Forecasting of jack mackerel landings (Trachurus murphyi) in central‐southern Chile through neural networks

Abstract

In the present study, the performance of neuronal networks models in monthly landing forecasting of jack mackerel (Trachurus murphyi) in central-southern Chile (32°S-42°S) was assessed. Thus, monthly estimations for 10 environmental variables, fishing effort (fe) and jack mackerel landings for the period 1973-2008 were used. A preliminary analysis was done in order to remove strongly correlated variables. Sea surface temperature (SST) and fe are established as input variables, then, a non-linear cross correlation analysis was performed to estimate the lag between the input variables and jack mackerel landings. Two models were adjusted: model one includes both training and testing cases randomly selected using all data involved in the analysed period; for model 2, the data is divided into two time series: the first from 1973 to 2002 used for training and the second between 2003 and 2008 used for validation. The external validation process for model 1 showed an explained variance of 92%, with a standard forecasting error of 30%. The explained variance for model 2 was 81%, with a standard forecasting error of 38%. Finally, the sensitivity analysis for both models showed the fe as the most influential variable to jack mackerel landings, which presents functionality depending on anthropogenic effects rather than environmental conditions.

The Interaction Between Stock Dynamics, Fishing and Climate Caused the Collapse of the Jack Mackerel Stock at Humboldt Current Ecosystem

“…On the other hand, ENSO variability seems to influence the spatial distribution of jack-mackerel, hence, affecting the catchability to the fishery (Yañez et al, 1996;Arcos et al, 2001;Naranjo et al, 2015). A similar finding was described for another jack mackerel species at New Zealand coasts, where ENSO variability has strong effects on krill distribution at coastal waters and introduce changes in the jack mackerel school behavior leading to fishery failures (Harris et al, 1992).…”

“…Indeed, Yañez et al (1996) reported that strong thermal gradients associated with the intrusion of oceanic waters off the Chilean coast increases the probability of catching jack mackerel, hence, influencing the operations of fishing vessels. For example, Chilean fishing fleet increased it capacity (larger vessels), the duration of the fishing trips and number of hauls per trip in response to changes in jack mackerel spatial distribution (Naranjo et al, 2015).…”

South Pacific Integrated Ecosystem Studies meeting: toward conservation and sustainable use of marine resources in the South Pacific

“…Naranjo et al . () presented a set of models based on neuronal networks to forecast jack mackerel landings ( Trachurus murphyi ) in central southern Chile. For jack mackerel, anthropogenic effects (e.g.…”

“…This supplement presents two articles related to this major theme, both exploring the use of environmental variables to forecast landings. Naranjo et al (2015) presented a set of models based on neuronal networks to forecast jack mackerel landings (Trachurus murphyi) in central southern Chile. For jack mackerel, anthropogenic effects (e.g.…”

Focused small-scale fisheries as complex systems using deep learning models

“…Artificial intelligence models, specifically deep learning models (DLM), are characterized by their ability to predict a variable's value concerning a specific scenario (Zhang et al 2018). The DLM have been used to forecast the catches of different fisheries, like mackerel, cod, sardine or finfish (Kim et al 2015, Naranjo et al 2015, Kim et al 2016, Petatán-Ramírez et al 2019. DLM has used as input variables of different data types, such as satellite images of sea spectrograph (e.g.…”