Exploiting the ANN potential in estimating Snow Depth and Snow Water Equivalent from the airborne SnowSAR data at X and Ku bands

Santi, Emanuele, Brogioni, Marco, Leduc-Leballeur, Marion, Macelloni, Giovanni, Montomoli, Francesco, Pampaloni, Paolo, Lemmetyinen, Juha, Cohen, Juval, Rott, Helmut, Nagler, Thomas, Derksen, Chris, King, Josh, Rutter, Nick, Essery, Richard, Menard, Cecile, Sandells, Melody and Kern, Michael (0202) Exploiting the ANN potential in estimating Snow Depth and Snow Water Equivalent from the airborne SnowSAR data at X and Ku bands. IEEE Transactions on Geoscience and Remote Sensing, 60. pp. 1-16. ISSN 0196-2892

SCADAS_R2_Santi_et_al_2021_in_TGARS.pdf - Accepted Version

Download (1MB) | Preview
Official URL: https://doi.org/10.1109/tgrs.2021.3086893


Within the framework of European Space Agency (ESA) activities, several campaigns were carried out in the last decade with the purpose of exploiting the capabilities of multifrequency synthetic aperture radar (SAR) data to retrieve snow information. This article presents the results obtained from the ESA SnowSAR airborne campaigns, carried out between 2011 and 2013 on boreal forest, tundra and alpine environments, selected as representative of different snow regimes. The aim of this study was to assess the capability of X- and Ku-bands SAR in retrieving the snow parameters, namely snow depth (SD) and snow water equivalent (SWE). The retrieval was based on machine learning (ML) techniques and, in particular, of artificial neural networks (ANNs). ANNs have been selected among other ML approaches since they are capable to offer a good compromise between retrieval accuracy and computational cost. Two approaches were evaluated, the first based on the experimental data (data driven) and the second based on data simulated by the dense medium radiative transfer (DMRT). The data driven algorithm was trained on half of the SnowSAR dataset and validated on the remaining half. The validation resulted in a correlation coefficient R ≃ 0.77 between estimated and target SD, a root-mean-square error (RMSE) ≃ 13 cm, and bias = 0.03 cm. ANN algorithms specific for each test site were also implemented, obtaining more accurate results, and the robustness of the data driven approach was evaluated over time and space. The algorithm trained with DMRT simulations and tested on the experimental dataset was able to estimate the target parameter (SWE in this case) with R = 0.74, RMSE = 34.8 mm, and bias = 1.8 mm. The model driven approach had the twofold advantage of reducing the amount of in situ data required for training the algorithm and of extending the algorithm exportability to other test sites.

Item Type: Article
Additional Information: Funding information: This study was carried out under the European Space Agency Contract "SnowSAR Campaign Data Analysis Study", C4000118400/16/NL/FF/gp. This support is gratefully acknowledged.
Uncontrolled Keywords: SnowSAR, Snow Depth, Snow Water Equivalent, SAR, Artificial Neural Networks, DMRT-QMS model
Subjects: F800 Physical and Terrestrial Geographical and Environmental Sciences
Department: Faculties > Engineering and Environment > Geography and Environmental Sciences
Depositing User: John Coen
Date Deposited: 24 May 2021 12:52
Last Modified: 25 Jan 2022 16:45
URI: http://nrl.northumbria.ac.uk/id/eprint/46257

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics