Separating the albedo-reducing effect of different light-absorbing particles on snow using deep learning

<p>Several different types of light-absorbing particles (LAPs) darken snow surfaces, enhancing snowmelt on glaciers and snowfields. LAPs are often present as a mixture of biotic and abiotic components at the snow surface, yet methods to separate their respective abundance and albedo-reducing e...

Full description

Saved in:
Bibliographic Details
Main Authors: L.-A. Chevrollier, A. Wehrlé, J. M. Cook, N. Pirk, L. G. Benning, A. M. Anesio, M. Tranter
Format: Article
Language:English
Published: Copernicus Publications 2025-04-01
Series:The Cryosphere
Online Access:https://tc.copernicus.org/articles/19/1527/2025/tc-19-1527-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850266108705112064
author L.-A. Chevrollier
A. Wehrlé
J. M. Cook
N. Pirk
L. G. Benning
A. M. Anesio
M. Tranter
author_facet L.-A. Chevrollier
A. Wehrlé
J. M. Cook
N. Pirk
L. G. Benning
A. M. Anesio
M. Tranter
author_sort L.-A. Chevrollier
collection DOAJ
description <p>Several different types of light-absorbing particles (LAPs) darken snow surfaces, enhancing snowmelt on glaciers and snowfields. LAPs are often present as a mixture of biotic and abiotic components at the snow surface, yet methods to separate their respective abundance and albedo-reducing effects are lacking. Here, we present a new optimisation method enabling the retrievals of dust, black carbon, and red algal abundances and their respective darkening effects from spectral albedo. This method includes a deep-learning emulator of a radiative transfer model (RTM) and an inversion algorithm. The emulator alone can be used as a fast and lightweight alternative to the full RTM with the possibility to add new features, such as new light-absorbing particles. The inversion method was applied to 180 ground field spectra collected on snowfields in southern Norway, with a mean absolute error on spectral albedo of 0.0056, and surface parameters that closely matched expectations from qualitative assessments of the surface. The emulator predictions of surface parameters were used to quantify the albedo-reducing effect of algal blooms, mineral dust, and dark particles represented by black carbon. Among these 180 surfaces, the albedo reduction due to light-absorbing particles was highly variable and reached up to 0.13, 0.21, and 0.25 for red algal blooms, mineral dust, and dark particles respectively. In addition, the effect of a single LAP was attenuated by the presence of other LAPs by up to 2–3 times. These results demonstrate the importance of considering the individual types of light-absorbing particles and their concomitant interactions for forecasting snow albedo.</p>
format Article
id doaj-art-75fff67e00c4447b9afe023eb8a4e7d5
institution OA Journals
issn 1994-0416
1994-0424
language English
publishDate 2025-04-01
publisher Copernicus Publications
record_format Article
series The Cryosphere
spelling doaj-art-75fff67e00c4447b9afe023eb8a4e7d52025-08-20T01:54:15ZengCopernicus PublicationsThe Cryosphere1994-04161994-04242025-04-01191527153810.5194/tc-19-1527-2025Separating the albedo-reducing effect of different light-absorbing particles on snow using deep learningL.-A. Chevrollier0A. Wehrlé1J. M. Cook2N. Pirk3L. G. Benning4A. M. Anesio5M. Tranter6Department of Environmental Science, iClimate, Aarhus University, Roskilde, DenmarkInstitute of Geography, University of Zürich, Zürich, SwitzerlandDepartment of Environmental Science, iClimate, Aarhus University, Roskilde, DenmarkDepartment of Geosciences, University of Oslo, Oslo, NorwayGFZ, Helmholtz Centre for Geosciences, Potsdam, Germany, and Department of Earth Sciences, Free University of Berlin, Berlin, GermanyDepartment of Environmental Science, iClimate, Aarhus University, Roskilde, DenmarkDepartment of Environmental Science, iClimate, Aarhus University, Roskilde, Denmark<p>Several different types of light-absorbing particles (LAPs) darken snow surfaces, enhancing snowmelt on glaciers and snowfields. LAPs are often present as a mixture of biotic and abiotic components at the snow surface, yet methods to separate their respective abundance and albedo-reducing effects are lacking. Here, we present a new optimisation method enabling the retrievals of dust, black carbon, and red algal abundances and their respective darkening effects from spectral albedo. This method includes a deep-learning emulator of a radiative transfer model (RTM) and an inversion algorithm. The emulator alone can be used as a fast and lightweight alternative to the full RTM with the possibility to add new features, such as new light-absorbing particles. The inversion method was applied to 180 ground field spectra collected on snowfields in southern Norway, with a mean absolute error on spectral albedo of 0.0056, and surface parameters that closely matched expectations from qualitative assessments of the surface. The emulator predictions of surface parameters were used to quantify the albedo-reducing effect of algal blooms, mineral dust, and dark particles represented by black carbon. Among these 180 surfaces, the albedo reduction due to light-absorbing particles was highly variable and reached up to 0.13, 0.21, and 0.25 for red algal blooms, mineral dust, and dark particles respectively. In addition, the effect of a single LAP was attenuated by the presence of other LAPs by up to 2–3 times. These results demonstrate the importance of considering the individual types of light-absorbing particles and their concomitant interactions for forecasting snow albedo.</p>https://tc.copernicus.org/articles/19/1527/2025/tc-19-1527-2025.pdf
spellingShingle L.-A. Chevrollier
A. Wehrlé
J. M. Cook
N. Pirk
L. G. Benning
A. M. Anesio
M. Tranter
Separating the albedo-reducing effect of different light-absorbing particles on snow using deep learning
The Cryosphere
title Separating the albedo-reducing effect of different light-absorbing particles on snow using deep learning
title_full Separating the albedo-reducing effect of different light-absorbing particles on snow using deep learning
title_fullStr Separating the albedo-reducing effect of different light-absorbing particles on snow using deep learning
title_full_unstemmed Separating the albedo-reducing effect of different light-absorbing particles on snow using deep learning
title_short Separating the albedo-reducing effect of different light-absorbing particles on snow using deep learning
title_sort separating the albedo reducing effect of different light absorbing particles on snow using deep learning
url https://tc.copernicus.org/articles/19/1527/2025/tc-19-1527-2025.pdf
work_keys_str_mv AT lachevrollier separatingthealbedoreducingeffectofdifferentlightabsorbingparticlesonsnowusingdeeplearning
AT awehrle separatingthealbedoreducingeffectofdifferentlightabsorbingparticlesonsnowusingdeeplearning
AT jmcook separatingthealbedoreducingeffectofdifferentlightabsorbingparticlesonsnowusingdeeplearning
AT npirk separatingthealbedoreducingeffectofdifferentlightabsorbingparticlesonsnowusingdeeplearning
AT lgbenning separatingthealbedoreducingeffectofdifferentlightabsorbingparticlesonsnowusingdeeplearning
AT amanesio separatingthealbedoreducingeffectofdifferentlightabsorbingparticlesonsnowusingdeeplearning
AT mtranter separatingthealbedoreducingeffectofdifferentlightabsorbingparticlesonsnowusingdeeplearning