DeepBedMap: Using a deep neural network to better resolve the bed topography of Antarctica
To better resolve the bed elevation of Antarctica, we present DeepBedMap – a novel machine learning method that produces realistic Antarctic bed topography from multiple remote sensing data inputs. Our super-resolution deep convolutional neural network model is trained on scattered regions in Antarc...
Main Authors: | , |
---|---|
Format: | Text |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://doi.org/10.5194/tc-2020-74 https://tc.copernicus.org/preprints/tc-2020-74/ |
id |
ftcopernicus:oai:publications.copernicus.org:tcd84539 |
---|---|
record_format |
openpolar |
spelling |
ftcopernicus:oai:publications.copernicus.org:tcd84539 2023-05-15T13:55:28+02:00 DeepBedMap: Using a deep neural network to better resolve the bed topography of Antarctica Leong, Wei Ji Horgan, Huw Joseph 2020-04-16 application/pdf https://doi.org/10.5194/tc-2020-74 https://tc.copernicus.org/preprints/tc-2020-74/ eng eng doi:10.5194/tc-2020-74 https://tc.copernicus.org/preprints/tc-2020-74/ eISSN: 1994-0424 Text 2020 ftcopernicus https://doi.org/10.5194/tc-2020-74 2020-07-20T16:22:17Z To better resolve the bed elevation of Antarctica, we present DeepBedMap – a novel machine learning method that produces realistic Antarctic bed topography from multiple remote sensing data inputs. Our super-resolution deep convolutional neural network model is trained on scattered regions in Antarctica where high resolution (250 m) groundtruth bed elevation grids are available. The model is then used to generate high resolution bed topography in less well 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. 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. Our DeepBedMap model is based on an adapted Enhanced Super Resolution Generative Adversarial Network architecture, 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 more realistic topographic roughness profile compared to a standard bicubic interpolated BEDMAP2 and BedMachine Antarctica, and envision it to be used where a high resolution bed elevation model is required. Text Antarc* Antarctic Antarctica Ice Sheet Copernicus Publications: E-Journals Antarctic |
institution |
Open Polar |
collection |
Copernicus Publications: E-Journals |
op_collection_id |
ftcopernicus |
language |
English |
description |
To better resolve the bed elevation of Antarctica, we present DeepBedMap – a novel machine learning method that produces realistic Antarctic bed topography from multiple remote sensing data inputs. Our super-resolution deep convolutional neural network model is trained on scattered regions in Antarctica where high resolution (250 m) groundtruth bed elevation grids are available. The model is then used to generate high resolution bed topography in less well 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. 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. Our DeepBedMap model is based on an adapted Enhanced Super Resolution Generative Adversarial Network architecture, 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 more realistic topographic roughness profile compared to a standard bicubic interpolated BEDMAP2 and BedMachine Antarctica, and envision it to be 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: Using a deep neural network to better resolve the bed topography of Antarctica |
author_facet |
Leong, Wei Ji Horgan, Huw Joseph |
author_sort |
Leong, Wei Ji |
title |
DeepBedMap: Using a deep neural network to better resolve the bed topography of Antarctica |
title_short |
DeepBedMap: Using a deep neural network to better resolve the bed topography of Antarctica |
title_full |
DeepBedMap: Using a deep neural network to better resolve the bed topography of Antarctica |
title_fullStr |
DeepBedMap: Using a deep neural network to better resolve the bed topography of Antarctica |
title_full_unstemmed |
DeepBedMap: Using a deep neural network to better resolve the bed topography of Antarctica |
title_sort |
deepbedmap: using a deep neural network to better resolve the bed topography of antarctica |
publishDate |
2020 |
url |
https://doi.org/10.5194/tc-2020-74 https://tc.copernicus.org/preprints/tc-2020-74/ |
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-2020-74 https://tc.copernicus.org/preprints/tc-2020-74/ |
op_doi |
https://doi.org/10.5194/tc-2020-74 |
_version_ |
1766262091877974016 |