Predicting Fishing Footprint of Trawlers From Environmental and Fleet Data: An Application of Artificial Neural Networks

The increasing use of tracking devices, such as the Vessel Monitoring System and the Automatic Identification System, have allowed, in the last decade, detailed spatial and temporal analyses of fishing footprints and of their effects on environments and resources. Nevertheless, tracking devices usually allow monitoring of the largest length classes composing different fleets, whereas fishing vessels below a regulatory threshold (i.e., 15 m in length-over-all) are not mandatorily equipped with these tools. This issue is critical, since 36% of the vessels in the EU fleets belong to these “hidden” length classes. In this study, a model (namely, a cascaded multilayer perceptron network) is devised to predict the annual fishing footprints of vessels without tracking devices. This model uses information about fleet structures, environmental characteristics, human activities, and fishing effort patterns of vessels equipped with tracking devices. Furthermore, the model is able to take into account the interactions between different components of the fleets (e.g., fleet segments), which are characterized by different operating ranges and compete for the same marine space. The model shows good predictive performance and allows the extension of spatial analyses of fishing footprints to the relevant, although still unexplored, fleet segments.

[1]  Michael J. Watts,et al.  Comparing ensemble and cascaded neural networks that combine biotic and abiotic variables to predict insect species distribution , 2008, Ecol. Informatics.

[2]  David B. Sampson,et al.  The accuracy of self-reported fisheries data: Oregon trawl logbook fishing locations and retained catches , 2011 .

[3]  Stephen V. Stehman,et al.  Selecting and interpreting measures of thematic classification accuracy , 1997 .

[4]  S. Gelcich,et al.  Combining participatory and socioeconomic approaches to map fishing effort in small-scale fisheries , 2017, PloS one.

[5]  Alfredo Giron-Nava,et al.  A spatial method to calculate small-scale fisheries effort in data poor scenarios , 2017, PloS one.

[6]  Fabrizio Natale,et al.  Defining small-scale fisheries in the EU on the basis of their operational range of activity The Swedish fleet as a case study , 2015 .

[7]  Inmaculada Pulido-Calvo,et al.  Anchovy (Engraulis ringens) and sardine (Sardinops sagax) abundance forecast off northern Chile: A multivariate ecosystemic neural network approach , 2010 .

[8]  William R. Black,et al.  Spatial interaction modeling using artificial neural networks , 1995 .

[9]  Michel J. Kaiser,et al.  Implications of using alternative methods of vessel monitoring system (VMS) data analysis to describ , 2012 .

[10]  J. Rasmus Nielsen,et al.  DISPLACE: a dynamic, individual-based model for spatial fishing planning and effort displacement — integrating underlying fish population models , 2014 .

[11]  Sovan Lek,et al.  Artificial neural networks as a tool in ecological modelling, an introduction , 1999 .

[12]  J. Pinnegar,et al.  Thirty years of fleet dynamics modelling using discrete-choice models: what have we learned? , 2017 .

[13]  H. Gerritsen,et al.  Do big boats tow big nets , 2011 .

[14]  Michele Scardi,et al.  Advances in neural network modeling of phytoplankton primary production , 2001 .

[15]  Colm Lordan,et al.  Integrating vessel monitoring systems (VMS) data with daily catch data from logbooks to explore the spatial distribution of catch and effort at high resolution , 2011 .

[16]  Carlo Cerrano,et al.  Large marine protected areas (LMPAs) in the Mediterranean Sea: The opportunity of the Adriatic Sea , 2016 .

[17]  M. Cardinale,et al.  The Saga of the Management of Fisheries in the Adriatic Sea: History, Flaws, Difficulties, and Successes toward the Application of the Common Fisheries Policy in the Mediterranean , 2017, Front. Mar. Sci..

[18]  Ronald Pelot,et al.  Past, present, and future of the satellite-based automatic identification system: areas of applications (2004–2016) , 2018, WMU Journal of Maritime Affairs.

[19]  Emanuele Gandola,et al.  Cascaded neural networks improving fish species prediction accuracy: the role of the biotic information , 2018, Scientific Reports.

