Anchovy (Engraulis ringens) and sardine (Sardinops sagax) abundance forecast off northern Chile: A multivariate ecosystemic neural network approach

Yáñez, Eleuterio; Plaza, Francisco; Gutiérrez‐Estrada, Juan Carlos; Rodríguez, Nibaldo; Barbieri, María Ángela; Pulido‐Calvo, Inmaculada; Bórquez, Cinthya

doi:10.1016/j.pocean.2010.09.015

Cited by 36 publications

(19 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The PFG prediction model uses the relationships between environmental conditions and resource distributions to determine the optimal ranges of environmental conditions within fishing grounds. Additionally, ANN simulation models were used to predict the monthly anchovy abundance and to analyze relationships with environmental factors using the methodological approaches described in Gutiérrez-Estrada et al (2007) and Yáñez et al (2010). The ANNs models are mathematical structures capable of representing highly non-linear complex models that are not limited by assumptions on the functional relations among the involved variables (physical environment, biological, fisheries, others), when the data does not meet statistical assumptions, and having good ability to generalize when entering new data; in this sense, they present a great advantage over conventional models (Lek & Guégan, 1999;Özesmi et al, 2006).…”

Section: Eaf Case Study: Prediction Of Environmental Variability Effementioning

confidence: 99%

See 1 more Smart Citation

Using indicators and models for an ecosystem approach to fisheries and aquaculture management: the anchovy fishery and Pacific oyster culture in Chile: case studies

Silva¹,

Barbieri²,

Yáñez³

et al. 2012

lajar

View full text Add to dashboard Cite

ABSTRACT. This study illustrate the use of indicators and models to support the Ecosystem Approach to Fisheries and Aquaculture management using two case studies in Chile: prediction of environmental variability effects upon anchovy (Engraulis ringens) fishery of northern Chile and prediction of suitable sites and carrying capacity of Pacific oyster (Crassostrea gigas) culture using FARM and geographic information system (GIS) models in the Valdivia estuary. A three stage approach was applied: Stage 1 considers spatiotemporal ecosystem indicators (fisheries, aquaculture, environmental, and regulatory), Stage 2 uses statistical relationships between indicators, GIS, and other simulation models (e.g., artificial neural networks and FARM) of environment-resources interaction, and Stage 3 is the analysis and validation of models outputs. The methodology illustrates how indicators and models may be used to assist decision-makers in developing an ecosystem approach to fisheries and aquaculture. The application of these approaches provides an integrative methodology for abundance prediction of anchovy and site selection for shellfish aquaculture, despite limitations in the available data.

show abstract

Section: Eaf Case Study: Prediction Of Environmental Variability Effementioning

confidence: 99%

“…In particular, non-linear modelling of pelagic fisheries of northern Chile was first performed using an univariate ANN model that considered only anchovy catches (Gutiérrez-Estrada et al, 2007). Studies by Gutiérrez-Estrada et al (2009) and Yáñez et al (2010) : Ferreira et al, 2007).…”

Section: Introductionmentioning

confidence: 99%

Using indicators and models for an ecosystem approach to fisheries and aquaculture management: the anchovy fishery and Pacific oyster culture in Chile: case studies

Silva¹,

Barbieri²,

Yáñez³

et al. 2012

lajar

View full text Add to dashboard Cite

show abstract

“…; Gutiérrez‐Estrada and Bilton ; Yáñez et al . ). The analysis was carried out by replacing each input variable with missing values and assessing the effect of this on the output error.…”

Section: Methodsmentioning

confidence: 99%

Dimensionality reduction in drought modelling

Santos

Portela

Pulido‐Calvo

2012

Hydrological Processes

Self Cite

View full text Add to dashboard Cite

For monitoring hydrological events characterized by high spatial and temporal variability, the number and location of recording stations must be carefully selected to ensure that the necessary information is collected. Depending on the characteristics of each natural process, certain stations may be spurious or redundant, whereas others may provide most of the relevant data. With the objective of reducing the costs of the monitoring system and, at the same time, improving its operational effectiveness, three procedures were applied to identify the minimum network of rain gauge stations able to capture the characteristics of droughts in mainland Portugal. Drought severity is characterized by the standardized precipitation index applied to the timescales of 1, 3, 6 and 12 consecutive months. The three techniques used to reduce the dimensionality of the network of rain gauges were as follows: (i) artificial neural networks with sensitivity analysis, (ii) application of the mutual information criterion and (iii) K‐means cluster analysis using Euclidean distances. The results demonstrated that the best dimensionality reduction method was case dependent in the three regions of Portugal (northern, central and southern) previously identified by cluster analysis. All the reduction techniques lead to the selection of a subset of rain gauges capable of reproducing the original temporal patterns of drought. For specific severe drought events in Portugal in the past, the comparison between drought spatial patterns obtained with the original stations and the selected subset indicated that the subset produced statistically satisfactory results (correlation coefficients higher than 0.6 and efficiency coefficients higher than 0.5). Copyright © 2012 John Wiley & Sons, Ltd.

show abstract

“…To the best of our knowledge, few publications exist on multi-step-ahead forecasting models for fisheries resources. In recent years, linear regression models [1], [2] and artificial neuronal networks (ANN) [3]- [5] have been proposed for fisheries forecasting models. The disadvantage of models based on linear regressions is the supposition of stationarity and linearity of the time series of pelagic species catches.…”

Section: Introductionmentioning

confidence: 99%

“…Although ANN allows modeling the non-linear behaviour of a time series, they also have some disadvantages such as the stagnancy of local minimum due to the steepest descent learning method and over-fitting problem. A multilayer perceptron neural network to improve the convergence speed and forecasting accuracy of anchovy and sardines catches off northern Chile was proposed by [3]- [5], which reported a coefficient of determination between 82% and 87%.…”

Section: Introductionmentioning

confidence: 99%

Multiscale RBF Neural Network for Forecasting of Monthly Hake Catches off Southern Chile

2013

View full text Add to dashboard Cite

Abstract-We present a forecasting strategy based on stationary wavelet transform combined with radial basis function (RBF) neural network to improve the accuracy of 3-month-ahead hake catches forecasting of the fisheries industry in the central southern Chile. The general idea of the proposed forecasting model is to decompose the raw data set into an annual cycle component and an inter-annual component by using 3-levels stationary wavelet decomposition. The components are independently predicted using an autoregressive RBF neural network model. The RBF neural network model is composed of linear and nonlinear weights, which are estimates using the separable nonlinear least squares method. Consequently, the proposed forecaster is the co-addition of two predicted components. We demonstrate the utility of the proposed model on hake catches data set for monthly periods from 1963 to 2008. Experimental results on hake catches data show that the autoregressive RBF neural network model is effective for 3-month-ahead forecasting.

show abstract

Anchovy (Engraulis ringens) and sardine (Sardinops sagax) abundance forecast off northern Chile: A multivariate ecosystemic neural network approach

Cited by 36 publications

References 45 publications

Using indicators and models for an ecosystem approach to fisheries and aquaculture management: the anchovy fishery and Pacific oyster culture in Chile: case studies

Using indicators and models for an ecosystem approach to fisheries and aquaculture management: the anchovy fishery and Pacific oyster culture in Chile: case studies

Dimensionality reduction in drought modelling

Multiscale RBF Neural Network for Forecasting of Monthly Hake Catches off Southern Chile

Contact Info

Product

Resources

About