Improved Classification Models to Distinguish Natural from Anthropic Oil Slicks in the Gulf of Mexico: Seasonality and Radarsat-2 Beam Mode Effects under a Machine Learning Approach

Distinguishing between natural and anthropic oil slicks is a challenging task, especially in the Gulf of Mexico, where these events can be simultaneously observed and recognized as seeps or spills. In this study, a powerful data analysis provided by machine learning (ML) methods was employed to deve...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Ítalo de Oliveira Matias, Patrícia Carneiro Genovez, Sarah Barrón Torres, Francisco Fábio de Araújo Ponte, Anderson José Silva de Oliveira, Fernando Pellon de Miranda, Gil Márcio Avellino
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Q
Acceso en línea:https://doaj.org/article/10e960cf8b374cba9e7883325556fc1d
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:10e960cf8b374cba9e7883325556fc1d
record_format dspace
spelling oai:doaj.org-article:10e960cf8b374cba9e7883325556fc1d2021-11-25T18:54:25ZImproved Classification Models to Distinguish Natural from Anthropic Oil Slicks in the Gulf of Mexico: Seasonality and Radarsat-2 Beam Mode Effects under a Machine Learning Approach10.3390/rs132245682072-4292https://doaj.org/article/10e960cf8b374cba9e7883325556fc1d2021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/22/4568https://doaj.org/toc/2072-4292Distinguishing between natural and anthropic oil slicks is a challenging task, especially in the Gulf of Mexico, where these events can be simultaneously observed and recognized as seeps or spills. In this study, a powerful data analysis provided by machine learning (ML) methods was employed to develop, test, and implement a classification model (CM) to distinguish an oil slick source (OSS) as natural or anthropic. A robust database containing 4916 validated oil samples, detected using synthetic aperture radar (SAR), was employed for this task. Six ML algorithms were evaluated, including artificial neural networks (ANN), random forest (RF), decision trees (DT), naive Bayes (NB), linear discriminant analysis (LDA), and logistic regression (LR). Using RF, the global CM achieved a maximum accuracy value of 73.15. An innovative approach evaluated how external factors, such as seasonality, satellite configurations, and the synergy between them, limit or improve OSS predictions. To accomplish this, specific classification models (SCMs) were derived from the global ones (CMs), tuning the best algorithms and parameters according to different scenarios. Median accuracies revealed winter and spring to be the best seasons and ScanSAR Narrow B (SCNB) as the best beam mode. The maximum median accuracy to distinguish seeps from spills was achieved in winter using SCNB (83.05). Among the tested algorithms, RF was the most robust, with a better performance in 81% of the investigated scenarios. The accuracy increment provided by the well-fitted models may minimize the confusion between seeps and spills. This represents a concrete contribution to reducing economic and geologic risks derived from exploration activities in offshore areas. Additionally, from an operational standpoint, specific models support specialists to select the best SAR products and seasons for new acquisitions, as well as to optimize performances according to the available data.Ítalo de Oliveira MatiasPatrícia Carneiro GenovezSarah Barrón TorresFrancisco Fábio de Araújo PonteAnderson José Silva de OliveiraFernando Pellon de MirandaGil Márcio AvellinoMDPI AGarticlesynthetic aperture radar (SAR)machine learning (ML)exploratory data analysis (EDA)classification model (CM)oil slicks source (OSS)oil seepsScienceQENRemote Sensing, Vol 13, Iss 4568, p 4568 (2021)
institution DOAJ
collection DOAJ
language EN
topic synthetic aperture radar (SAR)
machine learning (ML)
exploratory data analysis (EDA)
classification model (CM)
oil slicks source (OSS)
oil seeps
Science
Q
spellingShingle synthetic aperture radar (SAR)
machine learning (ML)
exploratory data analysis (EDA)
classification model (CM)
oil slicks source (OSS)
oil seeps
Science
Q
Ítalo de Oliveira Matias
Patrícia Carneiro Genovez
Sarah Barrón Torres
Francisco Fábio de Araújo Ponte
Anderson José Silva de Oliveira
Fernando Pellon de Miranda
Gil Márcio Avellino
Improved Classification Models to Distinguish Natural from Anthropic Oil Slicks in the Gulf of Mexico: Seasonality and Radarsat-2 Beam Mode Effects under a Machine Learning Approach
description Distinguishing between natural and anthropic oil slicks is a challenging task, especially in the Gulf of Mexico, where these events can be simultaneously observed and recognized as seeps or spills. In this study, a powerful data analysis provided by machine learning (ML) methods was employed to develop, test, and implement a classification model (CM) to distinguish an oil slick source (OSS) as natural or anthropic. A robust database containing 4916 validated oil samples, detected using synthetic aperture radar (SAR), was employed for this task. Six ML algorithms were evaluated, including artificial neural networks (ANN), random forest (RF), decision trees (DT), naive Bayes (NB), linear discriminant analysis (LDA), and logistic regression (LR). Using RF, the global CM achieved a maximum accuracy value of 73.15. An innovative approach evaluated how external factors, such as seasonality, satellite configurations, and the synergy between them, limit or improve OSS predictions. To accomplish this, specific classification models (SCMs) were derived from the global ones (CMs), tuning the best algorithms and parameters according to different scenarios. Median accuracies revealed winter and spring to be the best seasons and ScanSAR Narrow B (SCNB) as the best beam mode. The maximum median accuracy to distinguish seeps from spills was achieved in winter using SCNB (83.05). Among the tested algorithms, RF was the most robust, with a better performance in 81% of the investigated scenarios. The accuracy increment provided by the well-fitted models may minimize the confusion between seeps and spills. This represents a concrete contribution to reducing economic and geologic risks derived from exploration activities in offshore areas. Additionally, from an operational standpoint, specific models support specialists to select the best SAR products and seasons for new acquisitions, as well as to optimize performances according to the available data.
format article
author Ítalo de Oliveira Matias
Patrícia Carneiro Genovez
Sarah Barrón Torres
Francisco Fábio de Araújo Ponte
Anderson José Silva de Oliveira
Fernando Pellon de Miranda
Gil Márcio Avellino
author_facet Ítalo de Oliveira Matias
Patrícia Carneiro Genovez
Sarah Barrón Torres
Francisco Fábio de Araújo Ponte
Anderson José Silva de Oliveira
Fernando Pellon de Miranda
Gil Márcio Avellino
author_sort Ítalo de Oliveira Matias
title Improved Classification Models to Distinguish Natural from Anthropic Oil Slicks in the Gulf of Mexico: Seasonality and Radarsat-2 Beam Mode Effects under a Machine Learning Approach
title_short Improved Classification Models to Distinguish Natural from Anthropic Oil Slicks in the Gulf of Mexico: Seasonality and Radarsat-2 Beam Mode Effects under a Machine Learning Approach
title_full Improved Classification Models to Distinguish Natural from Anthropic Oil Slicks in the Gulf of Mexico: Seasonality and Radarsat-2 Beam Mode Effects under a Machine Learning Approach
title_fullStr Improved Classification Models to Distinguish Natural from Anthropic Oil Slicks in the Gulf of Mexico: Seasonality and Radarsat-2 Beam Mode Effects under a Machine Learning Approach
title_full_unstemmed Improved Classification Models to Distinguish Natural from Anthropic Oil Slicks in the Gulf of Mexico: Seasonality and Radarsat-2 Beam Mode Effects under a Machine Learning Approach
title_sort improved classification models to distinguish natural from anthropic oil slicks in the gulf of mexico: seasonality and radarsat-2 beam mode effects under a machine learning approach
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/10e960cf8b374cba9e7883325556fc1d
work_keys_str_mv AT italodeoliveiramatias improvedclassificationmodelstodistinguishnaturalfromanthropicoilslicksinthegulfofmexicoseasonalityandradarsat2beammodeeffectsunderamachinelearningapproach
AT patriciacarneirogenovez improvedclassificationmodelstodistinguishnaturalfromanthropicoilslicksinthegulfofmexicoseasonalityandradarsat2beammodeeffectsunderamachinelearningapproach
AT sarahbarrontorres improvedclassificationmodelstodistinguishnaturalfromanthropicoilslicksinthegulfofmexicoseasonalityandradarsat2beammodeeffectsunderamachinelearningapproach
AT franciscofabiodearaujoponte improvedclassificationmodelstodistinguishnaturalfromanthropicoilslicksinthegulfofmexicoseasonalityandradarsat2beammodeeffectsunderamachinelearningapproach
AT andersonjosesilvadeoliveira improvedclassificationmodelstodistinguishnaturalfromanthropicoilslicksinthegulfofmexicoseasonalityandradarsat2beammodeeffectsunderamachinelearningapproach
AT fernandopellondemiranda improvedclassificationmodelstodistinguishnaturalfromanthropicoilslicksinthegulfofmexicoseasonalityandradarsat2beammodeeffectsunderamachinelearningapproach
AT gilmarcioavellino improvedclassificationmodelstodistinguishnaturalfromanthropicoilslicksinthegulfofmexicoseasonalityandradarsat2beammodeeffectsunderamachinelearningapproach
_version_ 1718410571183816704