Artificial neural network approaches to one-step weekly prediction of Dinophysis acuminata blooms in Huelva (Western Andalucía, Spain)

Deep water longline selectivity for black spot seabream (Pagellus bogaraveo) in the Strait of Gibraltar

“…In this way, high correlations can be achieved by mediocre or poor models. Similar conclusions were obtained in the forecasting of different kinds of time variables [44][45][46][47][48].…”

Monthly catch forecasting of anchovy Engraulis ringens in the north area of Chile: Non-linear univariate approach

“…Recently, CNNs have been extensively applied to time series forecasting (Griñó, 1992;Prybutok et al, 2000;Belgrano et al, 2001;Zeng et al, 2001;Gutiérrez-Estrada et al, 2004;Pulido-Calvo and Portela, 2007;Velo-Suárez and Gutiérrez-Estrada, 2007), although few studies have been applied in fisheries sciences (Komatsu et al, 1994;Chen et al, 2000;Chen and Hare, 2006). This paper evaluates the performance of feed forward CNN models trained with the Levenberg-Marquardt algorithm (Shepherd, 1997) for the purpose of anchovy catches time series forecasting (one-step monthly anchovy catch forecast model).…”

Application of functional data analysis to investigate seasonal progression with interannual variability in plankton abundance in the Bay of Fundy, Canada

“…Although it was not attempted, it may be worthwhile to test the FDA method on a spatial scale using b-spline basis functions. As for forecasting future blooms, recent studies are focusing on the use of methods such as population viability analysis (Holmes et al 2007) and artificial neural networks (Teles et al 2006;Velo-Suárez and Gutiérrez-Estrada, 2007), where results from FDA could provide a starting point in carrying out such analyses.…”

“…To interpret these data, a central problem to be addressed is the extraction of the underlying abundance signal from these noisy data (Wyatt, 1995). Various statistical methods have been used to handle sparse and noisy abundance data, for example, time series analysis (Li and Smayda, 2001) Licandro et al 2001), spline fitting (Wood and Horwood, 1995), objective analysis (Zhou, 1998), and also more complex methods focused on forecasting future blooms, such as artificial neural networks (Teles et al 2006;Velo-Suárez and Gutiérrez-Estrada, 2007) and population dynamics models involving population viability analysis (Holmes et al 2007).…”