Retrieval of Melt Ponds on Arctic Multiyear Sea Ice in Summer from TerraSAR-X Dual-Polarization Data Using Machine Learning Approaches: A Case Study in the Chukchi Sea with Mid-Incidence Angle Data

Abstract

Melt ponds, a common feature on Arctic sea ice, absorb most of the incoming solar radiation and have a large effect on the melting rate of sea ice, which significantly influences climate change. Therefore, it is very important to monitor melt ponds in order to better understand the sea ice-climate interaction. In this study, melt pond retrieval models were developed using the TerraSAR-X dual-polarization synthetic aperture radar (SAR) data with mid-incidence angle obtained in a summer multiyear sea ice area in the Chukchi Sea, the Western Arctic, based on two rule-based machine learning approaches-decision trees (DT) and random forest (RF)-in order to derive melt pond statistics at high spatial resolution and to identify key polarimetric parameters for melt pond detection. Melt ponds, sea ice and open water were delineated from the airborne SAR images (0.3-m resolution), which were used as a reference dataset. A total of eight polarimetric parameters (HH and VV backscattering coefficients, co-polarization ratio, co-polarization phase difference, co-polarization correlation coefficient, alpha angle, entropy and anisotropy) were derived from the TerraSAR-X dual-polarization data and then used as input variables for the machine learning models. The DT and RF models could not effectively discriminate melt ponds from open water when using only the polarimetric parameters. This is because melt ponds showed similar polarimetric signatures to open water. The average and standard deviation of the polarimetric parameters based on a 15ˆ15 pixel window were supplemented to the input variables in order to consider the difference between the spatial texture of melt ponds and open water. Both the DT and RF models using the polarimetric parameters and their texture features produced improved performance for the retrieval of melt ponds, and RF was superior to DT. The HH backscattering coefficient was identified as the variable contributing the most, and its spatial standard deviation was the next most contributing one to the classification of open water, sea ice and melt ponds in the RF model. The average of the co-polarization phase difference and the alpha angle in a mid-incidence angle were also identified as the important variables in the RF model. The melt pond fraction and sea ice concentration retrieved from the RF-derived melt pond map showed root mean square deviations of 2.4% and 4.9%, respectively, compared to those from the reference melt pond maps. This indicates that there is potential to accurately monitor melt ponds on multiyear sea ice in the summer season at a local scale using high-resolution dual-polarization SAR data.

Signature of Arctic first-year ice melt pond fraction in X-band SAR imagery

“…The lack of backscatter from the melt pond surfaces compared to the sea ice could potentially be used for f MP retrieval utilising σ 0 , as the backscatter intensity becomes weaker with increasing f MP . This is confirmed by Han et al (2016), suggesting σ 0 to be a key feature in f MP estimation for MYI in X-band during calm winds. On the other hand, our results deviate from findings in C-band, where no correlation was found between σ 0 HH and f MP at low wind speeds (U 10 = 1.5 m s −1 ) by Yackel and Barber (2000).…”

“…Han et al (2016) found H , α 1 , |ρ|, and ρ to give useful information for f MP retrieval at X-band. …”

“…Several dual-polarimetric SAR features have been suggested for f MP retrieval from SAR, utilising different expected relations to physical properties of sea ice and melt ponds (Scharien et al, 2012(Scharien et al, , 2014aFors et al, 2015;Han et al, 2016). Eight of these features are included in our study and are described in the following section.…”

“…The potential of f MP retrieval with polarimetric Xband SAR has only been explored in one single study by Han et al (2016), focusing on MYI. Hence, there is a need for more studies on the influence of f MP on polarimetric X-band SAR imagery.…”

“…The findings were partly confirmed by Fors et al (2015), who also suggest a relationship between f MP and the statistical SAR feature relative kurtosis (RK) utilising Radarsat-2 on iceberg-fast FYI and MYI in the Fram Strait. Han et al (2016) combined multiple polarimetric SAR features in f MP estimation by machine learning methods, employing the co-polarisation channels of the MYI X-band SAR scene explored in Kim et al (2013). An additional scene was also included in the study, though without melt pond information.…”