GEOSCAN Search Results: Fastlink


TitleIntegrating intensity and context for improved supervised river ice classification from dual-pol Sentinel-1 SAR data
Authorde Roda Husman, SORCID logo; van der Sanden, JORCID logo; Lehrmitte, SORCID logo; Eleveld, MORCID logo
SourceInternational Journal of Applied Earth Observation and Geoinformation vol. 101, 102359, 2021 p. 1-10, Open Access logo Open Access
Alt SeriesNatural Resources Canada, Contribution Series 20210598
Mediapaper; on-line; digital
File formatpdf
NTS74D/04; 74D/05; 74D/12; 74D/13; 84A/01; 84A/02; 84A/07; 84A/08; 84A/09; 84A/10; 84A/15; 84A/16
Lat/Long WENS-113.0000 -111.5000 57.0000 56.0000
Subjectsenvironmental geology; Nature and Environment; rivers; ice; SARS; ice conditions; synthetic aperture radar surveys (SAR); Forests
Illustrationslocation maps; tables; flow charts; cross-plots; plots; photographs; figures
Released2021 05 12
AbstractRiver ice is a major contributor to flood risk in cold regions due to the physical impediment of flow caused by ice jamming. Although a variety of classifiers have been developed to distinguish ice types using HH or VV intensity of SAR data, mostly based on data from RADARSAT-1 and -2, these classifiers still experience problems with breakup classification, because meltwater development causes overlap in co-polarization backscatter intensities of open water and sheet ice pixels. In this study, we develop a Random Forest classifier based on multiple features of Sentinel-1 data for three main classes generally present during breakup: rubble ice, sheet ice and open water, in a case study over the Athabasca River in Canada. For each ice stage, intensity of the VV and VH backscatter, pseudo-polarimetric decomposition parameters and Grey Level Co-occurrence Matrix texture features were computed for 70 verified sample areas. Several classifiers were developed, based on i) solely intensity features or on ii) a combination of intensity, pseudo-polarimetric and texture features and each classifier was evaluated based on Recursive Feature Elimination with Cross-Validation and pair-wise correlation of the studied features. Results show improved classifier performance when including GLCM mean of VV intensity, and VH intensity features instead of the conventional classifier based solely on intensity. This highlights the complementary nature of texture and intensity for the classification of breaking river ice. GLCM mean incorporates spatial patterns of the co-polarized intensity and sensitivity to context, while VH intensity introduces cross-polarized surface and volume scattering signals and is less sensitive to wind than the commonly used co-polarized intensity. We conclude that the proposed method based on the combination of texture and intensity features is suitable for and performs well in physically complex situations such as breakup, which are hard to classify otherwise. This method has a high potential for classifying river ice operationally, also for data from other SAR missions. Since it is a generic approach, it also has potential to classify river ice along other rivers globally.
Summary(Plain Language Summary, not published)
One third of flood emergencies in Canada result from the development of ice jams in breaking rivers. Better information about the evolution of breakup processes can help to safeguard Canadians from ice-jam-flood-emergencies. Radar satellite systems make excellent tools to characterize river ice conditions as a function of time for emergency management purposes. Within Canada, including at NRCan, the operational use of radar remote sensing in support of the monitoring of river ice breakup processes is growing. More frequent imaging facilitates more detailed monitoring. This paper reports on a study that aimed to assess and develop the utility of Europe's Sentinel-1 mission. Sentinel-1 complements Canada's RADARSAT Constellation Mission; together these missions offer more imaging opportunities. An MSc student from Delft University of Technology performed the study under supervision of Dr. van der Sanden from NRCan/CCMEO/CCRS. The Athabasca River at Fort McMurray was selected as the study area. A machine-learning technique was used to develop an algorithm to classify river areas imaged by Sentinel-1 into water, sheet ice, and rubble ice - the ice type comprised in ice jams. This algorithm exploits information contained in backscatter intensity and texture, i.e. the local variability in image grey-tone.

Date modified: