Monthly Rainfall-Runoff Modeling at Watershed Scale: A Comparative Study of Data-Driven and Theory-Driven Approaches
Open Access
Abstract
Data-driven machine learning approaches have been rapidly developed in the past 10 to 20 years and applied to various problems in the field of hydrology. To investigate the capability of data-driven approaches in rainfall-runoff modeling in comparison to theory-driven models, we conducted a comparative study of simulated monthly surface runoff at 203 watersheds across the contiguous USA using a conceptual model, the proportionality hydrologic model, and a data-driven Gaussian process regression model. With the same input variables of precipitation and mean monthly aridity index, the two models showed similar performance. We then introduced two more input variables in the data-driven model: potential evaporation and the normalized difference vegetation index (NDVI), which were selected based on hydrologic knowledge. The modified data-driven model performed much better than either the conceptual or original data-driven model. A sensitivity analysis was conducted on all three models tested in this study, which showed that surface runoff responded positively to increased precipitation. However, a confounding effect on surface runoff sensitivity was found among mean monthly aridity index, potential evaporation, and NDVI. This confounding was caused by complex interconnections among energy supply, vegetation coverage, and climate seasonality of the watershed system. We also conducted an uncertainty analysis on the two data-driven models, which showed that both models had reasonable predictability within the 95% confidence interval. With the additional two input variables, the modified data-driven model had lower prediction uncertainty and higher prediction accuracy.Keywords
This publication has 56 references indexed in Scilit:
- Tree‐based iterative input variable selection for hydrological modelingWater Resources Research, 2013
- Similarity of climate control on base flow and perennial stream density in the Budyko frameworkHydrology and Earth System Sciences, 2013
- Assessing the impact of climate variability on catchment water balance and vegetation coverHydrology and Earth System Sciences, 2012
- Prediction of event-based stormwater runoff quantity and quality by ANNs developed using PMI-based input selectionJournal of Hydrology, 2011
- Load or concentration, logged or unlogged? Addressing ten years of uncertainty in neural network suspended sediment predictionHydrological Processes, 2011
- A continuous satellite‐derived global record of land surface evapotranspiration from 1983 to 2006Water Resources Research, 2010
- Model Parameter Estimation Experiment (MOPEX): An overview of science strategy and major results from the second and third workshopsJournal of Hydrology, 2006
- Calibration and validation of neural networks to ensure physically plausible hydrological modelingJournal of Hydrology, 2005
- Input determination for neural network models in water resources applications. Part 1—background and methodologyJournal of Hydrology, 2005
- River flow forecasting through conceptual models part I — A discussion of principlesJournal of Hydrology, 1970