Improving surface melt estimation over the Antarctic Ice Sheet using deep learning: a proof of concept over the Larsen Ice Shelf

Hu, Z., Kuipers Munneke, P., Lhermitte, S., Izeboud, M., and van den Broeke, M.: Improving Surface Melt Estimation over Antarctica Using Deep Learning: A Proof-of-Concept over the Larsen Ice Shelf, The Cryosphere Discuss. [preprint], https://doi.org/10.5194/tc-2021-102, in review, 2021. --- (1) MLP_...

Full description

Bibliographic Details
Main Authors: Zhongyang Hu, Peter Kuipers Munneke, Stef Lhermitte, Maaike Izeboud, Michiel van den Broeke
Format: Dataset
Language:unknown
Published: 2021
Subjects:
Antarctic
Surface Melt
Deep Learning
Austral
Kuipers
Larsen Ice Shelf
The Antarctic
Antarc*
Antarctica
Ice Sheet
Ice Shelf
Online Access:https://zenodo.org/record/5764242
https://doi.org/10.5194/tc-2021-102
Description
Summary:Hu, Z., Kuipers Munneke, P., Lhermitte, S., Izeboud, M., and van den Broeke, M.: Improving Surface Melt Estimation over Antarctica Using Deep Learning: A Proof-of-Concept over the Larsen Ice Shelf, The Cryosphere Discuss. [preprint], https://doi.org/10.5194/tc-2021-102, in review, 2021. --- (1) MLP_model_surface_melt_corr.h5 is the developed MLP model used for correcting RACMO2 surface melt. (2) RACMO2_surface_melt_corr_MLP_AWS14.xlsx corrected surface melt [mm w.e. per day] from RACMO2 at AWS 14 during austral summers 2001 - 2016. The model inputs are (1) the simulated albedo, (2) the albedo difference between the observed and simulated albedo, (3) air temperature at 2m, (4) incoming shortwave radiation, (5) downwelling longwave radiation, (6) simulated surface melt, (7) Boolean melt flag, (8) surface melt difference to the previous day, and (9) record date as day of the year. (3) RACMO2_surface_melt_corr_MLP_AWS17.xlsx The same as point 2 but for AWS 17 (4) RACMO2_surface_melt_corr_MLP_AWS18.xlsx The same as point 2 but for AWS 18 Note: Data 2-4 are corrected RACMO2 simulations of surface melt at the pixels in RACMO2 27 km grid corresponding to AWS 14, 17, and 18 locations. They are not AWS observations. --- Related data set: MODIS/Terra Surface Reflectance Daily L2G Global 1 km and 500 m SIN Grid product is available via the Land Processes Distributed Active Archive Center (LP DAAC) (https://doi.org/10.5067/MODIS/MOD09GA.006, last access: 3 December 2021). MODIS/Terra+Aqua Albedo Daily L3 Global 500 m SIN Grid product is also available via LP DAAC (https://doi.org/10.5067/MODIS/MCD43A3.006, last access: 3 December 2021). Sentinel-1 images are provided by the European Space Agency (ESA) (https://sentinel.esa.int/web/sentinel/sentinel-data-access, last access: 3 December 2021). Automatic weather station observations from AWS 14, 17, and 18 are available via https://doi.pangaea.de/10.1594/PANGAEA.910473 (last access: 3 December 2021). RACMO2 simulations ...

Similar Items