (GMTED2010) Jeffrey J. Danielson and Dean B. Gesch https://doi.org/10.3133/ofr20111073

Model code and software

Code for 'Downscaling precipitation over High-mountain Asia using multi-fidelity Gaussian processes: improved estimates from ERA5' Kenza Tazi https://doi.org/10.5281/zenodo.14106487

Short summary

This work aims to improve the understanding of precipitation patterns in High-mountain Asia, a crucial water source for around 1.9 billion people. Through a novel machine learning method, we generate high-resolution precipitation predictions, including the likelihoods of floods and droughts. Compared to state-of-the-art methods, our method is simpler to implement and more suitable for small datasets. The method also shows accuracy comparable to or better than existing benchmark datasets.