Using classification trees to study the effects of fisheries management plans on the yield of Merluccius merluccius (Linnaeus, 1758) in the Alboran Sea (Western Mediterranean)

Mendoza, Manuel; Garcı́a, Teresa; Baro, J.

doi:10.1016/j.fishres.2009.11.012

Cited by 5 publications

(3 citation statements)

References 32 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning, and more specifically regression and classification trees, have been scarcely used in fisheries (e.g. Mendoza et al 2010, Pérez-Ortiz et al 2013. However, this approach has shown a clear advantage over traditional multivariate methods or GLM/ GAM approaches, mainly because the resulting trees are by themselves explicative models of the relationship between the predictors and the response.…”

Section: Discussionmentioning

confidence: 99%

“…This study therefore proposes a new approach to analysing the impact of fishing, using in addition a novel methodological approach from the machine learning field. Regression trees allow for the recognition of patterns in data (Mendoza et al 2010, Davidson et al 2012. Here, these patterns are the combinations of technical, environmental and geographical factors that increase the fishing impact on cartilaginous fish in southeastern Spain.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Factors affecting the fishing impact on cartilaginous fishes in southeastern Spain (western Mediterranean Sea)

Mendoza¹,

Garrido²

2014

Sci. Mar.

Self Cite

View full text Add to dashboard Cite

Summary:We propose a global index of impact based on the relative vulnerability of the local population of every species and the further application of regression trees globally optimized with evolutionary algorithms to study the fishing impact on the cartilaginous fish in southeastern Spain. The fishing impact is much higher in areas of less than 40 m depth within 11 km of the Cape Palos marine reserve. The impact also depends on the state of the sea and the kind of habitat. Deep-sea habitats associated with hard substrata and sandy beds show the highest impact, and sublittoral muds and habitats associated with circalittoral rocks with moderate energy show the lowest impact. The fishing impact changes throughout the moon cycle, showing different day-scale patterns associated with different habitats and different species compositions. Finally, we show that the global optimization of the regression trees can be essential to find some important patterns and that these trees are a useful tool for determining which areas are considered to be more important in terms of protection, taking into account specifically the vulnerability of the local populations.Keywords: Cape of Palos MPA; conservation; cartilaginous fish; fishing impact; regression trees; evolutionary algorithms; vulnerable species. Factores que afectan el impacto pesquero sobre peces cartilaginosos en el sureste español (Mediterráneo Suroccidental)Resumen: Proponemos un índice global de impacto basado en la vulnerabilidad relativa de las poblaciones locales de cada una de las especies y la posterior aplicación de árboles de regresión globalmente optimizados con algoritmos evolutivos, para estudiar el impacto de la pesca en los peces cartilaginosos del sureste español. El impacto de la pesca es mucho mayor, dentro de los 11 km de la reserva marina de Cabo de Palos, en aquellas zonas de menos de 40 m de profundidad. El impacto también depende del estado de la mar y el tipo de hábitat. Los hábitats de aguas profundas asociados a sustrato duro y fondo arenoso muestran los máximos impactos, mientras que, tanto los fondos fangosos sublitorales como los hábitats rocosos circalitorales con moderada energía de las corrientes, muestran un menor impacto. Además, se dan cambios a lo largo del ciclo lunar en el impacto de la pesca, lo que significa que existen diferentes patrones diarios, asociados a distintos hábitats, con distinta composición específica. Finalmente, mostramos que la optimización global de los árboles de regresión es esencial para revelar patrones importantes y son una herramienta útil para determinar aquellas áreas mas importantes en términos de protección, teniendo en cuenta, concretamente, la vulnerabilidad de las poblaciones locales Palabras clave: Área Marina Protegida de Cabo de Palos; conservación; peces cartilaginosos; impacto pesquero; árboles de regresión; algoritmos evolutivos; especies vulnerables. Citation/Como citar este artículo: Mendoza M., Garrido D., Jose M.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Factors affecting the fishing impact on cartilaginous fishes in southeastern Spain (western Mediterranean Sea)

Mendoza¹,

Garrido²

2014

Sci. Mar.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Since their introduction to the scientific community (Quinlan, 1979, 1986; Breiman et al ., 1984) and their first applications in ecology (e.g. Kompare et al ., 1994), decision trees have successfully been applied for solving various problems, such as predicting algal blooms (Kompare et al ., 1994; Džeroski, 2001), analysing impacts of exotic species on ecosystems (Everaert et al ., 2011; Boets, Lock & Goethals, in press), fisheries management (Mendoza, García & Baro, 2010; Leclere et al ., 2011), predicting water quality (Dzeroski & Grbovic, 1995), conducting ecological assessments (De’ath & Fabricius, 2000; Dakou et al ., 2007) and habitat suitability modelling (Džeroski, 2009). Still, according to a literature review, the use of decision trees in ecology is quite modest compared to other methods, particularly statistical approaches, and to other disciplines (Olden, Lawler & Poff, 2008).…”

Section: Introductionmentioning

confidence: 99%

Fluctuations in water level and the dynamics of zooplankton: a data‐driven modelling approach

Škerjanec

Atanasova

2013

Freshwater Biology

View full text Add to dashboard Cite

Summary 1. The zooplankton in Lake Kinneret (Israel) have undergone large fluctuations in recent decades, which have been linked to both biotic and abiotic processes. 2. By applying a data‐driven modelling approach to a long‐term database, and focusing on key abiotic (lake‐level change) and biotic (prey abundance) variables, we attempted to identify the possible factors impacting the lake’s zooplankton community. 3. We hypothesised that changes in the predatory zooplankton (adult cyclopoids) assemblage are driven by changes in lake level during years of large changes. We further postulated that lake‐level changes would have a similar impact on the herbivorous zooplankton (cladocerans and cyclopoid copepodites) but an opposite effect on the microzooplankton. In the years of moderate changes to lake level, however, the abundance of predatory zooplankton would determine the size of the herbivore and microzooplankton populations rather than their food sources, that is, top‐down control. 4. The resulting decision trees supported the hypotheses stressing the importance of the annual rate of lake‐level change in shaping the zooplankton community in the lake. In addition, and in contrast to expectations, bottom‐up processes seem to play a role in determining zooplankton abundance.

show abstract

Demersal Resources

Aguilar

Ruiz

Jiménez

et al. 2021

Alboran Sea - Ecosystems and Marine Resources

View full text Add to dashboard Cite

Using classification trees to study the effects of fisheries management plans on the yield of Merluccius merluccius (Linnaeus, 1758) in the Alboran Sea (Western Mediterranean)

Cited by 5 publications

References 32 publications

Factors affecting the fishing impact on cartilaginous fishes in southeastern Spain (western Mediterranean Sea)

Factors affecting the fishing impact on cartilaginous fishes in southeastern Spain (western Mediterranean Sea)

Fluctuations in water level and the dynamics of zooplankton: a data‐driven modelling approach

Demersal Resources

Contact Info

Product

Resources

About