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

    107 Citations (Scopus)


    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
    Issue number6
    Publication statusPublished - 1996


    • hydraulic conductivity
    • infiltration
    • seepage


    Dive into the research topics of 'Testing an artificial neural network for predicting soil hydraulic conductivity'. Together they form a unique fingerprint.

    Cite this