Surface circulation in the Nordic Seas from clustered drifters

We compare two methods for estimating mean velocities and diffusivities from surface drifter observations, using data from the Nordic Seas. The first is the conventional method of grouping data into geographical bins. The second relies on a "clustering" algorithm, and groups velocity observations according to nearest-neighbor distance. Capturing the spatial variability of the mean velocity requires using bins with a length scale of similar to 50 km. However, because many bins have few observations, the statistical significance varies substantially between bins. Clustering yields sets with approximately the same number of observations, so the significance is more uniform. At the densely sampled Svinoy section, clusters can be used to construct the mean flow field with <= 10 km resolution. Clustering also excels at the estimation of eddy diffusivities, allowing resolution at the 20 km scale in the densely sampled regions. Taking bathymetry into account in the clustering process further improves mean estimates where the data is sparse. Clustering the available surface drifter data, extended by recent deployments from the POLEWARD project, reveals new features in the surface circulation. These are a large anticyclonic vortex in the center of the Lofoten Basin and two anticyclonic recirculations at the Svinoy section. Clustering also yields maps of the eddy diffusivities at unprecedented resolution. Diffusivities are suppressed at the core of the Norwegian Atlantic Current, while they are elevated in the Lofoten Basin and along the Polar Front. (C) 2011 Elsevier Ltd. All rights reserved.