A Novel Interannual Rainfall Runoff Equation Derived from Ol'Dekop's Model Using Artificial Neural Networks

In water resources management, modeling water balance factors is necessary to control dams, agriculture, irrigation, and also to provide water supply for drinking and industries. Generally, conceptual and physical models present challenges to find more hydro-climatic parameters, which show good performance in the assessment of runoff in different climatic regions. Accordingly, a dynamic and reliable model is proposed to estimate inter-annual rainfall-runoff in five climatic regions of northern Algeria. This is a new improvement of Ol'Dekop's equation, which models the residual values obtained between real and predicted data using artificial neuron networks (ANN(s)), namely by ANN(1) and ANN(2) sub-models. In this work, a set of climatic and geographical variables, obtained from 16 basins, which are inter-annual rainfall (IAR), watershed area (S), and watercourse (WC), were used as input data in the first model. Further, the ANN(1) output results and De Martonne index (I) were classified, and were then processed by ANN(2) to further increase reliability, and make the model more dynamic and unaffected by the climatic characteristic of the area. The final model proved the best performance in the entire region compared to a set of parametric and non-parametric water balance models used in this study, where the R-Adj(2) obtained from each test gave values between 0.9103 and 0.9923.

Automated summary

Modeling water balance factors is necessary in water resources management. This study proposes a dynamic and reliable model using artificial neuron networks (ANNs) to estimate inter-annual rainfall-runoff in different climatic regions. The model shows better performance compared to other water balance models in the region.