Supervised pattern recognition methods had scarcely been applied to assess the origin of hydrocarbons lumps arrived at the coastline. In this work eight supervised multivariate methods based on quite different principles (Discriminant Analysis, Principal Components Analysis combined to Discriminant Analysis, Soft Independent Modelling of Class Analogy, K-Nearest Neighbours, Partial Least Squares Discriminant Analysis –PLS-DA-, kernel-PLS (radial basis functions-PLS), Counterpropagation Artificial Neural Networks –CP-ANN- and Support Vector Machines with linear, radial basis function and polynomial kernels) and a ‘consensus’ approach were used to discriminate between the aliquots of six oil spillages monitored on time by mid-IR spectroscopy. Further, a set of 45 unknowns collected in Galician beaches after a major shipwreck were analyzed by both the IR-chemometric-based method and an international oil fingerprinting standard protocol (the European Guideline CEN/TR 15522–2 guide) to set their ‘true’ assignations. Classification of the controlled spillages yielded almost 100% successful classification ratios (precision, sensitivity and specificity) whereas less than 5% false positives and false negatives were obtained when the 45 samples were classified. SVM with polynomial kernels had only 1 misclassification and outperformed the other approaches, including the ‘consensus’ approach. CP-ANN, radial basis functions-PLS and the consensus approach were the second best models with 93.3% agreement with the standard protocol. On the other hand, linear PLS-DA yielded the worst classification model. ⺠Oil spillages represent a common problem in the European marine environment ⺠Current European Directives imply tiered visual comparisons of chromatograms ⺠Subjective decisions can be avoided with supervised pattern recognition to classify unknowns ⺠Support Vector Machines outstood among eight parametric and non parametric methods ⺠Less than 5% false positives and negatives revealed the chemometric alternative as a powerful alternative

Gómez Carracedo, M., Fernández Varela, R., Ballabio, D., Andrade, J. (2012). Screening oil spills by mid-IR spectroscopy and supervised pattern recognition techniques. CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 114(15 May 2012), 132-142 [10.1016/j.chemolab.2012.03.013].

Screening oil spills by mid-IR spectroscopy and supervised pattern recognition techniques

BALLABIO, DAVIDE;
2012

Abstract

Supervised pattern recognition methods had scarcely been applied to assess the origin of hydrocarbons lumps arrived at the coastline. In this work eight supervised multivariate methods based on quite different principles (Discriminant Analysis, Principal Components Analysis combined to Discriminant Analysis, Soft Independent Modelling of Class Analogy, K-Nearest Neighbours, Partial Least Squares Discriminant Analysis –PLS-DA-, kernel-PLS (radial basis functions-PLS), Counterpropagation Artificial Neural Networks –CP-ANN- and Support Vector Machines with linear, radial basis function and polynomial kernels) and a ‘consensus’ approach were used to discriminate between the aliquots of six oil spillages monitored on time by mid-IR spectroscopy. Further, a set of 45 unknowns collected in Galician beaches after a major shipwreck were analyzed by both the IR-chemometric-based method and an international oil fingerprinting standard protocol (the European Guideline CEN/TR 15522–2 guide) to set their ‘true’ assignations. Classification of the controlled spillages yielded almost 100% successful classification ratios (precision, sensitivity and specificity) whereas less than 5% false positives and false negatives were obtained when the 45 samples were classified. SVM with polynomial kernels had only 1 misclassification and outperformed the other approaches, including the ‘consensus’ approach. CP-ANN, radial basis functions-PLS and the consensus approach were the second best models with 93.3% agreement with the standard protocol. On the other hand, linear PLS-DA yielded the worst classification model. ⺠Oil spillages represent a common problem in the European marine environment ⺠Current European Directives imply tiered visual comparisons of chromatograms ⺠Subjective decisions can be avoided with supervised pattern recognition to classify unknowns ⺠Support Vector Machines outstood among eight parametric and non parametric methods ⺠Less than 5% false positives and negatives revealed the chemometric alternative as a powerful alternative
Articolo in rivista - Articolo scientifico
Oil spill fingerprint, IR spectroscopy, chemometrics
English
2012
114
15 May 2012
132
142
none
Gómez Carracedo, M., Fernández Varela, R., Ballabio, D., Andrade, J. (2012). Screening oil spills by mid-IR spectroscopy and supervised pattern recognition techniques. CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 114(15 May 2012), 132-142 [10.1016/j.chemolab.2012.03.013].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/30379
Citazioni
  • Scopus 18
  • ???jsp.display-item.citation.isi??? 18
Social impact