Testing an artificial neural network for predicting soil hydraulic conductivity

S. Tamari, J.H.M. Wösten, J.C. Ruiz-Suárez

    Research output: Contribution to journalArticleAcademicpeer-review

    93 Citations (Scopus)

    Abstract

    Multilinear regression has been used extensively to predict soil hydraulic properties from easily obtainable soil variables. This study investigated the performance of an artificial radial-basis neural network in predicting K(h) values from other variables. A fitting procedure was used that required only two parameters to ensure a unique solution. With a soil database the neural network was tested in solving multivariate problems. The neural network proved to be more efficient than the multilinear regression for predicting K(h) from two qualitative and five quantitative soil variables. It was also more efficient than two independent multilinear regressions, one for the sandy samples and the other for the loamy and clayey samples.
    Original languageEnglish
    Pages (from-to)1732-1741
    JournalSoil Science Society of America Journal
    Volume60
    Issue number6
    Publication statusPublished - 1996

    Fingerprint

    hydraulic conductivity
    artificial neural network
    neural networks
    soil
    soil hydraulic properties
    testing
    hydraulic property
    sampling

    Keywords

    • hydraulic conductivity
    • infiltration
    • seepage

    Cite this

    @article{67430ecb58504b3f8ea3cd351801d126,
    title = "Testing an artificial neural network for predicting soil hydraulic conductivity",
    abstract = "Multilinear regression has been used extensively to predict soil hydraulic properties from easily obtainable soil variables. This study investigated the performance of an artificial radial-basis neural network in predicting K(h) values from other variables. A fitting procedure was used that required only two parameters to ensure a unique solution. With a soil database the neural network was tested in solving multivariate problems. The neural network proved to be more efficient than the multilinear regression for predicting K(h) from two qualitative and five quantitative soil variables. It was also more efficient than two independent multilinear regressions, one for the sandy samples and the other for the loamy and clayey samples.",
    keywords = "hydraulisch geleidingsvermogen, infiltratie, kwel, hydraulic conductivity, infiltration, seepage",
    author = "S. Tamari and J.H.M. W{\"o}sten and J.C. Ruiz-Su{\'a}rez",
    year = "1996",
    language = "English",
    volume = "60",
    pages = "1732--1741",
    journal = "Soil Science Society of America Journal",
    issn = "0361-5995",
    publisher = "Soil Science Society of America",
    number = "6",

    }

    Testing an artificial neural network for predicting soil hydraulic conductivity. / Tamari, S.; Wösten, J.H.M.; Ruiz-Suárez, J.C.

    In: Soil Science Society of America Journal, Vol. 60, No. 6, 1996, p. 1732-1741.

    Research output: Contribution to journalArticleAcademicpeer-review

    TY - JOUR

    T1 - Testing an artificial neural network for predicting soil hydraulic conductivity

    AU - Tamari, S.

    AU - Wösten, J.H.M.

    AU - Ruiz-Suárez, J.C.

    PY - 1996

    Y1 - 1996

    N2 - Multilinear regression has been used extensively to predict soil hydraulic properties from easily obtainable soil variables. This study investigated the performance of an artificial radial-basis neural network in predicting K(h) values from other variables. A fitting procedure was used that required only two parameters to ensure a unique solution. With a soil database the neural network was tested in solving multivariate problems. The neural network proved to be more efficient than the multilinear regression for predicting K(h) from two qualitative and five quantitative soil variables. It was also more efficient than two independent multilinear regressions, one for the sandy samples and the other for the loamy and clayey samples.

    AB - Multilinear regression has been used extensively to predict soil hydraulic properties from easily obtainable soil variables. This study investigated the performance of an artificial radial-basis neural network in predicting K(h) values from other variables. A fitting procedure was used that required only two parameters to ensure a unique solution. With a soil database the neural network was tested in solving multivariate problems. The neural network proved to be more efficient than the multilinear regression for predicting K(h) from two qualitative and five quantitative soil variables. It was also more efficient than two independent multilinear regressions, one for the sandy samples and the other for the loamy and clayey samples.

    KW - hydraulisch geleidingsvermogen

    KW - infiltratie

    KW - kwel

    KW - hydraulic conductivity

    KW - infiltration

    KW - seepage

    M3 - Article

    VL - 60

    SP - 1732

    EP - 1741

    JO - Soil Science Society of America Journal

    JF - Soil Science Society of America Journal

    SN - 0361-5995

    IS - 6

    ER -