Preprints
https://doi.org/10.5194/egusphere-2023-2145
https://doi.org/10.5194/egusphere-2023-2145
24 Nov 2023
 | 24 Nov 2023
Status: this preprint is open for discussion.

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

Abstract. The rivers of High Mountain Asia provide freshwater to around 2 billion people. However, precipitation, the main driver of river flow, is still poorly understood due to limited direct measurements in this area. Existing tools to interpolate these measurements or downscale and bias-correct precipitation models have several limitations. To overcome these challenges, this paper uses a probabilistic machine learning approach called Multi-Fidelity Gaussian Processes (MFGPs) to downscale ERA5 climate reanalysis. The method is first validated by downscaling ERA5 precipitation data over data-rich Europe and then data-sparse Upper Beas and Sutlej River Basins in the Himalayas. We find that MFGPs are simpler to implement and more applicable to smaller datasets than other state-of-the-art machine learning models. MFGPs are also able to quantify and narrow the uncertainty associated with the precipitation estimates, which is especially needed over ungauged areas, and can be used to estimate the likelihood of extreme events that lead to floods or droughts. Over the Upper Beas and Sutlej River Basins, the precipitation estimates from the MFGP model are similar to or more accurate than available gridded precipitation products (APHRODITE, TRMM, CRU, bias-corrected WRF). The MFGP model and APHRODITE annual mean precipitation estimates generally agree with each other for this region. The MFGP model predicting slightly higher average precipitation and variance. However, more significant spatial deviations between the MFGP model and APHRODITE over this region appear during the summer monsoon. The MFGP model also presents a more effective spatial resolution of precipitation, generating more structure at finer scales than ERA5 and APHRODITE. MFGP precipitation estimates for the Upper Beas and Sutlej Basins between 1980 and 2013 at a 0.0625° resolution (approx. 9 km) are jointly published with this paper.

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

Status: open (extended)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
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

Model code and software

mfgp Kenza Tazi https://github.com/kenzaxtazi/mfgp

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

Viewed

Total article views: 373 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
244 121 8 373 13 8
  • HTML: 244
  • PDF: 121
  • XML: 8
  • Total: 373
  • BibTeX: 13
  • EndNote: 8
Views and downloads (calculated since 24 Nov 2023)
Cumulative views and downloads (calculated since 24 Nov 2023)

Viewed (geographical distribution)

Total article views: 359 (including HTML, PDF, and XML) Thereof 359 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 03 Mar 2024
Download
Short summary
This work aims to improve the understanding of precipitation patterns in High Mountain Asia, a crucial water source for around 2 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 comparable or better accuracy to existing benchmark datasets.