A Robust Strategy to Account for Data Sampling Variability in the Development of Hydrological Models. Issue 3 (1st March 2023)

• Record Type: Journal Article
• Authors: Zheng, Feifei; Chen, Junyi; Ma, Yiyi; Chen, Qiuwen; Maier, Holger R.; Gupta, Hoshin
• Is Part Of: Water resources research. Volume 59:Issue 3(2023)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2023-03-01
• Subjects: data sampling variability -- hydrological model -- uncertainty analysis -- stochastic gradient descent -- model calibration; Hydrology -- Periodicals; 333.91
• DOI: 10.1029/2022WR033703
• Languages: English
• ISSNs: 0043-1397

Abstract

Abstract: It is typical to use a single portion of the available data to calibrate hydrological models, and the remainder for model evaluation. To minimize model‐bias, this partitioning must be performed so as to ensure distributional representativeness and mutual consistency. However, failure to account for data sampling variability (DSV) in the underlying Data Generating Process can weaken the model's generalization performance. While " K‐fold cross‐validation " can mitigate this problem, it is computationally inefficient since the calibration/evaluation operations must be repeated numerous times. This paper develops a general strategy for stochastic evolutionary parameter optimization (SEPO) that explicitly accounts for DSV when calibrating a model using any population‐based evolutionary optimization algorithm (EOA), such as Shuffled Complex Evolution (SCE). Inspired in part by the machine‐learning strategy of stochastic gradient descent (SGD), we use various representative random sub‐samples to drive the EOA toward the distribution of the model parameters. Unlike in SGD, derivative information is not required and hence SEPO can be applied to any hydrological model where such information is not readily available. To demonstrate the effectiveness of the proposed strategy, we implement it within the well‐known SCE, to calibrate the GR4J conceptual rainfall‐runoff model to 163 hydro‐climatically diverse catchments. Using only a single optimization run, our Stochastic SCE method converges to population‐based estimates of model parameter distributions (and corresponding simulation uncertainties), without compromising model performance during either calibration or evaluation. Further, it effectively reduces the need to perform independent evaluation tests of model performance under conditions that are represented by the available data. Key Points: Development of a general strategy for accounting for uncertainty due to data sampling variability in the development of hydrological models Demonstrating an efficient implementation using a modified version of the population‐based Shuffled Complex Evolution optimization algorithm Large sample modeling study to demonstrate robustness of the method and to verify the reasonableness of using all data for calibration