Oil Spills or Look-Alikes? Classification Rank of Surface Ocean Slick Signatures in Satellite Data
Linear discriminant analysis (LDA) is a mathematically robust multivariate data analysis approach that is sometimes used for surface oil slick signature classification. Our goal is to rank the effectiveness of LDAs to differentiate oil spills from look-alike slicks. We explored multiple combinations...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/17/3466 |
| _version_ | 1797520892061810688 |
|---|---|
| author | Gustavo de Araújo Carvalho Peter J. Minnett Nelson F. F. Ebecken Luiz Landau |
| author_facet | Gustavo de Araújo Carvalho Peter J. Minnett Nelson F. F. Ebecken Luiz Landau |
| author_sort | Gustavo de Araújo Carvalho |
| collection | DOAJ |
| description | Linear discriminant analysis (LDA) is a mathematically robust multivariate data analysis approach that is sometimes used for surface oil slick signature classification. Our goal is to rank the effectiveness of LDAs to differentiate oil spills from look-alike slicks. We explored multiple combinations of (i) variables (size information, Meteorological-Oceanographic (metoc), geo-location parameters) and (ii) data transformations (non-transformed, cube root, log<sub>10</sub>). Active and passive satellite-based measurements of RADARSAT, QuikSCAT, AVHRR, SeaWiFS, and MODIS were used. Results from two experiments are reported and discussed: (i) an investigation of 60 combinations of several attributes subjected to the same data transformation and (ii) a survey of 54 other data combinations of three selected variables subjected to different data transformations. In Experiment 1, the best discrimination was reached using ten cube-transformed attributes: ~85% overall accuracy using six pieces of size information, three metoc variables, and one geo-location parameter. In Experiment 2, two combinations of three variables tied as the most effective: ~81% of overall accuracy using area (log transformed), length-to-width ratio (log- or cube-transformed), and number of feature parts (non-transformed). After verifying the classification accuracy of 114 algorithms by comparing with expert interpretations, we concluded that applying different data transformations and accounting for metoc and geo-location attributes optimizes the accuracies of binary classifiers (oil spill vs. look-alike slicks) using the simple LDA technique. |
| first_indexed | 2024-03-10T08:04:58Z |
| format | Article |
| id | doaj.art-730434accdae4398b85a7ebd0eeb17c4 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T08:04:58Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-730434accdae4398b85a7ebd0eeb17c42023-11-22T11:09:28ZengMDPI AGRemote Sensing2072-42922021-09-011317346610.3390/rs13173466Oil Spills or Look-Alikes? Classification Rank of Surface Ocean Slick Signatures in Satellite DataGustavo de Araújo Carvalho0Peter J. Minnett1Nelson F. F. Ebecken2Luiz Landau3Laboratório 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 21941-859, RJ, BrazilDepartment of Ocean Sciences (OCE), Rosenstiel School of Marine and Atmospheric Science (RSMAS), University of Miami (UM), Miami, FL 33149, USANúcleo de Transferência de Tecnologia (NTT), 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 21941-901, RJ, BrazilLaboratório 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 21941-859, RJ, BrazilLinear discriminant analysis (LDA) is a mathematically robust multivariate data analysis approach that is sometimes used for surface oil slick signature classification. Our goal is to rank the effectiveness of LDAs to differentiate oil spills from look-alike slicks. We explored multiple combinations of (i) variables (size information, Meteorological-Oceanographic (metoc), geo-location parameters) and (ii) data transformations (non-transformed, cube root, log<sub>10</sub>). Active and passive satellite-based measurements of RADARSAT, QuikSCAT, AVHRR, SeaWiFS, and MODIS were used. Results from two experiments are reported and discussed: (i) an investigation of 60 combinations of several attributes subjected to the same data transformation and (ii) a survey of 54 other data combinations of three selected variables subjected to different data transformations. In Experiment 1, the best discrimination was reached using ten cube-transformed attributes: ~85% overall accuracy using six pieces of size information, three metoc variables, and one geo-location parameter. In Experiment 2, two combinations of three variables tied as the most effective: ~81% of overall accuracy using area (log transformed), length-to-width ratio (log- or cube-transformed), and number of feature parts (non-transformed). After verifying the classification accuracy of 114 algorithms by comparing with expert interpretations, we concluded that applying different data transformations and accounting for metoc and geo-location attributes optimizes the accuracies of binary classifiers (oil spill vs. look-alike slicks) using the simple LDA technique.https://www.mdpi.com/2072-4292/13/17/3466remote sensingsynthetic aperture radar (SAR)microwave sensorsoptical sensorsimage processinglinear discriminant analysis (LDA) |
| spellingShingle | Gustavo de Araújo Carvalho Peter J. Minnett Nelson F. F. Ebecken Luiz Landau Oil Spills or Look-Alikes? Classification Rank of Surface Ocean Slick Signatures in Satellite Data Remote Sensing remote sensing synthetic aperture radar (SAR) microwave sensors optical sensors image processing linear discriminant analysis (LDA) |
| title | Oil Spills or Look-Alikes? Classification Rank of Surface Ocean Slick Signatures in Satellite Data |
| title_full | Oil Spills or Look-Alikes? Classification Rank of Surface Ocean Slick Signatures in Satellite Data |
| title_fullStr | Oil Spills or Look-Alikes? Classification Rank of Surface Ocean Slick Signatures in Satellite Data |
| title_full_unstemmed | Oil Spills or Look-Alikes? Classification Rank of Surface Ocean Slick Signatures in Satellite Data |
| title_short | Oil Spills or Look-Alikes? Classification Rank of Surface Ocean Slick Signatures in Satellite Data |
| title_sort | oil spills or look alikes classification rank of surface ocean slick signatures in satellite data |
| topic | remote sensing synthetic aperture radar (SAR) microwave sensors optical sensors image processing linear discriminant analysis (LDA) |
| url | https://www.mdpi.com/2072-4292/13/17/3466 |
| work_keys_str_mv | AT gustavodearaujocarvalho oilspillsorlookalikesclassificationrankofsurfaceoceanslicksignaturesinsatellitedata AT peterjminnett oilspillsorlookalikesclassificationrankofsurfaceoceanslicksignaturesinsatellitedata AT nelsonffebecken oilspillsorlookalikesclassificationrankofsurfaceoceanslicksignaturesinsatellitedata AT luizlandau oilspillsorlookalikesclassificationrankofsurfaceoceanslicksignaturesinsatellitedata |