Beach cusps: Using multivariate data analysis techniques for the identification of important variables and for predicting their spacing

• Type: Article in International Scientific Journal
• Date: 2011

Authors

Lopes, V (Author) Other; Pais Barbosa, J (Author) FEUP; Taveira Pinto, F (Author) FEUP; Veloso Gomes, F (Author) FEUP

Journal

Title: Journal of Coastal Research

No. SI 39

Pages: 1106-1110

ISSN: 0749-0208

Publisher: Coastal Education & Research Foundation, Inc.

Indexing

ISI Web of Knowledge - 7 Citations

ISI Web of Science

Scopus - 7 Citations

Scientific classification

FOS: Natural sciences > Earth and related Environmental sciences

Other information

Authenticus ID: P-002-WEA

Abstract (EN): A beach cusp is defined as a cuspate feature which usually occurs in groups along the foreshore as a series of alternating horns (pointing seaward) and embayments. No formulation has yet been capable of providing accurate estimates of beach cusp spacing (distance between two consecutive horns) and no theory has been able to explain their formation. In this work, we try to identify important variables in the process of cusp formation and to develop a statistical tool capable of predicting beach cusp spacing. Three multivariate data analysis techniques, Multiple Linear Regression (MLR), Principal Component Analysis (PCA) and Principal Component Regression (PCR) were used to try to achieve this objective. Multiple linear regression attempts to model the relationship between two or more explanatory variables and a response variable by fitting a linear equation to observed data. Principal component analysis (PCA) involves a mathematical procedure that transforms a number of possibly correlated variables into a number of uncorrelated variables called principal components, related to the original variables by an orthogonal transformation. Principal component regression is a method that combines MLR with PCA. Two regression equations were derived. MLR equation explains almost 80% of the variance in cusp spacing, and there is no strong evidence that this model has multicollinearity problems. Standardized PCR equation explains 83,4% of the variance. Wave breaking height is, for the dataset used in this work, the most important variable. Variables other than those included in this work should also be important in determining beach cusp spacing.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 5