Sequential Fish Catch Forecasting Using Bayesian State Space Models

Yuya Kokaki, Naohiro Tawara, Tetsunori Kobayashi, Kazuo Hashimoto, Tetsuji Ogawa

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    A new state space model suitable for fixed shore net fishing is proposed and successfully applied to daily fish catch forecasting. Accurate prediction of daily fish catches makes it possible to support fishery workers with decision-making for efficient operations. For that purpose, the predictive model should be intuitive to the fishery workers and provide an estimate with a confidence. In the present paper, a fish catch forecasting method is developed using a state space model that emulates the process of fixed shore net fishing. In this method, the parameter estimation and prediction are sequentially performed using the Hamiltonian Monte Carlo method. The experimental comparisons using actual fish catch data and public meteorological information demonstrated that the proposed forecasting system yielded significant reductions in predictive errors over the systems based on decision-trees and legacy state-space models.

    Original languageEnglish
    Title of host publication2018 24th International Conference on Pattern Recognition, ICPR 2018
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages776-781
    Number of pages6
    Volume2018-August
    ISBN (Electronic)9781538637883
    DOIs
    Publication statusPublished - 2018 Nov 26
    Event24th International Conference on Pattern Recognition, ICPR 2018 - Beijing, China
    Duration: 2018 Aug 202018 Aug 24

    Other

    Other24th International Conference on Pattern Recognition, ICPR 2018
    CountryChina
    CityBeijing
    Period18/8/2018/8/24

    Fingerprint

    Fish
    Fisheries
    Hamiltonians
    Decision trees
    Parameter estimation
    Monte Carlo methods
    Decision making

    ASJC Scopus subject areas

    • Computer Vision and Pattern Recognition

    Cite this

    Kokaki, Y., Tawara, N., Kobayashi, T., Hashimoto, K., & Ogawa, T. (2018). Sequential Fish Catch Forecasting Using Bayesian State Space Models. In 2018 24th International Conference on Pattern Recognition, ICPR 2018 (Vol. 2018-August, pp. 776-781). [8546069] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.2018.8546069

    Sequential Fish Catch Forecasting Using Bayesian State Space Models. / Kokaki, Yuya; Tawara, Naohiro; Kobayashi, Tetsunori; Hashimoto, Kazuo; Ogawa, Tetsuji.

    2018 24th International Conference on Pattern Recognition, ICPR 2018. Vol. 2018-August Institute of Electrical and Electronics Engineers Inc., 2018. p. 776-781 8546069.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Kokaki, Y, Tawara, N, Kobayashi, T, Hashimoto, K & Ogawa, T 2018, Sequential Fish Catch Forecasting Using Bayesian State Space Models. in 2018 24th International Conference on Pattern Recognition, ICPR 2018. vol. 2018-August, 8546069, Institute of Electrical and Electronics Engineers Inc., pp. 776-781, 24th International Conference on Pattern Recognition, ICPR 2018, Beijing, China, 18/8/20. https://doi.org/10.1109/ICPR.2018.8546069
    Kokaki Y, Tawara N, Kobayashi T, Hashimoto K, Ogawa T. Sequential Fish Catch Forecasting Using Bayesian State Space Models. In 2018 24th International Conference on Pattern Recognition, ICPR 2018. Vol. 2018-August. Institute of Electrical and Electronics Engineers Inc. 2018. p. 776-781. 8546069 https://doi.org/10.1109/ICPR.2018.8546069
    Kokaki, Yuya ; Tawara, Naohiro ; Kobayashi, Tetsunori ; Hashimoto, Kazuo ; Ogawa, Tetsuji. / Sequential Fish Catch Forecasting Using Bayesian State Space Models. 2018 24th International Conference on Pattern Recognition, ICPR 2018. Vol. 2018-August Institute of Electrical and Electronics Engineers Inc., 2018. pp. 776-781
    @inproceedings{6e61f3e1905d4ebb95f05d0242a393cf,
    title = "Sequential Fish Catch Forecasting Using Bayesian State Space Models",
    abstract = "A new state space model suitable for fixed shore net fishing is proposed and successfully applied to daily fish catch forecasting. Accurate prediction of daily fish catches makes it possible to support fishery workers with decision-making for efficient operations. For that purpose, the predictive model should be intuitive to the fishery workers and provide an estimate with a confidence. In the present paper, a fish catch forecasting method is developed using a state space model that emulates the process of fixed shore net fishing. In this method, the parameter estimation and prediction are sequentially performed using the Hamiltonian Monte Carlo method. The experimental comparisons using actual fish catch data and public meteorological information demonstrated that the proposed forecasting system yielded significant reductions in predictive errors over the systems based on decision-trees and legacy state-space models.",
    author = "Yuya Kokaki and Naohiro Tawara and Tetsunori Kobayashi and Kazuo Hashimoto and Tetsuji Ogawa",
    year = "2018",
    month = "11",
    day = "26",
    doi = "10.1109/ICPR.2018.8546069",
    language = "English",
    volume = "2018-August",
    pages = "776--781",
    booktitle = "2018 24th International Conference on Pattern Recognition, ICPR 2018",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - GEN

    T1 - Sequential Fish Catch Forecasting Using Bayesian State Space Models

    AU - Kokaki, Yuya

    AU - Tawara, Naohiro

    AU - Kobayashi, Tetsunori

    AU - Hashimoto, Kazuo

    AU - Ogawa, Tetsuji

    PY - 2018/11/26

    Y1 - 2018/11/26

    N2 - A new state space model suitable for fixed shore net fishing is proposed and successfully applied to daily fish catch forecasting. Accurate prediction of daily fish catches makes it possible to support fishery workers with decision-making for efficient operations. For that purpose, the predictive model should be intuitive to the fishery workers and provide an estimate with a confidence. In the present paper, a fish catch forecasting method is developed using a state space model that emulates the process of fixed shore net fishing. In this method, the parameter estimation and prediction are sequentially performed using the Hamiltonian Monte Carlo method. The experimental comparisons using actual fish catch data and public meteorological information demonstrated that the proposed forecasting system yielded significant reductions in predictive errors over the systems based on decision-trees and legacy state-space models.

    AB - A new state space model suitable for fixed shore net fishing is proposed and successfully applied to daily fish catch forecasting. Accurate prediction of daily fish catches makes it possible to support fishery workers with decision-making for efficient operations. For that purpose, the predictive model should be intuitive to the fishery workers and provide an estimate with a confidence. In the present paper, a fish catch forecasting method is developed using a state space model that emulates the process of fixed shore net fishing. In this method, the parameter estimation and prediction are sequentially performed using the Hamiltonian Monte Carlo method. The experimental comparisons using actual fish catch data and public meteorological information demonstrated that the proposed forecasting system yielded significant reductions in predictive errors over the systems based on decision-trees and legacy state-space models.

    UR - http://www.scopus.com/inward/record.url?scp=85059747873&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85059747873&partnerID=8YFLogxK

    U2 - 10.1109/ICPR.2018.8546069

    DO - 10.1109/ICPR.2018.8546069

    M3 - Conference contribution

    AN - SCOPUS:85059747873

    VL - 2018-August

    SP - 776

    EP - 781

    BT - 2018 24th International Conference on Pattern Recognition, ICPR 2018

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -