Machine learning for the detection of oil spills in satellite radar images

Miroslav Kubat, Robert C. Holte, Stan Matwin

Research output: Contribution to journalArticle

741 Citations (Scopus)

Abstract

During a project examining the use of machine learning techniques for oil spill detection, we encountered several essential questions that we believe deserve the attention of the research community. We use our particular case study to illustrate such issues as problem formulation, selection of evaluation measures, and data preparation. We relate these issues to properties of the oil spill application, such as its imbalanced class distribution, that are shown to be common to many applications. Our solutions to these issues are implemented in the Canadian Environmental Hazards Detection System (CEHDS), which is about to undergo field testing.

Original languageEnglish
Pages (from-to)195-215
Number of pages21
JournalMachine Learning
Volume30
Issue number2-3
StatePublished - Dec 1 1998
Externally publishedYes

Fingerprint

Oil spills
Learning systems
Radar
Satellites
Hazards
Testing

Keywords

  • Classification
  • Inductive learning
  • Methodology
  • Radar images

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Systems Engineering

Cite this

Machine learning for the detection of oil spills in satellite radar images. / Kubat, Miroslav; Holte, Robert C.; Matwin, Stan.

In: Machine Learning, Vol. 30, No. 2-3, 01.12.1998, p. 195-215.

Research output: Contribution to journalArticle

Kubat, M, Holte, RC & Matwin, S 1998, 'Machine learning for the detection of oil spills in satellite radar images', Machine Learning, vol. 30, no. 2-3, pp. 195-215.
Kubat, Miroslav ; Holte, Robert C. ; Matwin, Stan. / Machine learning for the detection of oil spills in satellite radar images. In: Machine Learning. 1998 ; Vol. 30, No. 2-3. pp. 195-215.
@article{86eef068a4f54564a968d2d4399e2117,
title = "Machine learning for the detection of oil spills in satellite radar images",
abstract = "During a project examining the use of machine learning techniques for oil spill detection, we encountered several essential questions that we believe deserve the attention of the research community. We use our particular case study to illustrate such issues as problem formulation, selection of evaluation measures, and data preparation. We relate these issues to properties of the oil spill application, such as its imbalanced class distribution, that are shown to be common to many applications. Our solutions to these issues are implemented in the Canadian Environmental Hazards Detection System (CEHDS), which is about to undergo field testing.",
keywords = "Classification, Inductive learning, Methodology, Radar images",
author = "Miroslav Kubat and Holte, {Robert C.} and Stan Matwin",
year = "1998",
month = "12",
day = "1",
language = "English",
volume = "30",
pages = "195--215",
journal = "Machine Learning",
issn = "0885-6125",
publisher = "Springer Netherlands",
number = "2-3",

}

TY - JOUR

T1 - Machine learning for the detection of oil spills in satellite radar images

AU - Kubat, Miroslav

AU - Holte, Robert C.

AU - Matwin, Stan

PY - 1998/12/1

Y1 - 1998/12/1

N2 - During a project examining the use of machine learning techniques for oil spill detection, we encountered several essential questions that we believe deserve the attention of the research community. We use our particular case study to illustrate such issues as problem formulation, selection of evaluation measures, and data preparation. We relate these issues to properties of the oil spill application, such as its imbalanced class distribution, that are shown to be common to many applications. Our solutions to these issues are implemented in the Canadian Environmental Hazards Detection System (CEHDS), which is about to undergo field testing.

AB - During a project examining the use of machine learning techniques for oil spill detection, we encountered several essential questions that we believe deserve the attention of the research community. We use our particular case study to illustrate such issues as problem formulation, selection of evaluation measures, and data preparation. We relate these issues to properties of the oil spill application, such as its imbalanced class distribution, that are shown to be common to many applications. Our solutions to these issues are implemented in the Canadian Environmental Hazards Detection System (CEHDS), which is about to undergo field testing.

KW - Classification

KW - Inductive learning

KW - Methodology

KW - Radar images

UR - http://www.scopus.com/inward/record.url?scp=0031998121&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031998121&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0031998121

VL - 30

SP - 195

EP - 215

JO - Machine Learning

JF - Machine Learning

SN - 0885-6125

IS - 2-3

ER -