Spatio-temporal reconstruction of winter glacier mass balance in the Alps, Scandinavia, Central Asia and western Canada (1981–2019) using climate reanalyses and machine learning
Spatio-temporal reconstruction of winter glacier mass balance is important for assessing long-term impacts of climate change. However, high-altitude regions significantly lack reliable observations, which is limiting the calibration of glaciological and hydrological models. Reanalysis products provi...
Published in: | The Cryosphere |
---|---|
Main Authors: | , , , |
Format: | Text |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://doi.org/10.5194/tc-17-977-2023 https://tc.copernicus.org/articles/17/977/2023/ |
id |
ftcopernicus:oai:publications.copernicus.org:tc102066 |
---|---|
record_format |
openpolar |
spelling |
ftcopernicus:oai:publications.copernicus.org:tc102066 2023-05-15T16:22:25+02:00 Spatio-temporal reconstruction of winter glacier mass balance in the Alps, Scandinavia, Central Asia and western Canada (1981–2019) using climate reanalyses and machine learning Guidicelli, Matteo Huss, Matthias Gabella, Marco Salzmann, Nadine 2023-03-01 application/pdf https://doi.org/10.5194/tc-17-977-2023 https://tc.copernicus.org/articles/17/977/2023/ eng eng doi:10.5194/tc-17-977-2023 https://tc.copernicus.org/articles/17/977/2023/ eISSN: 1994-0424 Text 2023 ftcopernicus https://doi.org/10.5194/tc-17-977-2023 2023-03-06T17:23:09Z Spatio-temporal reconstruction of winter glacier mass balance is important for assessing long-term impacts of climate change. However, high-altitude regions significantly lack reliable observations, which is limiting the calibration of glaciological and hydrological models. Reanalysis products provide estimates of snow precipitation also for remote high-mountain regions, but this data come with inherent uncertainty, and assessing their biases is difficult given the low quantity and quality of available (long-term) in situ observations. In this study, we aim at improving knowledge on the spatio-temporal variations in winter glacier mass balance by exploring the combination of data from reanalyses and direct snow accumulation observations on glaciers using machine learning. We use the winter mass balance data of 95 glaciers distributed over the European Alps, western Canada, Central Asia and Scandinavia and compare them with the total precipitation from the ERA5 and the MERRA-2 reanalysis products during the snow accumulation seasons from 1981 until 2019. We develop and apply a machine learning model to adjust the precipitation from the reanalysis products along the elevation profile of the glaciers and consequently to reconstruct the winter mass balance in both space (for glaciers without observational data) and time (filling observational data gaps). The employed machine learning model is a gradient boosting regressor (GBR), which combines several meteorological variables from the reanalyses (e.g. air temperature, relative humidity) with topographical parameters. These GBR-derived estimates are evaluated against the winter mass balance data using (i) independent glaciers (site-independent GBR) and (ii) independent accumulation seasons (season-independent GBR). Both approaches resulted in reduced biases and increased correlation between the precipitation of the original reanalyses and the winter mass balance data of the glaciers. Generally, the GBR models have also shown a good representation of the spatial ... Text glacier* Copernicus Publications: E-Journals Canada Merra ENVELOPE(12.615,12.615,65.816,65.816) The Cryosphere 17 2 977 1002 |
institution |
Open Polar |
collection |
Copernicus Publications: E-Journals |
op_collection_id |
ftcopernicus |
language |
English |
description |
Spatio-temporal reconstruction of winter glacier mass balance is important for assessing long-term impacts of climate change. However, high-altitude regions significantly lack reliable observations, which is limiting the calibration of glaciological and hydrological models. Reanalysis products provide estimates of snow precipitation also for remote high-mountain regions, but this data come with inherent uncertainty, and assessing their biases is difficult given the low quantity and quality of available (long-term) in situ observations. In this study, we aim at improving knowledge on the spatio-temporal variations in winter glacier mass balance by exploring the combination of data from reanalyses and direct snow accumulation observations on glaciers using machine learning. We use the winter mass balance data of 95 glaciers distributed over the European Alps, western Canada, Central Asia and Scandinavia and compare them with the total precipitation from the ERA5 and the MERRA-2 reanalysis products during the snow accumulation seasons from 1981 until 2019. We develop and apply a machine learning model to adjust the precipitation from the reanalysis products along the elevation profile of the glaciers and consequently to reconstruct the winter mass balance in both space (for glaciers without observational data) and time (filling observational data gaps). The employed machine learning model is a gradient boosting regressor (GBR), which combines several meteorological variables from the reanalyses (e.g. air temperature, relative humidity) with topographical parameters. These GBR-derived estimates are evaluated against the winter mass balance data using (i) independent glaciers (site-independent GBR) and (ii) independent accumulation seasons (season-independent GBR). Both approaches resulted in reduced biases and increased correlation between the precipitation of the original reanalyses and the winter mass balance data of the glaciers. Generally, the GBR models have also shown a good representation of the spatial ... |
format |
Text |
author |
Guidicelli, Matteo Huss, Matthias Gabella, Marco Salzmann, Nadine |
spellingShingle |
Guidicelli, Matteo Huss, Matthias Gabella, Marco Salzmann, Nadine Spatio-temporal reconstruction of winter glacier mass balance in the Alps, Scandinavia, Central Asia and western Canada (1981–2019) using climate reanalyses and machine learning |
author_facet |
Guidicelli, Matteo Huss, Matthias Gabella, Marco Salzmann, Nadine |
author_sort |
Guidicelli, Matteo |
title |
Spatio-temporal reconstruction of winter glacier mass balance in the Alps, Scandinavia, Central Asia and western Canada (1981–2019) using climate reanalyses and machine learning |
title_short |
Spatio-temporal reconstruction of winter glacier mass balance in the Alps, Scandinavia, Central Asia and western Canada (1981–2019) using climate reanalyses and machine learning |
title_full |
Spatio-temporal reconstruction of winter glacier mass balance in the Alps, Scandinavia, Central Asia and western Canada (1981–2019) using climate reanalyses and machine learning |
title_fullStr |
Spatio-temporal reconstruction of winter glacier mass balance in the Alps, Scandinavia, Central Asia and western Canada (1981–2019) using climate reanalyses and machine learning |
title_full_unstemmed |
Spatio-temporal reconstruction of winter glacier mass balance in the Alps, Scandinavia, Central Asia and western Canada (1981–2019) using climate reanalyses and machine learning |
title_sort |
spatio-temporal reconstruction of winter glacier mass balance in the alps, scandinavia, central asia and western canada (1981–2019) using climate reanalyses and machine learning |
publishDate |
2023 |
url |
https://doi.org/10.5194/tc-17-977-2023 https://tc.copernicus.org/articles/17/977/2023/ |
long_lat |
ENVELOPE(12.615,12.615,65.816,65.816) |
geographic |
Canada Merra |
geographic_facet |
Canada Merra |
genre |
glacier* |
genre_facet |
glacier* |
op_source |
eISSN: 1994-0424 |
op_relation |
doi:10.5194/tc-17-977-2023 https://tc.copernicus.org/articles/17/977/2023/ |
op_doi |
https://doi.org/10.5194/tc-17-977-2023 |
container_title |
The Cryosphere |
container_volume |
17 |
container_issue |
2 |
container_start_page |
977 |
op_container_end_page |
1002 |
_version_ |
1766010392607195136 |