Item: Improved snow parameters estimation through integration of simulated and remotely sensed snow cover information
-
-
Title: Improved snow parameters estimation through integration of simulated and remotely sensed snow cover information
Proceedings: International Snow Science Workshop Proceedings 2018, Innsbruck, Austria
Authors:
- Ludovica De Gregorio [ EURAC Research, European Academy of Bozen/Bolzano, Institute for Earth Observation, viale Druso, 1-39100 Bolzano, Italy ] [ University of Trento, Dept. of Information Engineering and Computer Science, Via Sommarive, 9, I-38123 Trento, Italy ]
- Mattia Callegari [ EURAC Research, European Academy of Bozen/Bolzano, Institute for Earth Observation, viale Druso, 1-39100 Bolzano, Italy ]
- Carlo Marin [ EURAC Research, European Academy of Bozen/Bolzano, Institute for Earth Observation, viale Druso, 1-39100 Bolzano, Italy ]
- Marc Zebisch [ EURAC Research, European Academy of Bozen/Bolzano, Institute for Earth Observation, viale Druso, 1-39100 Bolzano, Italy ]
- Lorenzo Bruzzone [ University of Trento, Dept. of Information Engineering and Computer Science, Via Sommarive, 9, I-38123 Trento, Italy ]
- Begum Demir [ University of Trento, Dept. of Information Engineering and Computer Science, Via Sommarive, 9, I-38123 Trento, Italy ]
- Ulrich Strasser [ University of Innsbruck, Institute of Geography, Innrain 52f, 6020 Innsbruck, Austria ]
- Thomas Marke [ University of Innsbruck, Institute of Geography, Innrain 52f, 6020 Innsbruck, Austria ]
- Daniel Günther [ University of Innsbruck, Institute of Geography, Innrain 52f, 6020 Innsbruck, Austria ]
- Rudi Nadalet [ Autonomous Province of Bolzano, Agency for Civil Protection - Hydrographic Office, viale Druso 116, 39100 Bolzano, Italy ]
- Claudia Notarnicola [ EURAC Research, European Academy of Bozen/Bolzano, Institute for Earth Observation, viale Druso, 1-39100 Bolzano, Italy ]
Date: 2018-10-07
Abstract: The main idea of this work is the development of an innovative data fusion approach through which state-of-the-art remotely sensed products and hydrological modelling simulations can be integrated in order to improve the retrieval and the reliability of the snow cover mapping in the Euregio area. The fusion approach, based on a machine learning technique and, specifically, on Support Vector Machine (SVM), involves snow cover maps derived from remote sensing and from hydrological model simulation together with their uncertainty layers. The results obtained are promising and the agreement with ground data is in average of 96%.
Language of Article: English
Presenters:
Keywords: Data fusion, snow cover mapping, machine learning, remote sensing, hydrological model.
Page Number(s): 318-322
-
Digital Abstract Not Available
-