Detection of potential fishing zones for neon flying squid based on remote-sensing data in the Northwest Pacific Ocean using an artificial neural network

Ommastrephes bartramii is a short-lived species of squid and reacts rapidly to changes in the regional environmental conditions of the fishing ground. Understanding the preferred range of key environmental variables and predicting potential resource distributions are critical to conserve and manage its resources. Commercial fishery data for the western winter–spring cohort of O. bartramii from Chinese squid-jigging vessels during 2003–2013 were used to evaluate a suitable range of three key environmental variables, sea surface temperature (SST), sea surface height (SSH), and chlorophyll-a (chl-a) concentration, and to explore potential fishing zones (PFZs) using an artificial neural network. The neural interpretation diagram and independent variable relevance analysis indicate that month, latitude, and SST had significant influences on the PFZ distribution of O. bartramii, yielding 21.78%, 23.91%, and 26.04% of contribution rates, respectively. Based on the sensitivity analyses, a high abundance of O. bartramii mainly occurred in the waters between 150°–165° E and 37°–42° N during July to August. Suitable ranges of environmental variables for O. bartramii were 11–18°C for SST, −10 to 60 cm for SSH, and 0.1–1.7 mg/m³ for chl-a concentration, respectively. The back-propagation network model was well developed and could be used to predict the PFZ with 80% accuracy. The actual fishing grounds coincided with the predicted PFZ, suggesting that the established model of PFZ is effective in forecasting the potential habitat of O. bartramii in the Northwest Pacific Ocean.