Piece‐wise constant cluster modelling of dynamics of upwelling patterns

Nascimento, Susana; Martins, Alexandre; Relvas, Paulo; Luis, Joaquim; Mirkin, Boris

http://hdl.handle.net/10400.1/20129

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
Piece-wise constant cluster modelling of dynamics.pdf		5.33 MB	Adobe PDF	Download

Send Feedback

Authors

Abstract(s)

A comprehensive approach is presented to analyse season's coastal upwelling represented by weekly sea surface temperature (SST) image grids. Our three-stage data recovery clustering method assumes that the season's upwelling can be divided into shorter periods of stability, ranges, each to be represented by a constant core and variable shell parts. Corresponding clustering algorithms parameters are automatically derived by using the least-squares clustering criterion. The approach has been successfully applied to real-world SST data covering two distinct regions: Portuguese coast and Morocco coast, for 16 years each.