Regionalization of hydrological model parameters using gradient boosting machine

Abstract

Abstract. The regionalization of hydrological model parameters is key to hydrological predictions in ungauged basins. The commonly used multiple linear regression (MLR) method may not be applicable in complex and nonlinear relationships between model parameters and watershed properties. Moreover, most regionalization methods assume lumped parameters for each catchment without considering within-catchment heterogeneity. Here we incorporated the Penman–Monteith–Leuning (PML) equation into the Distributed Time Variant Gain Model (DTVGM) to improve the mechanistic representation of the evapotranspiration (ET) process. We calibrated six key model parameters, grid by grid across China, using a multivariable calibration strategy which incorporates spatiotemporal runoff and ET datasets (0.25∘; monthly) as reference. In addition, we used the gradient boosting machine (GBM), a machine learning technique, to portray the dependence of model parameters on soil and terrain attributes in four distinct climatic zones across China. We show that the modified DTVGM could reasonably estimate the runoff and ET over China using the calibrated parameters but performed better in humid rather than arid regions for the validation period. The regionalized parameters by the GBM method exhibited better spatial coherence relative to the calibrated grid-by-grid parameters. In addition, GBM outperformed the stepwise MLR method in both parameter regionalization and gridded runoff simulations at a national scale, though the improvement pertaining to watershed streamflow validation is not significant due to most of the watersheds being located in humid regions. We also revealed that the slope, saturated soil moisture content, and elevation are the most important explanatory variables to inform model parameters based on the GBM approach. The machine-learning-based regionalization approach provides an effective alternative to deriving hydrological model parameters from watershed properties, particularly in ungauged regions.

Multi-Model Comparison in the Attribution of Runoff Variation across a Humid Region of Southern China

“…Moreover, this model has a relatively parsimonious model structure and limited free parameters to describe the rainfall-runoff processes. Consequently, the DTVGM model has demonstrated successful applications in many basins in China with satisfactory results [31][32][33][34]. Therefore, this model was selected to simulate streamflow process of the GRB.…”

Advanced Machine Learning Techniques to Improve Hydrological Prediction: A Comparative Analysis of Streamflow Prediction Models

“…It has been applied to streamflow forecasting to better capture interactions between different hydrological factors [51,52]. In streamflow forecasting, gradient boosting machines (GBMs) like the extreme gradient boosting regression model (XGBoost) [53] and LGBM [54] have grown in popularity. They focus on samples with large prediction errors and repeatedly incorporate weak models to produce a strong predictive model.…”

Regional Flood Frequency Analysis of Northern Iran

“…This step is the most challenging but important step in regional flood frequency analysis. Various regionalization techniques have been developed by researchers for the determination of homogeneous regions [7,[13][14][15][16][17][18][19][20][21]. Hierarchical Agglomerative Clustering has become a popular tool for regional distribution identification, and testing of outlier stations [22][23][24][25][26][27].…”