# Oil-Slick Category Discrimination (Seeps vs. Spills): A Linear Discriminant Analysis Using RADARSAT-2 Backscatter Coefficients (σ°, β°, and γ°) in Campeche Bay (Gulf of Mexico)

^{1}

Laboratório de Sensoriamento Remoto por Radar Aplicado à Indústria do Petróleo (LabSAR), Laboratório de Métodos Computacionais em Engenharia (LAMCE), Programa de Engenharia Civil (PEC), Instituto Alberto Luiz Coimbra de Pós-Graduação e Pesquisa de Engenharia (COPPE), Universidade Federal do Rio de Janeiro (UFRJ), Rio de Janeiro 21941-909, RJ, Brazil

^{2}

Department of Ocean Sciences (OCE), Rosenstiel School of Marine and Atmospheric Science (RSMAS), University of Miami (UM), Miami, FL 33145, USA

^{3}

Laboratório de Ecologia Marinha e Oceanografia Pesqueira da Amazônia (LEMOPA), Instituto Socioambiental e dos Recursos Hídricos (ISARH), Universidade Federal Rural da Amazônia (UFRA), Belém 66077-830, PA, Brazil

^{4}

Centro de Pesquisas Leopoldo Américo Miguez de Mello (CENPES), Petróleo Brasileiro S.A. (Petrobras), Rio de Janeiro 21941-915, RJ, Brazil

^{*}

Author to whom correspondence should be addressed.

Received: 10 May 2019 / Revised: 13 June 2019 / Accepted: 24 June 2019 / Published: 11 July 2019

(This article belongs to the Special Issue Oil Spill Remote Sensing)

A novel empirical approach to categorize oil slicks’ sea surface expressions in synthetic aperture radar (SAR) measurements into oil seeps or oil spills is investigated, contributing both to academic remote sensing research and to practical applications for the petroleum industry. We use linear discriminant analysis (LDA) to try accuracy improvements from our previously published methods of discriminating seeps from spills that achieved ~70% of overall accuracy. Analyzing 244 RADARSAT-2 scenes containing 4562 slicks observed in Campeche Bay (Gulf of Mexico), our exploratory data analysis evaluates the impact of 61 combinations of SAR backscatter coefficients (σ°, β°, γ°), SAR calibrated products (received radar beam given in amplitude or decibel, with or without a despeckle filter), and data transformations (none, cube root, log

_{10}). The LDA ability to discriminate the oil-slick category is rather independent of backscatter coefficients and calibrated products, but influenced by data transformations. The combination of attributes plays a role in the discrimination; combining oil-slicks’ size and SAR information is more effective. We have simplified our analyses using fewer attributes to reach accuracies comparable to those of our earlier studies, and we suggest using other multivariate data analyses—cubist or random forest—to attempt to further improve oil-slick category discrimination.