Comparing machine-learning-based black box techniques and white box models to predict rainfall-runoff in a northern area of Iraq, the Little Khabur River

The rainfall-runoff process is one of the most complex hydrological phenomena. Estimating runoff in the basin is one of the main conditions for planning and optimal use of rainfall. Using machine learning models in various sciences to investigate phenomena for which statistical information is available is a helpful tool. This study investigates and compares the abilities of HEC-HMS and TOPMODEL as white box models and adaptive neural fuzzy inference system (ANFIS) and gene expression programming (GEP) as black box models in rainfall-runoff simulation using 5-year statistical data. Using the inputs of rainfall and temperature of the previous day and discharge in the steps of the previous 2 days reduced the prediction error of both models. Examining the role of different parameters in improving the accuracy of simulations showed that the temperature as an effective parameter in cold months reduces the amount of prediction error. A comparison of R-2, RMSE, and MBE showed that black box models are more effective forecasting tools. Among the black box models, the ANFIS model with R-2 = 0.82 has performed better than the GEP model with R-2 = 0.76. For white box models, the HEC-HMS and TOPMODEL had R-2 equal to 0.3 and 0.25, respectively.

Automated summary

This study compares the abilities of four models in rainfall-runoff simulation and finds that black box models are more effective than white box models. Among them, the ANFIS model performs the best with the highest accuracy.