Precipitation prediction over the upper Indus Basin from large-scale circulation patterns using Gaussian processes

Tazi, Kenza; Orr, Andrew; Hosking, J. Scott; Turner, Richard E.

Precipitation prediction over the upper Indus Basin from large-scale circulation patterns using Gaussian processes

Tazi, Kenza ORCID: https://orcid.org/0000-0002-8169-6673; Orr, Andrew ORCID: https://orcid.org/0000-0001-5111-8402; Hosking, J. Scott ORCID: https://orcid.org/0000-0002-3646-3504; Turner, Richard E.. 2025 Precipitation prediction over the upper Indus Basin from large-scale circulation patterns using Gaussian processes. Environmental Data Science, 4, e46. 18, pp. 10.1017/eds.2025.10020

Before downloading, please read NORA policies.

Preview

Text (Open Access)
© The Author(s), 2025. Published by Cambridge University Press.
precipitation-prediction-over-the-upper-indus-basin-from-large-scale-circulation-patterns-using-gaussian-processes.pdf - Published Version
Available under License Creative Commons Attribution 4.0.
Download (1MB) | Preview

Official URL: https://doi.org/10.1017/eds.2025.10020

Abstract/Summary

Water resources from the Indus Basin sustain over 270 million people. However, water security in this region is threatened by climate change. This is especially the case for the upper Indus Basin, where most frozen water reserves are expected to decrease significantly by the end of the century, leaving rainfall as the main driver of river flow. However, future precipitation estimates from global climate models differ greatly for this region. To address this uncertainty, this paper explores the feasibility of using probabilistic machine learning to map large-scale circulation fields, better represented by global climate models, to local precipitation over the upper Indus Basin. More specifically, Gaussian processes are trained to predict monthly ERA5 precipitation data over a 15-year horizon. This paper also explores different Gaussian process model designs, including a non-stationary covariance function to learn complex spatial relationships in the data. Going forward, this approach could be used to make more accurate predictions from global climate model outputs and better assess the probability of future precipitation extremes.

Item Type:

Publication - Article

Digital Object Identifier (DOI):

10.1017/eds.2025.10020

ISSN:

2634-4602

Additional Keywords:

Gaussian processes, mountains, non-stationary covariance, precipitation, probabilistic machine learning

Date made live:

06 Oct 2025 08:51 +0 (UTC)

URI:

https://nora.nerc.ac.uk/id/eprint/540346