[20]  Stefanos Kavadas,et al.  Multi-Criteria Decision Analysis as a tool to extract fishing footprints and estimate fishing pressure: application to small scale coastal fisheries and implications for management in the context of the Maritime Spatial Planning Directive , 2015 .

[21]  Jeremy S. Collie,et al.  Modification of marine habitats by trawling activities: prognosis and solutions , 2002 .

[22]  G. Swartzman,et al.  Anchovy (Engraulis ringens) and sardine (Sardinops sagax) spatial dynamics and aggregation patterns in the Humboldt Current ecosystem, Peru, from 1983–2003 , 2007 .

[23]  Shui-Kai Chang,et al.  Application of a vessel monitoring system to advance sustainable fisheries management--Benefits received in Taiwan , 2011 .

[24]  Michele Scardi,et al.  Modeling landings profiles of fishing vessels: An application of Self-Organizing Maps to VMS and logbook data , 2016 .

[25]  N. Guillemot,et al.  A framework for mapping small-scale coastal fisheries using fishers' knowledge , 2014 .

[26]  Michele Scardi,et al.  Developing an empirical model of phytoplankton primary production: a neural network case study , 1999 .

[27]  Christopher J. Smith,et al.  Impact of otter trawling on an eastern Mediterranean commercial trawl fishing ground , 2000 .

[28]  R. Lewison,et al.  Quantifying fishing effort: a synthesis of current methods and their applications , 2008 .

[29]  J. Collie,et al.  A quantitative analysis of fishing impacts on shelf-sea benthos. , 2000, The Journal of animal ecology.

[30]  Michele Gristina,et al.  SMART: A Spatially Explicit Bio-Economic Model for Assessing and Managing Demersal Fisheries, with an Application to Italian Trawlers in the Strait of Sicily , 2014, PloS one.

[31]  Andrea Belardinelli,et al.  Assessing the fishing footprint using data integrated from different tracking devices: Issues and opportunities , 2016 .

[32]  Tommaso Russo,et al.  New insights in interpolating fishing tracks from VMS data for different métiers , 2011 .

[33]  Hadley Wickham,et al.  ggmap: Spatial Visualization with ggplot2 , 2013, R J..

[34]  Makarand Deo,et al.  Artificial neural networks in coastal and ocean engineering , 2010 .

[35]  S. Libralato,et al.  Analysis of Long-Term Changes in a Mediterranean Marine Ecosystem Based on Fishery Landings , 2017, Front. Mar. Sci..

[36]  C. Papaconstantinou,et al.  Fisheries in the Mediterranean , 2000 .

[37]  Stefano Cataudella,et al.  When behaviour reveals activity: Assigning fishing effort to métiers based on VMS data using artificial neural networks , 2011 .

[38]  Michael Matthies,et al.  Artificial neural networks for modeling time series of beach litter in the southern North Sea. , 2014, Marine environmental research.

[39]  Sophie Bertrand,et al.  Optimization of an artificial neural network for identifying fishing set positions from VMS data: An example from the Peruvian anchovy purse seine fishery , 2011 .

[40]  S. Libralato,et al.  Recent Trends and Impacts of Fisheries Exploitation on Mediterranean Stocks and Ecosystems , 2017, Front. Mar. Sci..

[41]  Stefano Cataudella,et al.  VMSbase: An R-Package for VMS and Logbook Data Management and Analysis in Fisheries Ecology , 2014, PloS one.

[42]  Jacob Cohen,et al.  Weighted kappa: Nominal scale agreement provision for scaled disagreement or partial credit. , 1968 .

[43]  O. R. Eigaard,et al.  Bottom trawl fishing footprints on the world’s continental shelves , 2018, Proceedings of the National Academy of Sciences.

[44]  Martin A. Pastoors,et al.  Effects of fishing power and competitive interactions among vessels on the effort allocation on the trip level of the Dutch beam trawl fleet , 2000 .

[45]  Tommi Kärkkäinen,et al.  On Cross-Validation for MLP Model Evaluation , 2014, S+SSPR.

[46]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[47]  Antoni Quetglas,et al.  The Use of Artificial Neural Networks (ANNs) in Aquatic Ecology , 2011 .

[48]  Francois Bastardie,et al.  Spatial planning for fisheries in the Northern Adriatic: working toward viable and sustainable fishing , 2017 .