Por favor, use este identificador para citar o enlazar este ítem: http://dspace.azti.es/handle/24689/295
Ficheros en este ítem:
Fichero Tamaño Formato  
evaluating machine-learning.pdf2,36 MBAdobe PDFVisualizar/Abrir
Título : Evaluating machine-learning techniques for recruitment forecasting of seven North East Atlantic fish species
Autor : Fernandes, Jose A.; Irigoien, Xabier; Lozano, Jose A.; Inza, Inaki; Goikoetxea, Nerea; Perez, Aritz
Citación : ECOLOGICAL INFORMATICS, 2015, 25, 35-42
Resumen : The effect of different factors (spawning biomass, environmental conditions) on recruitment is a subject of great importance in the management of fisheries, recovery plans and scenario exploration. In this study, recently proposed supervised classification techniques, tested by the machine-learning community, are applied to forecast the recruitment of seven fish species of North East Atlantic (anchovy, sardine, mackerel, horse mackerel, hake, blue whiting and albacore), using spawning, environmental and climatic data. In addition, the use of the probabilistic flexible naive Bayes classifier (FNBC) is proposed as modelling approach in order to reduce uncertainty for fisheries management purposes. Those improvements aim is to improve probability estimations of each possible outcome (low, medium and high recruitment) based in kernel density estimation, which is crucial for informed management decision making with high uncertainty. Finally, a comparison between goodness-of-fit and generalization power is provided, in order to assess the reliability of the final forecasting models. It is found that in most cases the proposed methodology provides useful information for management whereas the case of horse mackerel is an example of the limitations of the approach. The proposed improvements allow for a better probabilistic estimation of the different scenarios, i.e. to reduce the uncertainty in the provided forecasts. (C) 2014 Elsevier B.V. All rights reserved.
Palabras clave : Pelagic fish; Fisheries management; Recruitment forecasting; Bayesian networks; Supervised classification; Kernel density estimation; ANCHOVY ENGRAULIS-ENCRASICOLUS; BISCAY ANCHOVY; BAY; ENVIRONMENT; CLASSIFICATION; CLASSIFIERS; PREDICTION; VARIABLES; MODEL
Fecha de publicación : 2015
Editorial : ELSEVIER SCIENCE BV
Tipo de documento: Article
Idioma: Inglés
DOI: 10.1016/j.ecoinf.2014.11.004
URI : http://dspace.azti.es/handle/24689/295
ISSN : 1574-9541
E-ISSN: 1878-0512
Patrocinador: Fundacion Centros Tecnologicos Inaki Goenaga
Department of Agriculture, Fisheries and Food of the Basque Country Government
Saiotek and Research Groups programs (Basque Government) \[IT-242-07]
Spanish Ministry of Education and Science \[TIN2008-06815-C02-01]
COMBIOMED network in computational biomedicine (Carlos III Health Institute)
EU project UNCOVER
EU FACT
EU VII Framework project MEECE (MEECE) \[212085]
Aparece en las tipos de publicación: Artículos científicos



Los ítems de DSpace están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.