Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2018 May 21;13(5):e0196991.
doi: 10.1371/journal.pone.0196991. eCollection 2018.

Disentangling the complexity of tropical small-scale fisheries dynamics using supervised Self-Organizing Maps

Manuel Mendoza-Carranza  1 , Elisabet Ejarque  2 , Leopold A J Nagelkerke  3
Affiliations

Disentangling the complexity of tropical small-scale fisheries dynamics using supervised Self-Organizing Maps

Manuel Mendoza-Carranza et al. PLoS One. .

Abstract

Tropical small-scale fisheries are typical for providing complex multivariate data, due to their diversity in fishing techniques and highly diverse species composition. In this paper we used for the first time a supervised Self-Organizing Map (xyf-SOM), to recognize and understand the internal heterogeneity of a tropical marine small-scale fishery, using as model the fishery fleet of San Pedro port, Tabasco, Mexico. We used multivariate data from commercial logbooks, including the following four factors: fish species (47), gear types (bottom longline, vertical line+shark longline and vertical line), season (cold, warm), and inter-annual variation (2007-2012). The size of the xyf-SOM, a fundamental characteristic to improve its predictive quality, was optimized for the minimum distance between objects and the maximum prediction rate. The xyf-SOM successfully classified individual fishing trips in relation to the four factors included in the model. Prediction percentages were high (80-100%) for bottom longline and vertical line + shark longline, but lower prediction values were obtained for vertical line (51-74%) fishery. A confusion matrix indicated that classification errors occurred within the same fishing gear. Prediction rates were validated by generating confidence interval using bootstrap. The xyf-SOM showed that not all the fishing trips were targeting the most abundant species and the catch rates were not symmetrically distributed around the mean. Also, the species composition is not homogeneous among fishing trips. Despite the complexity of the data, the xyf-SOM proved to be an excellent tool to identify trends in complex scenarios, emphasizing the diverse and complex patterns that characterize tropical small scale-fishery fleets.

PubMed Disclaimer

Conflict of interest statement

The authors have declared that no competing interests exist.

Figures

Fig 1
Fig 1. Study area.
The light-grey polygon indicates the fishing area of the small-scale fleet from San Pedro Port in the southern Gulf of Mexico.
Fig 2
Fig 2. Graphical summary of the methodology.
a) Vessel arrival identified by fishermen nickname of vessel name, b) data acquisition in logbook, c) ordering and classifying data in electronic format, d) defining the importance of factor by ctree methodology, e) definition the size of xyf-SOM grid, f) xyf-SOM training, g) generation of confidence intervals for xfy-SOM predictions, h) testing for species arrangement based on xyf-SOM weights using cluster analysis, i) catch rate analyses using beanplots on xyf-SOM weights.
Fig 3
Fig 3. Conditional inference tree.
Main factors influencing catch rates of the small-scale fishery fleets of San Pedro port, Tabasco, Mexico. BL = bottom longline, VL = vertical line, SBL = Shark bottom longline. Boxplots below the tree are catch rates (mean±S.D).
Fig 4
Fig 4. Determination of the xyf-SOM map size.
Relationship between number of nodes (xyf-SOM size) and prediction percentage (blue circles), and distance between objects inside the xyf-SOM (red circles).
Fig 5
Fig 5. Supervised Self-Organizing Map (xyf-SOM).
At the general xyf-SOM map, color indicates gear type: bottom longline (BL) is represented in blue, vertical line + shark bottom longline (SBL) in green and vertical line (VL) in red; light tones indicate the cold season, and dark tones the warm season. Thick lines delineate years. At the species-specific xyf-SOM maps, lines indicate the predicted areas for BL, VL and SBL, whereas the color scale corresponds to the catch rate in kg/trip (blue is low, red is high).
Fig 6
Fig 6. Hierarchical cluster analysis of fish groups’.
Cluster was based on weights from the general xyf-SOM using Ward’s method.
Fig 7
Fig 7. Seasonal catch rates (kg/trip) by fishing gear based on the weights derived from the xyf-SOM analysis.
Cold seasons are in blue and warm seasons are in red. BL) bottom longline, VL+SBL) vertical line + shark bottom longline and, VL) vertical line. Dotted line indicates the overall mean catch rate; long thick lines indicate the mean catch rates by season; short lines indicate individual catch rates by node as derived from the xyf-SOM. Areas correspond to the kernel density shape.
Fig 8
Fig 8. Seasonal catch rates (kg/ trip) for principal species associated with bottom longline (BL) based on the weights derived from the xyf-SOM analysis.
Cold seasons are in blue and warm seasons are in red. Dotted line indicates the overall mean catch rate; long, thick lines indicate mean values by season; short lines indicate individual catch rates by node, as derived from the xyf-SOM. Areas correspond to the kernel density shape.
Fig 9
Fig 9. Seasonal catch rates (kg/ trip) for the main species associated to vertical line plus shark bottom longline (VL+SBL) based on weights derived from the seasonal SOM analysis.
Cold seasons are in blue and warm seasons are in red. Dotted line indicates the overall mean catch rate; long, thick lines indicate the mean values by season, short lines indicate individual catch rates by node, as derived from the xyf-SOM. Areas correspond to kernel density shapes.
Fig 10
Fig 10. Seasonal catch rates (kg/trip) for the main species associated to vertical line (VL) based on weights derived from the seasonal SOM analysis.
Cold seasons are in blue and warm seasons are in red. Dotted line indicates the overall mean catch rate; long, thick lines indicate the mean values by season, short lines indicate individual catch rates by node, as derived from the SOM. Areas correspond to kernel density shapes.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Hollowed AB, Bax N, Beamish R, Collie J, Fogarty M, Livingston P, et al. Are multispecies models an improvement on single-species models for measuring fishing impacts on marine ecosystems? ICES J Mar Sci. 2000;57(3):707–19.
    1. Dreyfus-Leon M, Kleiber P. A spatial individual behaviour-based model approach of the yellowfin tuna fishery in the eastern Pacific Ocean. Ecol Model. 2001;146(1):47–56.
    1. Wilen JE, Smith MD, Lockwood D, Botsford LW. Avoiding Surprises: Incorporating Fisherman Behavior into Management Models. Bull Mar Sci. 2002;70:553–75.
    1. Brosse S, Giraudel JL, Lek S. Utilisation of non-supervised neural networks and principal component analysis to study fish assemblages. Ecol Model. 2001;146(1):159–66.
    1. Winker H, Kerwath SE, Attwood CG. Comparison of two approaches to standardize catch-per-unit-effort for targeting behaviour in a multispecies hand-line fishery. Fish Res. 2013;139:118–31.

Publication types

Grants and funding

This work was supported by the Consejo Nacional de Ciencia y Tecnología, 120931, 120925, to Dr Manuel Mendoza-Carranza and FORDECYT-CONACYT, 273646, to Dr Manuel Mendoza-Carranza. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

LinkOut - more resources