Coupled machine learning and the limits of acceptability approach applied in parameter identification for a distributed hydrological model

Abstract

Abstract. Monte Carlo (MC) methods have been widely used in uncertainty analysis and parameter identification for hydrological models. The main challenge with these approaches is, however, the prohibitive number of model runs required to get an adequate sample size which may take from days to months especially when the simulations are run in distributed mode. In the past, emulators have been used to minimize the computational burden of the MC simulation through direct estimation of the residual based response surfaces. Here, we apply emulators of MC simulation in parameter identification for a distributed conceptual hydrological model using two likelihood measures, i.e. the absolute bias of model predictions (Score) and another based on the time relaxed limits of acceptability concept (pLoA). Three machine learning models (MLMs) were built using model parameter sets and response surfaces with limited number of model realizations (4000). The developed MLMs were applied to predict pLoA and Score for a large set of model parameters (95 000). The behavioural parameter sets were identified using a time relaxed limits of acceptability approach based on the predicted pLoA values; and applied to estimate the quantile streamflow predictions weighted by their respective Score. The three MLMs were able to adequately mimic the response surfaces directly estimated from MC simulations; and the models identified using the coupled ML emulators and the limits of acceptability approach have performed very well in reproducing the median streamflow prediction both during the calibration and validation periods.

Feature importance measures to dissect the role of sub-basins in shaping the catchment hydrological response: a proof of concept

“…2). The hyperparameters of a single layer neural network are the number of units in the hidden layer (size) and the regularization parameter to avoid over-fitting (decay) (Teweldebrhan et al 2020).…”

Feature importance measures to dissect the role of sub-basins in shaping the catchment hydrological response: a proof of concept

“…Specifically, we have 2). The hyperparameters of a single layer neural network are the number of units in the hidden layer (size) and the regularization parameter to avoid over-fitting (decay) (Teweldebrhan et al, 2020). In order to achieve a high performance of the ML models, we combine hyperparameter tuning and cross validation.…”

Using a long short-term memory (LSTM) neural network to boost river streamflow forecasts over the western United States

“…If the model calibration of a physical model is aided by ma-chine learning is this process included in the definition of a hybrid system (e.g. Teweldebrhan et al, 2020)? Would deeplearning-based quality control of observations be included within a hybrid system (e.g.…”