No abstract

Globally, over 80% of fisheries are at maximum sustainable levels or overexploited. However, small-scale fisheries (SSFs) in developing countries play a relevant role in coastal communities’ development with important impacts on the economy. The SSFs are normally multi-specific and due to the lack of data, studying them by simulation poses an important challenge especially forecasting models. These models are necessary to support management decisions or develop sustainable fisheries; therefore, models based on Deep Learning were proposed to forecast SSFs catch, using data from official catch landing reports (OCLRs), satellite images, and oceanographic data. The finfish fishery in Bahía Magdalena-Almejas (México) was used for the present study. According to an analysis of OCLRs, the target species of major importance in the fishery were identified and selected for the model. The proposed deep learning models used two artificial neural networks structures: non-linear autoregressive neural network and long-short term memory network, which were designed to assess and forecast monthly catch levels of Paralabrax nebulifer and Caulolatilus princeps. Models with a performance efficiency of R > 0.8, MSE < 300 were found, which indicate that the models are applicable in SSF with poor data and multi-specific fishery contexts, at low cost.

Small-scale fishing (SSF) is a relevant economic activity worldwide, so sustainable development will be essential to assure its contributions to food security, poverty alleviation, and healthy ecosystems. However, the wide diversity of fisheries, their complexity, and the lack of information limit the ability to propose/evaluate management measures and plans and their effects on communities and other productive activities. The state of Baja California Sur, Mexico, our study case, ranks as the third place in national fisheries production, possesses SSF fleets, has a wide variety of fisheries that share fishing areas, fishing seasons, and operating units. In this work, assuming SSF as a complex system were proposed deep learning models (DLM) to forecast the catch volumes, evaluate each input variable's importance, and find interactions. Environmental variables and catch fisheries were tested in the DLM to estimate their predictive power. Different DLM structures and parameters to find the optimal model was used. The variables that presented higher predictive power are the environmental variables with R = 0.90. Moreover, when used in combination with the catches from other areas, the performance of R = 0.95 is obtained. Using only the catches, the model has an R = 0.81. This model allows the use of variables that indirectly affect the system and demonstrates a useful tool to assess a complex system's state in the face of disturbances in its variables.