Predicting the Onset of Australian Winter Rainfall by Nonlinear Classification

Laura Firth, M.L. Hazelton, E.P. Campbell

    Research output: Contribution to journalArticle

    9 Citations (Scopus)

    Abstract

    A method for predicting the timing of winter rains is presented, making no assumptions about the functional form of any relationships that may exist. Ideas built on classification and regression trees and machine learning are used to develop robust predictive rules. These methods are applied in a case study to predict the timing of winter rain in five farming towns in the southwest of Western Australia. The variables used to construct the model are mean monthly sea Surface temperatures (SSTs) over a 72-cell grid in the Indian Ocean, Perth monthly mean sea level pressure (MSLP), and monthly values of the Southern Oscillation index (SOI). A predictive model is constructed from data over the period 1949-99. This model correctly classifies the onset of the winter rains approximately 80% of the time with SST variables proving to be the most important in deriving the predictions. Further analysis indicates a change point in the mid-1970s, a well-known phenomenon in the region. The prediction rates are significantly worse after 1975. Furthermore. the important region of the Indian Ocean, in terms of SSTs for prediction, moves from the Tropics down toward the Southern Ocean after this date.
    Original languageEnglish
    Pages (from-to)772-781
    JournalJournal of Climate
    Volume18
    DOIs
    Publication statusPublished - 2005

    Fingerprint

    sea surface temperature
    rainfall
    winter
    prediction
    Southern Oscillation
    sea level pressure
    ocean
    rain
    Indian Ocean
    method
    machine learning
    index
    analysis
    rate
    tropics

    Cite this

    Firth, Laura ; Hazelton, M.L. ; Campbell, E.P. / Predicting the Onset of Australian Winter Rainfall by Nonlinear Classification. In: Journal of Climate. 2005 ; Vol. 18. pp. 772-781.
    @article{8748c413ba1144a7a1b27c9a152b2c4e,
    title = "Predicting the Onset of Australian Winter Rainfall by Nonlinear Classification",
    abstract = "A method for predicting the timing of winter rains is presented, making no assumptions about the functional form of any relationships that may exist. Ideas built on classification and regression trees and machine learning are used to develop robust predictive rules. These methods are applied in a case study to predict the timing of winter rain in five farming towns in the southwest of Western Australia. The variables used to construct the model are mean monthly sea Surface temperatures (SSTs) over a 72-cell grid in the Indian Ocean, Perth monthly mean sea level pressure (MSLP), and monthly values of the Southern Oscillation index (SOI). A predictive model is constructed from data over the period 1949-99. This model correctly classifies the onset of the winter rains approximately 80{\%} of the time with SST variables proving to be the most important in deriving the predictions. Further analysis indicates a change point in the mid-1970s, a well-known phenomenon in the region. The prediction rates are significantly worse after 1975. Furthermore. the important region of the Indian Ocean, in terms of SSTs for prediction, moves from the Tropics down toward the Southern Ocean after this date.",
    author = "Laura Firth and M.L. Hazelton and E.P. Campbell",
    year = "2005",
    doi = "10.1175/JCLI-3291.1",
    language = "English",
    volume = "18",
    pages = "772--781",
    journal = "Journal of Climate",
    issn = "0894-8755",
    publisher = "American Meteorological Society",

    }

    Predicting the Onset of Australian Winter Rainfall by Nonlinear Classification. / Firth, Laura; Hazelton, M.L.; Campbell, E.P.

    In: Journal of Climate, Vol. 18, 2005, p. 772-781.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Predicting the Onset of Australian Winter Rainfall by Nonlinear Classification

    AU - Firth, Laura

    AU - Hazelton, M.L.

    AU - Campbell, E.P.

    PY - 2005

    Y1 - 2005

    N2 - A method for predicting the timing of winter rains is presented, making no assumptions about the functional form of any relationships that may exist. Ideas built on classification and regression trees and machine learning are used to develop robust predictive rules. These methods are applied in a case study to predict the timing of winter rain in five farming towns in the southwest of Western Australia. The variables used to construct the model are mean monthly sea Surface temperatures (SSTs) over a 72-cell grid in the Indian Ocean, Perth monthly mean sea level pressure (MSLP), and monthly values of the Southern Oscillation index (SOI). A predictive model is constructed from data over the period 1949-99. This model correctly classifies the onset of the winter rains approximately 80% of the time with SST variables proving to be the most important in deriving the predictions. Further analysis indicates a change point in the mid-1970s, a well-known phenomenon in the region. The prediction rates are significantly worse after 1975. Furthermore. the important region of the Indian Ocean, in terms of SSTs for prediction, moves from the Tropics down toward the Southern Ocean after this date.

    AB - A method for predicting the timing of winter rains is presented, making no assumptions about the functional form of any relationships that may exist. Ideas built on classification and regression trees and machine learning are used to develop robust predictive rules. These methods are applied in a case study to predict the timing of winter rain in five farming towns in the southwest of Western Australia. The variables used to construct the model are mean monthly sea Surface temperatures (SSTs) over a 72-cell grid in the Indian Ocean, Perth monthly mean sea level pressure (MSLP), and monthly values of the Southern Oscillation index (SOI). A predictive model is constructed from data over the period 1949-99. This model correctly classifies the onset of the winter rains approximately 80% of the time with SST variables proving to be the most important in deriving the predictions. Further analysis indicates a change point in the mid-1970s, a well-known phenomenon in the region. The prediction rates are significantly worse after 1975. Furthermore. the important region of the Indian Ocean, in terms of SSTs for prediction, moves from the Tropics down toward the Southern Ocean after this date.

    U2 - 10.1175/JCLI-3291.1

    DO - 10.1175/JCLI-3291.1

    M3 - Article

    VL - 18

    SP - 772

    EP - 781

    JO - Journal of Climate

    JF - Journal of Climate

    SN - 0894-8755

    ER -