DeepBedMap: a deep neural network for resolving the bed topography of Antarctica
To resolve the bed elevation of Antarctica, we present DeepBedMap – a novel machine learning method that can produce Antarctic bed topography with adequate surface roughness from multiple remote sensing data inputs. The super-resolution deep convolutional neural network model is trained on scattered...
Published in: | The Cryosphere |
---|---|
Main Authors: | , |
Format: | Text |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://doi.org/10.5194/tc-14-3687-2020 https://tc.copernicus.org/articles/14/3687/2020/ |
id |
ftcopernicus:oai:publications.copernicus.org:tc84539 |
---|---|
record_format |
openpolar |
spelling |
ftcopernicus:oai:publications.copernicus.org:tc84539 2023-05-15T13:31:39+02:00 DeepBedMap: a deep neural network for resolving the bed topography of Antarctica Leong, Wei Ji Horgan, Huw Joseph 2020-11-05 application/pdf https://doi.org/10.5194/tc-14-3687-2020 https://tc.copernicus.org/articles/14/3687/2020/ eng eng doi:10.5194/tc-14-3687-2020 https://tc.copernicus.org/articles/14/3687/2020/ eISSN: 1994-0424 Text 2020 ftcopernicus https://doi.org/10.5194/tc-14-3687-2020 2020-11-09T17:22:15Z To resolve the bed elevation of Antarctica, we present DeepBedMap – a novel machine learning method that can produce Antarctic bed topography with adequate surface roughness from multiple remote sensing data inputs. The super-resolution deep convolutional neural network model is trained on scattered regions in Antarctica where high-resolution (250 m ) ground-truth bed elevation grids are available. This model is then used to generate high-resolution bed topography in less surveyed areas. DeepBedMap improves on previous interpolation methods by not restricting itself to a low-spatial-resolution (1000 m ) BEDMAP2 raster image as its prior image. It takes in additional high-spatial-resolution datasets, such as ice surface elevation, velocity and snow accumulation, to better inform the bed topography even in the absence of ice thickness data from direct ice-penetrating-radar surveys. The DeepBedMap model is based on an adapted architecture of the Enhanced Super-Resolution Generative Adversarial Network, chosen to minimize per-pixel elevation errors while producing realistic topography. The final product is a four-times-upsampled (250 m ) bed elevation model of Antarctica that can be used by glaciologists interested in the subglacial terrain and by ice sheet modellers wanting to run catchment- or continent-scale ice sheet model simulations. We show that DeepBedMap offers a rougher topographic profile compared to the standard bicubically interpolated BEDMAP2 and BedMachine Antarctica and envision it being used where a high-resolution bed elevation model is required. Text Antarc* Antarctic Antarctica Ice Sheet Copernicus Publications: E-Journals Antarctic The Cryosphere 14 11 3687 3705 |
institution |
Open Polar |
collection |
Copernicus Publications: E-Journals |
op_collection_id |
ftcopernicus |
language |
English |
description |
To resolve the bed elevation of Antarctica, we present DeepBedMap – a novel machine learning method that can produce Antarctic bed topography with adequate surface roughness from multiple remote sensing data inputs. The super-resolution deep convolutional neural network model is trained on scattered regions in Antarctica where high-resolution (250 m ) ground-truth bed elevation grids are available. This model is then used to generate high-resolution bed topography in less surveyed areas. DeepBedMap improves on previous interpolation methods by not restricting itself to a low-spatial-resolution (1000 m ) BEDMAP2 raster image as its prior image. It takes in additional high-spatial-resolution datasets, such as ice surface elevation, velocity and snow accumulation, to better inform the bed topography even in the absence of ice thickness data from direct ice-penetrating-radar surveys. The DeepBedMap model is based on an adapted architecture of the Enhanced Super-Resolution Generative Adversarial Network, chosen to minimize per-pixel elevation errors while producing realistic topography. The final product is a four-times-upsampled (250 m ) bed elevation model of Antarctica that can be used by glaciologists interested in the subglacial terrain and by ice sheet modellers wanting to run catchment- or continent-scale ice sheet model simulations. We show that DeepBedMap offers a rougher topographic profile compared to the standard bicubically interpolated BEDMAP2 and BedMachine Antarctica and envision it being used where a high-resolution bed elevation model is required. |
format |
Text |
author |
Leong, Wei Ji Horgan, Huw Joseph |
spellingShingle |
Leong, Wei Ji Horgan, Huw Joseph DeepBedMap: a deep neural network for resolving the bed topography of Antarctica |
author_facet |
Leong, Wei Ji Horgan, Huw Joseph |
author_sort |
Leong, Wei Ji |
title |
DeepBedMap: a deep neural network for resolving the bed topography of Antarctica |
title_short |
DeepBedMap: a deep neural network for resolving the bed topography of Antarctica |
title_full |
DeepBedMap: a deep neural network for resolving the bed topography of Antarctica |
title_fullStr |
DeepBedMap: a deep neural network for resolving the bed topography of Antarctica |
title_full_unstemmed |
DeepBedMap: a deep neural network for resolving the bed topography of Antarctica |
title_sort |
deepbedmap: a deep neural network for resolving the bed topography of antarctica |
publishDate |
2020 |
url |
https://doi.org/10.5194/tc-14-3687-2020 https://tc.copernicus.org/articles/14/3687/2020/ |
geographic |
Antarctic |
geographic_facet |
Antarctic |
genre |
Antarc* Antarctic Antarctica Ice Sheet |
genre_facet |
Antarc* Antarctic Antarctica Ice Sheet |
op_source |
eISSN: 1994-0424 |
op_relation |
doi:10.5194/tc-14-3687-2020 https://tc.copernicus.org/articles/14/3687/2020/ |
op_doi |
https://doi.org/10.5194/tc-14-3687-2020 |
container_title |
The Cryosphere |
container_volume |
14 |
container_issue |
11 |
container_start_page |
3687 |
op_container_end_page |
3705 |
_version_ |
1766019814009077760 |