[01] Mohmed Abdallah Mohmed Abdalhi, Hydrology and Water Resources Department, Hohai University, Nanjing City, People’s Republic of China; Department of Agricultural Engineering, Faculty of Agricultural Technology and Fish Sciences, Al-Neelain University, Khartoum, Sudan. [02] Zhang Jingyi, Hydrology and Water Resources Department, Hohai University, Nanjing City, People’s Republic of China. [03] Osama Osman Ali, Department of Agricultural Engineering, Faculty of Agricultural Technology and Fish Sciences, Al-Neelain University, Khartoum, Sudan.

Artificial neural networks (ANNs) are Soft computing models usually used to emulate the processes of the human nervous system in order to reach successful solutions for the complicated problems in the various fields of sciences and recently, have been widely applied in hydrological modeling. In this study, an ANN was used to model the rainfall-runoff relationship, precisely, to forecast daily runoff as a function of daily precipitation, and self-adjust training was done to produce consistent response with observed outputs. Eight years of input data were divided into two sets as three years (1992-1994) for calibration/training and five years (1995-1999) for validation/testing, collected from catchment located Longyan - China. The two data sets were used to minimize the error and avoiding the overtrained of ANN employed. The ANN rainfall-runoff model assessed and compared with results obtained using existing techniques including coefficient of determination (R²) and error in volume (VE) as simple linear (black box) model. As an expected for the data used in training and testing, a good matching is obtained in the present case between observed runoff and those computed by ANN model. The obtained results of R² and VE prove a success and optimality of ANN model to predict the study catchment runoff from rainfall observed data with fairly high precision performance.

Artificial Neural Network, Catchment, Calibration, Validation, Linear Model, Rainfall-runoff Modeling

[01] Wang, J., Shi, P., Jiang, P., Hu, J., Qu, S., Chen, X., Chen, Y., Dai, Y. and Xiao, Z., 2017. Application of BP neural network algorithm in traditional hydrological model for flood forecasting. Water, 9 (1), p. 48. [02] Hu, C., Wu, Q., Li, H., Jian, S., Li, N. and Lou, Z., 2018. Deep learning with a long short-term memory networks approach for rainfall-runoff simulation. Water, 10 (11), p. 1543. [03] Adamowski, J., Chan, H. F., Prasher, S. O. and Sharda, V. N., 2012. Comparison of multivariate adaptive regression splines with coupled wavelet transform artificial neural networks for runoff forecasting in Himalayan micro-watersheds with limited data. Journal of Hydroinformatics, 14 (3), pp. 731-744. [04] Poul, A. K., Shourian, M. and Ebrahimi, H., 2019. A comparative study of MLR, KNN, ANN and ANFIS models with wavelet transform in monthly stream flow prediction. Water Resources Management, 33 (8), pp. 2907-2923. [05] Cheng, C., Sa-Ngasoongsong, A., Beyca, O., Le, T., Yang, H., Kong, Z. and Bukkapatnam, S. T., 2015. Time series forecasting for nonlinear and non-stationary processes: A review and comparative study. Iie Transactions, 47 (10), pp. 1053-1071. [06] Shamseldin, A. Y., O'Connor, K. M. and Liang, G. C., 1997. Methods for combining the outputs of different rainfall–runoff models. Journal of Hydrology, 197 (1-4), pp. 203-229. [07] Barão, S. M. M., 2008. Linear and Non-linear time series analysis: forecasting financial markets (Doctoral dissertation). [08] Dar, A. Q., Tabbassum, R. and Faisal, S., 2015. Using Artificial Neural Network for real-time flood prediction in river Jhelum, J&K, India''. Elixir Civil Engg, 82, pp. 32710-32713. [09] ASCE Task Committee on Application of the Artificial Neural Networks in Hydrology, 2000a. Artificial neural networks in hydrology I: preliminary concepts. J. Hydrol. Engng, ASCE 5 (2), 115–123. [10] ASCE Task Committee on Application of the Artificial Neural Networks in Hydrology, 2000b. Artificial neural networks in hydrology II: hydrologic applications. J. Hydrol. Engng, ASCE 5 (2), 124–137. [11] Imrie, C. E., Durucan, S. and Korre, A., 2000. River flow prediction using artificial neural networks: generalisation beyond the calibration range. Journal of hydrology, 233 (1-4), pp. 138-153. [12] Rajurkar, M. P., Kothyari, U. C. and Chaube, U. C., 2004. Modeling of the daily rainfall-runoff relationship with artificial neural network. Journal of Hydrology, 285 (1-4), pp. 96-113. [13] Try, S., Tanaka, S., Tanaka, K., Sayama, T., Oeurng, C., Uk, S., Takara, K., Hu, M. and Han, D., 2020. Comparison of gridded precipitation datasets for rainfall-runoff and inundation modeling in the Mekong River Basin. PloS one, 15 (1), p.e0226814. [14] Kalteh, A. M., 2008. Rainfall-runoff modelling using artificial neural networks (ANNs): modelling and understanding, 53-58. [15] Jimeno-Sáez, P., Senent-Aparicio, J., Pérez-Sánchez, J. and Pulido-Velazquez, D., 2018. A Comparison of SWAT and ANN models for daily runoff simulation in different climatic zones of Peninsular Spain. Water, 10 (2), p. 192.