This is a Preprint and has not been peer reviewed. This is version 1 of this Preprint.
Applicability of machine learning-based downscaling method to climate change prediction
Downloads
Supplementary Files
Authors
Takao Yoshikane 
,
Kei Yoshimura
Abstract
The precipitation characteristics that cause water-related disasters strongly depend on local factors such as topography. Therefore, high-resolution climate change projection data is needed to accurately assess regional flood disaster risk. Climate models generally have low resolution and are insufficient to reproduce observed precipitation distributions. Downscaling techniques are usually applied to estimate detailed precipitation distributions. In recent years, machine learning techniques have been widely adopted for downscaling to improve accuracy. However, data-driven machine learning methods have been criticized for issues such as an inability to make appropriate extrapolations when predicting climate change, and there are currently very few examples of their application in this context. In this study, a machine learning–based downscaling bias correction method that recognizes hourly weather patterns in past and future climates was applied and its validity was examined. This method enables temporal and spatial downscaling and bias correction of multiple variables related to hydrological processes, while adequately reproducing climate change characteristics in climate models that are difficult to achieve using conventional methods. Although each variable was estimated independently, the temporal changes were highly correlated with reanalysis values, indicating that the variables were interrelated. Therefore, this simple method of recognizing temporal and spatial distribution patterns can also be applied to hydrologically relevant climate model output variables, allowing downscaling and bias correction while accurately reflecting the climate change characteristics predicted by global climate models.
DOI
https://doi.org/10.31223/X55R29
Subjects
Oceanography and Atmospheric Sciences and Meteorology
Keywords
downscaling, climate change, machine learning
Dates
Published: 2026-01-30 00:49
Last Updated: 2026-01-30 00:49
License
CC BY Attribution 4.0 International
Additional Metadata
Data Availability (Reason not available):
In this study, we used the following three datasets:
1. ECMWF Reanalysis v5 (ERA5)
Hersbach H, Bell B, Berrisford P, Biavati G, Horányi A, Muñoz Sabater J, et al. ERA5 hourly data on single levels from 1940 to present. Copernicus Climate Change Service (C3S). 2023. doi:10.24381/cds.adbb2d47.
The data is available from the following web site:
https://cds.climate.copernicus.eu/datasets/reanalysis-era5-single-levels?tab=overview
2. 20th Century Reanalysis V3 contains objectively analyzed four-dimensional weather maps and their uncertainty from the early 19th century to the 21st century. (20CR Project).
Slivinski LC, Compo GP, Whitaker JS, Sardeshmukh PD, Giese BS, McColl C, et al. Towards a more reliable historical reanalysis: improvements for version 3 of the twentieth-century reanalysis system. Q J R Meteorol Soc. 2019145(724):2876–2908.
The data is available from the following web site:
https://www.psl.noaa.gov/data/gridded/data.20thC_ReanV3.html
3. CMIP6 MIROC (MIROC) simulations (r1i1p1f1, historical and ssp126 scenario )
Shiogama H, Abe M, Tatebe H. MIROC6 model output prepared for CMIP6 ScenarioMIP. Earth Syst Grid Fed. 2019. doi:10.22033/ESGF/CMIP6.898.
https://ipcc-browser.ipcc-data.org/browser/dataset/6993
The data is available from the following web site:
https://esgf-data.ucar.edu/thredds/catalog/catalog.html
Conflict of interest statement:
We have no conflict to interest to declare.
Metrics
Views: 30
Downloads: 2
There are no comments or no comments have been made public for this article.