Comparison of artificial neural networks and adaptive neuro-fuzzy inference system for regional flood estimation in Australia

    Research output: Chapter in Book / Conference PaperConference Paperpeer-review

    2 Citations (Scopus)

    Abstract

    ![CDATA[Regional flood frequency analysis (RFFA) involves transfer of flood characteristics from gauged to ungauged catchments. In Australia, RFFA methods generally focus on the application of empirical methods based on linear forms of models such as the Probabilistic Rational Method, the Index Flood Method and the Quantile Regression Technique (QRT). There have been successful applications of non-linear models in RFFA in some other countries such as Artificial Neural Networks (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS). The application of these non-linear RFFA methods in Australia is limited. This study focuses on the application of ANN and ANFIS-based RFFA models to Australian data. Using data from 452 catchments in eastern Australia (a part of Australian Rainfall and Runoff Revision Project 5 regional flood methods database), it has been found that the ANN-based RFFA performs better that the ANFIS and provides quite accurate regional flood quantile estimates. However, the Bayesian Generalised Least Squares based QRT coupled with the Region of Influence approach outperforms both the ANN and ANFIS based RFFA models.]]
    Original languageEnglish
    Title of host publication2012 Hydrology and Water Resources Symposium : 19-22 November 2012, Dockside, Cockle Bay, Sydney, NSW Australia
    PublisherEngineers Australia
    Pages954-961
    Number of pages8
    ISBN (Print)9781922107626
    Publication statusPublished - 2012
    EventHydrology and Water Resources Symposium -
    Duration: 19 Nov 2012 → …

    Conference

    ConferenceHydrology and Water Resources Symposium
    Period19/11/12 → …

    Keywords

    • Australia
    • flood forecasting
    • fuzzy logic
    • neural networks (computer science)

    Fingerprint

    Dive into the research topics of 'Comparison of artificial neural networks and adaptive neuro-fuzzy inference system for regional flood estimation in Australia'. Together they form a unique fingerprint.

    Cite this