TY - JOUR
T1 - Oil-slick category discrimination (seeps vs. spills)
T2 - A linear discriminant analysis using RADARSAT-2 backscatter coefficients (σ°, β°, and γ°) in Campeche Bay (Gulf of Mexico)
AU - Carvalho, Gustavo de Araújo
AU - Minnett, Peter J.
AU - Paes, Eduardo T.
AU - de Miranda, Fernando P.
AU - Landau, Luiz
N1 - Funding Information:
We thank Roberta Santana for the helpful discussions, L?via Diniz and Lucas Medeiros for text edit assistance, LabSAR/LAMCE/PEC/COPPE/UFRJ colleagues, staff, and employees for their support, as well as Pemex and MDA Geospatial Services for the RADARSAT-2 dataset. We also express our gratitude to the four anonymous reviewers for their enlightening comments and to the unidentified academic editor for his clever observations, both of which have contributed to improving this paper. This research is supported by the Programa Nacional de P?s Doutorado (PNPD) of Coordena??o de Aperfei?oamento de Pessoal de N?vel Superior (CAPES), Brazil.
PY - 2019
Y1 - 2019
N2 - 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°, and γ°), SAR calibrated products (received radar beam given in amplitude or decibel, with or without a despeckle filter), and data transformations (none, cube root, log10). 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.
AB - 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°, and γ°), SAR calibrated products (received radar beam given in amplitude or decibel, with or without a despeckle filter), and data transformations (none, cube root, log10). 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.
KW - Campeche Bay (Gulf of Mexico)
KW - Linear discriminant analysis (LDA)
KW - Ocean remote sensing
KW - Oil seeps
KW - Oil slicks
KW - Oil spills
KW - Physical oceanography
KW - RADARSAT
KW - Satellite image classification and segmentation
KW - Synthetic aperture radar (SAR)
UR - http://www.scopus.com/inward/record.url?scp=85071524698&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85071524698&partnerID=8YFLogxK
U2 - 10.3390/rs11141652
DO - 10.3390/rs11141652
M3 - Article
AN - SCOPUS:85071524698
VL - 11
JO - Remote Sensing
JF - Remote Sensing
SN - 2072-4292
IS - 14
M1 - 1652
ER -