TY - JOUR
T1 - A sensor-agnostic albedo retrieval method for realistic sea ice surfaces
T2 - model and validation
AU - Zhou, Yingzhen
AU - Li, Wei
AU - Chen, Nan
AU - Fan, Yongzhen
AU - Stamnes, Knut
N1 - Publisher Copyright:
© 2023 Yingzhen Zhou et al.
PY - 2023/3/3
Y1 - 2023/3/3
N2 - A framework was established for remote sensing of sea ice albedo that integrates sea ice physics with high computational efficiency and that can be applied to optical sensors that measure appropriate radiance data. A scientific machine learning (SciML) approach was developed and trained on a large synthetic dataset (SD) constructed using a coupled atmosphere-surface radiative transfer model (RTM). The resulting RTM-SciML framework combines the RTM with a multi-layer artificial neural network SciML model. In contrast to the Moderate Resolution Imaging Spectroradiometer (MODIS) MCD43 albedo product, this framework does not depend on observations from multiple days and can be applied to single angular observations obtained under clear-sky conditions. Compared to the existing melt pond detection (MPD)-based approach for albedo retrieval, the RTM-SciML framework has the advantage of being applicable to a wide variety of cryosphere surfaces, both heterogeneous and homogeneous. Excellent agreement was found between the RTM-SciML albedo retrieval results and measurements collected from airplane campaigns. Assessment against pyranometer data (NCombining double low line4144) yields RMSE Combining double low line 0.094 for the shortwave albedo retrieval, while evaluation against albedometer data (NCombining double low line1225) yields RMSE Combining double low line 0.069, 0.143, and 0.085 for the broadband albedo in the visible, near-infrared, and shortwave spectral ranges, respectively.
AB - A framework was established for remote sensing of sea ice albedo that integrates sea ice physics with high computational efficiency and that can be applied to optical sensors that measure appropriate radiance data. A scientific machine learning (SciML) approach was developed and trained on a large synthetic dataset (SD) constructed using a coupled atmosphere-surface radiative transfer model (RTM). The resulting RTM-SciML framework combines the RTM with a multi-layer artificial neural network SciML model. In contrast to the Moderate Resolution Imaging Spectroradiometer (MODIS) MCD43 albedo product, this framework does not depend on observations from multiple days and can be applied to single angular observations obtained under clear-sky conditions. Compared to the existing melt pond detection (MPD)-based approach for albedo retrieval, the RTM-SciML framework has the advantage of being applicable to a wide variety of cryosphere surfaces, both heterogeneous and homogeneous. Excellent agreement was found between the RTM-SciML albedo retrieval results and measurements collected from airplane campaigns. Assessment against pyranometer data (NCombining double low line4144) yields RMSE Combining double low line 0.094 for the shortwave albedo retrieval, while evaluation against albedometer data (NCombining double low line1225) yields RMSE Combining double low line 0.069, 0.143, and 0.085 for the broadband albedo in the visible, near-infrared, and shortwave spectral ranges, respectively.
UR - http://www.scopus.com/inward/record.url?scp=85149448081&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85149448081&partnerID=8YFLogxK
U2 - 10.5194/tc-17-1053-2023
DO - 10.5194/tc-17-1053-2023
M3 - Article
AN - SCOPUS:85149448081
SN - 1994-0416
VL - 17
SP - 1053
EP - 1087
JO - Cryosphere
JF - Cryosphere
IS - 2
ER -