jcbw / arctic_lead_detection

Classifies leads and other sea ice features

Lead detection with Sentinel-1 in the Beaufort Gyre using Google Earth Engine

Jullian C. B. Williams, Stephen F. Ackley, Alberto M. Mestas-Nuñez, Grant J. MacDonald

NASA Center for Advanced Measurements in Extreme Environments (CAMEE)
The University of Texas at San Antonio, 1 UTSA Circle, San Antonio, Texas 78249

Abstract

Sea ice leads are produced from deformational forces, which break apart the ice surface and expose open water areas. Open water leads are the highest regulators of heat in the Arctic during Polar night-time, producing low level cloud layers from vertical heat exchange in the atmosphere. Partially frozen and re-frozen lead areas produce smaller heat exchanges with the absence of a warm water surface. Identifying past and present ice types through machine learning techniques is useful in change detection and climate change studies. This paper uses Sentinel-1 Synthetic Aperture RADAR (SAR) data with a support vector machine classifier to identify leads of open water and thin ice types across the Beaufort Gyre.

Code is adapted from supplimentary documents in:

• Hird, J., DeLancey, E., McDermid, G., & Kariyeva, J. (2017). Google Earth engine, open-access satellite data, and machine learning in support of large-area probabilistic wetland mapping. Remote Sensing, 9(12), 1315. doi:10.3390/rs9121315

Google Earth Engine can be accessed from here.