Minimum input variances for modelling rainfall-runoff using ANN
Date
2014Author
Zulkarnain, Hassan
Supiah, Shamsudin, Assoc. Prof.
Sobri, Harun, Prof. Madya Dr.
Metadata
Show full item recordAbstract
This paper presents the study of possible input variances for modeling the long-term runoff series using artificial neural network (ANN). ANN has the ability to derive the relationship between the inputs and outputs of a PROCESS without the physics being provided to it, and it is believed to be more flexible to be used compared to the conceptual models [1]. Data series from the Kurau River sub-catchment was applied to build the ANN networks and the model was calibrated using the input of rainfall, antecedent rainfall, temperature, antecedent temperature and antecedent runoff. In addition, the results were compared with the conceptual model, named IHACRES. The study reveal that ANN and IHACRES can simulate well for mean runoff but ANN gives a remarkable performance compared to IHACRES, if the model customizes with a good configuration.
URI
http://www.jurnalteknologi.utm.my/index.php/jurnalteknologi/article/view/3154http://dspace.unimap.edu.my:80/xmlui/handle/123456789/40074