• DocumentCode
    3023606
  • Title

    Prediction of probable Tuna fishing grounds based on Bayesian theorem

  • Author

    Zhou, Sufang ; Fan, Wei ; Wu, Jianping

  • Author_Institution
    Geogr. Dept., East China Normal Univ., Shanghai, China
  • Volume
    4
  • fYear
    2009
  • fDate
    7-8 Nov. 2009
  • Firstpage
    156
  • Lastpage
    162
  • Abstract
    Highly migratory tuna is one of economically important harvesting objects of the world. It is practically significant to forecast the probable fishing grounds. Based on satellite data of SST supplied by NASA and historical tuna catch data provided by SPC, relationship between catchability and SST was studied. And then using the Bayesian theorem, a tuna probable fishing grounds prediction expert system was set up. The result of 40-years-hindcasting experiments shows that the predicting accuracy of skipjack fishing grounds in West Pacific is over 70%, which is significant to guide fishing operations. However, now fishing grounds transcendental probability and conditional probability are computed every month, it must be modified according to field survey data for future fishing grounds prediction every week.
  • Keywords
    Bayes methods; expert systems; fishing industry; ocean temperature; probability; Bayesian theorem; SPC; SST; catchability; conditional probability; expert system; historical tuna catch data; probable tuna fishing grounds prediction; satellite data; skipjack fishing grounds; transcendental probability; Aquaculture; Artificial neural networks; Bayesian methods; Decision making; Economic forecasting; Environmental economics; Expert systems; Geography; Marine animals; Predictive models; Bayesian probability; Fishing grounds; Prediction model; Tuna;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Artificial Intelligence and Computational Intelligence, 2009. AICI '09. International Conference on
  • Conference_Location
    Shanghai
  • Print_ISBN
    978-1-4244-3835-8
  • Electronic_ISBN
    978-0-7695-3816-7
  • Type

    conf

  • DOI
    10.1109/AICI.2009.530
  • Filename
    5376398