b2099787-b57c-44ae-bf42-0d46d9ec87cc eng utf8 dataset dataset NERC EDS UK Polar Data Centre +44 (0)1223 221400 British Antarctic Survey, High Cross, Madingley Road Cambridge Cambridgeshire CB3 0ET United Kingdom polardatacentre@bas.ac.uk https://www.bas.ac.uk/team/business-teams/information-services/uk-polar-data-centre/ information pointOfContact 2023-08-09 ISO 19115 Geographic Information - Metadata ISO 19115:2003(E) European Petroleum Survey Group (EPSG) Geodetic Parameter Registry 2008-11-12 publication European Petroleum Survey Group EPSGadministrator@iogp.org https://www.epsg-registry.org/ EPSG Geodetic Parameter Dataset The EPSG Geodetic Parameter Dataset is a structured dataset of Coordinate Reference Systems and Coordinate Transformations, accessible through this online registry. information publisher urn:ogc:def:crs:EPSG::3031 6.18.3 Downscaled ERA5 monthly precipitation data using Multi-Fidelity Gaussian Processes between 1980 and 2012 for the Upper Beas and Sutlej Basins, Himalayas 2023-08-09 creation 2023-08-09 revision 2023-08-09 publication 2023-08-09 released 1.0 https://doi.org/10.5285/b2099787-b57c-44ae-bf42-0d46d9ec87cc doi GB/NERC/BAS/PDC/01769 https://data.bas.ac.uk/ Please cite this item as: Tazi, K. (2023). Downscaled ERA5 monthly precipitation data using Multi-Fidelity Gaussian Processes between 1980 and 2012 for the Upper Beas and Sutlej Basins, Himalayas (Version 1.0) [Data set]. NERC EDS UK Polar Data Centre. https://doi.org/10.5285/b2099787-b57c-44ae-bf42-0d46d9ec87cc The dataset is the output of a statistical model which downscales ERA5 monthly precipitation data using gauge measurements from the Upper Beas and Sutlej Basins in the Western Himalayas. Multi-Fidelity Gaussian Processes (MFGPs) are used to generate more accurate precipitation values between 1980 and 2012, including over ungauged areas of the basins. MFGPs are a probabilistic machine learning method that provides principled uncertainty estimates via the prediction of probability distributions. These predictions can therefore be used to estimate the likelihood of extreme precipitation events which have led to droughts, floods, and landslides. Funding from UK Engineering and Physical Sciences Research Council [grant number: 2270379]. No credit. completed Tazi, Kenza British Antarctic Survey Researcher author Tazi, Kenza University of Cambridge Researcher author NERC EDS UK Polar Data Centre +44 (0)1223 221400 British Antarctic Survey, High Cross, Madingley Road Cambridge Cambridgeshire CB3 0ET United Kingdom PDCServiceDesk@bas.ac.uk https://www.bas.ac.uk/team/business-teams/information-services/uk-polar-data-centre/ information pointOfContact asNeeded completed EARTH SCIENCE > Atmosphere > Precipitation > Precipitation Amount EARTH SCIENCE > Atmosphere > Precipitation theme Global Change Master Directory (GCMD) Science Keywords 2026-01-27 publication 23 Global Change Data Center, Science and Exploration Directorate, Goddard Space Flight Center (GSFC) National Aeronautics and Space Administration (NASA) Greenbelt MD United States of America https://earthdata.nasa.gov/about/gcmd/global-change-master-directory-gcmd-keywords Global Change Master Directory (GCMD) Keywords The information provided on this page seeks to define how the GCMD Keywords are structured, used and accessed. It also provides information on how users can participate in the further development of the keywords. information publisher ERA5 Himalayas downscaling machine learning precipitation theme Upper Beas Basin, Himalayas Asia Upper Sutlej Basin, Himalayas Asia place Atmospheric conditions theme GEMET - INSPIRE themes, version 1.0 2021-01-06 revision otherRestrictions no limitations to public access otherRestrictions no limitations license Open Government Licence v3.0 otherRestrictions Data supplied under Open Government Licence v3.0 otherRestrictions No restrictions apply. url url crossReference doi doi crossReference url url crossReference textTable eng utf8 climatologyMeteorologyAtmosphere 75.84375 82.40625 30.28125 32.90625 1980-01-01 2012-12-01 306.0 6295.0 urn:ogc:def:crs:EPSG::5714 MSL height Not specific to any location or epoch. Hydrography. It is recommended that careful attention be paid to the contents of any data, and that the author be contacted with any questions regarding appropriate use. If you find any errors or omissions, please report them to polardatacentre@bas.ac.uk. NERC EDS UK Polar Data Centre +44 (0)1223 221400 British Antarctic Survey, High Cross, Madingley Road Cambridge Cambridgeshire CB3 0ET United Kingdom PDCServiceDesk@bas.ac.uk https://www.bas.ac.uk/team/business-teams/information-services/uk-polar-data-centre/ information distributor text/plain text/csv application/x-hdf application/netcdf bytes 234881024 https://ramadda.data.bas.ac.uk/repository/entry/show?entryid=b2099787-b57c-44ae-bf42-0d46d9ec87cc WWW:LINK-1.0-http--link Get Data Download data download bytes 234881024 https://ramadda.data.bas.ac.uk/repository/entry/show?entryid=b2099787-b57c-44ae-bf42-0d46d9ec87cc WWW:LINK-1.0-http--link Get Data Download data download bytes 234881024 https://ramadda.data.bas.ac.uk/repository/entry/show?entryid=b2099787-b57c-44ae-bf42-0d46d9ec87cc WWW:LINK-1.0-http--link Get Data Download data download bytes 234881024 https://ramadda.data.bas.ac.uk/repository/entry/show?entryid=b2099787-b57c-44ae-bf42-0d46d9ec87cc WWW:LINK-1.0-http--link Get Data Download data download dataset Methodology: The MFGP model is trained using all stations data from Bannister et al. and ERA5 data over the study area (30 degrees North - 33.5 degrees North, 75.5 degrees East - 83 degrees East) between 1980 and 2012. The model takes as inputs time, latitude, longitude, and elevation. The raw model outputs the predictions at ERA5 and gauge fidelity levels in the form of normal distributions. The distributions need to be transformed to get the monthly precipitation values in mm/day. The dataset includes the raw mean and variance of the model output for both fidelity levels. The dataset also includes the transformed mean and upper and lower 95 percent confidence interval bounds for the high-fidelity output. This corresponds to the accurately downscaled data. The user can transform the data on their own via inverse Box-Cox transformations using the scaling factors separately provided. Data collection: Python v3.10 Data quality: Data is a model output so should be complete. NaNs in the netCDF file correspond to locations outside of the study areas. asNeeded completed