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

Emanuele Santi, M. Brogioni, M. Leduc-Leballeur, G. Macelloni, F. Montomoli, P. Pampaloni, Juha Lemmetyinen, J. Cohen, H. Rott, Thomas Nagler, Chris Derksen, Josh King, Nick Rutter, Richard Essery, C. Menard, Mel Sandells, M. Kern

Research output: Contribution to journalArticlepeer-review

4 Downloads (Pure)

Abstract

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 multi- frequency Synthetic Aperture Radar (SAR)
data to retrieve snow information. This paper 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 band 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 (ANN). ANN 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 extending the algorithm exportability to other test sites.
Original languageEnglish
Number of pages16
JournalIEEE Transactions on Geoscience and Remote Sensing
Publication statusAccepted/In press - 19 May 2021

Fingerprint Dive into the research topics of 'Exploiting the ANN potential in estimating Snow Depth and Snow Water Equivalent from the airborne SnowSAR data at X and Ku bands'. Together they form a unique fingerprint.

Cite this