KIT | KIT-Bibliothek | Impressum | Datenschutz

Fusion of hyperspectral and ground penetrating radar data to estimate soil moisture

Riese, Felix M.; Keller, Sina

Abstract:
In this contribution, we investigate the potential of hyperspectral data combined with either simulated ground penetrating radar (GPR) or simulated soil-moisture (sensor-like) data to estimate soil moisture. We propose two simulation approaches to extend a given multi-sensor dataset which contains sparse GPR data. In the first approach, simulated GPR data is generated either by an interpolation along the time axis or by a machine learning model. The second approach includes the simulation of soil-moisture along the GPR profile. The soil-moisture estimation is improved significantly by the fusion of hyperspectral and GPR data. In contrast, the combination of simulated, sensor-like soil-moisture values and hyperspectral data achieves the worst regression performance. In conclusion, the estimation of soil moisture with hyperspectral and GPR data engages further investigations.



Originalveröffentlichung
DOI: 10.1109/WHISPERS.2018.8747076
Zugehörige Institution(en) am KIT Institut für Photogrammetrie und Fernerkundung (IPF)
Publikationstyp Proceedingsbeitrag
Jahr 2018
Sprache Englisch
Identifikator ISBN: 978-1-7281-1581-8
ISSN: 2158-6276
KITopen-ID: 1000082164
Erschienen in 9th Workshop on Hyperspectral Image and Signal Processing : Evolution in Remote Sensing (Whispers 2018), Amsterdam, NL, September 23-26, 2018
Veranstaltung 9th Workshop on Hyperspectral Image and Signal Processing (2018), Amsterdam, Niederlande, 23.09.2018 – 26.09.2018
Verlag IEEE
Externe Relationen Siehe auch
Schlagworte Hyperspectral data; ground penetrating radar; soil moisture; machine learning; regression; simulation
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page