Possibility Of Hydrological Grouping Of Geological Formations By Neural Network In Sefidrood Basin
2006
Rezaei, A., Instructor of Agriculture and Natural Resources Research Center of Zanjan. | Mahdavi, M., Prof. Of Tehran University. | Feiznia, S., Prof. Of Tehran University. | Lucas, C., Prof. Of Tehran University. | Mahdian, M., Assi. Prof. Of Soil Conservation and Watershed Management Institute.
The Geological formations and Rock Units (GFRUs) of 12 sub - basins in south zone of Sefidrood basin have been classified to four or some combination of them by inspiration of four soil hydrologic groups and measured their occupied area. The 628 hydrographs have been selected for training and 54 other for testing and their similar daily flooding rainfall and five days antecedent rainfall depths were extracted and runoff depths was calculated. The relations among runoff depths with sub basins areas, daily flooding rainfall depths, five days antecedent rainfall depths and percent occupied by any of Geological Formations units (GFRUs) have been modeled based on Multiple Linear Regression (MLR) and Artificial Perceptron Neural Networks (APNN). The results show significance differences among (GFRUs) at error level of %1 and occasionally %5 for producing of runoff based on (APNN) and (MLR). The rainfalls depths have been simulated by (APNN) with stabilize of all entrances exclusive of rainfall depths and hypothesis of sub basins area was occupied only by one type of (GFRUs). The conclusion states that there are some chaos hydrologic behaviors and vague borders among (GFRUs) and will better to decline number of hydrologic groups to three and changing the form of complexity of them.
Afficher plus [+] Moins [-]Mots clés AGROVOC
Informations bibliographiques
Cette notice bibliographique a été fournie par Agricultural Research and Education Organization
Découvrez la collection de ce fournisseur de données dans AGRIS