TY - JOUR

T1 - Improving tropospheric corrections on large-scale Sentinel-1 interferograms using a machine learning approach for integration with GNSS-derived zenith total delay (ZTD)

AU - Shamshiri, Roghayeh

AU - Motagh, Mahdi

AU - Nahavandchi, Hossein

AU - Haghshenas Haghighi, Mahmud

AU - Hoseini, Mostafa

N1 - Funding information: This work was supported by the Norwegian University of Science and Technology (NTNU). The Copernicus Sentinel data were provided by ESA. ERA-Interim data was provided by European Centre for Medium-Range Weather Forecasts (ECMWF). Some of the figures were generated using Generic Mapping Tools ( Wessel et al., 2013 ). The digital elevation model was provided by the Norwegian Mapping Authority (NMA). We would like to thank Halfdan Pascal Kierulf from the NMA for preparing the displacement time-series at the global navigation satellite systems (GNSS) stations, Knut Stanley Jacobsen from the NMA for preparing total electron content values, and Leo Olsen from NMA for providing GNSS observations. We acknowledge constructive reviews by Romain Jolivet and two anonymous reviewers, whose comments greatly improved the quality of the original manuscript. This work was supported by the Norwegian University of Science and Technology (NTNU). The Copernicus Sentinel data were provided by ESA. ERA-Interim data was provided by European Centre for Medium-Range Weather Forecasts (ECMWF). Some of the figures were generated using Generic Mapping Tools (Wessel et al. 2013). The digital elevation model was provided by the Norwegian Mapping Authority (NMA). We would like to thank Halfdan Pascal Kierulf from the NMA for preparing the displacement time-series at the global navigation satellite systems (GNSS) stations, Knut Stanley Jacobsen from the NMA for preparing total electron content values, and Leo Olsen from NMA for providing GNSS observations. We acknowledge constructive reviews by Romain Jolivet and two anonymous reviewers, whose comments greatly improved the quality of the original manuscript.

PY - 2020/3/15

Y1 - 2020/3/15

N2 - Sentinel-1 mission with its wide spatial coverage (250 km), short revisit time (6 days), and rapid data dissemination opened new perspectives for large-scale interferometric synthetic aperture radar (InSAR) analysis. However, the spatiotemporal changes in troposphere limits the accuracy of InSAR measurements for operational deformation monitoring at a wide scale. Due to the coarse node spacing of the tropospheric models, like ERA-Interim and other external data like Global Navigation Satellite System (GNSS), the interpolation techniques are not able to well replicate the localized and turbulent tropospheric effects. In this study, we propose a new technique based on machine learning (ML) Gaussian processes (GP) regression approach using the combination of small-baseline interferograms and GNSS derived zenith total delay (ZTD) values to mitigate phase delay caused by troposphere in interferometric observations. By applying the ML technique over 12 Sentinel-1 images acquired between May–October 2016 along a track over Norway, the root mean square error (RMSE) reduces on average by 83% compared to 50% reduction obtained by using ERA-Interim model.

AB - Sentinel-1 mission with its wide spatial coverage (250 km), short revisit time (6 days), and rapid data dissemination opened new perspectives for large-scale interferometric synthetic aperture radar (InSAR) analysis. However, the spatiotemporal changes in troposphere limits the accuracy of InSAR measurements for operational deformation monitoring at a wide scale. Due to the coarse node spacing of the tropospheric models, like ERA-Interim and other external data like Global Navigation Satellite System (GNSS), the interpolation techniques are not able to well replicate the localized and turbulent tropospheric effects. In this study, we propose a new technique based on machine learning (ML) Gaussian processes (GP) regression approach using the combination of small-baseline interferograms and GNSS derived zenith total delay (ZTD) values to mitigate phase delay caused by troposphere in interferometric observations. By applying the ML technique over 12 Sentinel-1 images acquired between May–October 2016 along a track over Norway, the root mean square error (RMSE) reduces on average by 83% compared to 50% reduction obtained by using ERA-Interim model.

KW - Gaussian processes (GP) regression

KW - Global navigation satellite system (GNSS)

KW - Large-scale

KW - Machine learning (ML)

KW - Sentinel-1

KW - Synthetic aperture radar (SAR)

KW - Troposphere

KW - Zenith total delay (ZTD)

UR - http://www.scopus.com/inward/record.url?scp=85078758996&partnerID=8YFLogxK

U2 - 10.1016/j.rse.2019.111608

DO - 10.1016/j.rse.2019.111608

M3 - Article

AN - SCOPUS:85078758996

VL - 239

JO - Remote Sensing of Environment

JF - Remote Sensing of Environment

SN - 0034-4257

M1 - 111608

ER -