Simulated annealing coupled with a Naive Bayes model and base flow separation for streamflow simulation in a snow dominated basin


TONGAL H. , Booij M. J.

STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT, 2022 (Journal Indexed in SCI) identifier identifier

  • Publication Type: Article / Article
  • Publication Date: 2022
  • Doi Number: 10.1007/s00477-022-02276-1
  • Title of Journal : STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
  • Keywords: Streamflow simulation, Simulated annealing, Base flow separation, Long short-term memory, Artificial neural network, ARTIFICIAL NEURAL-NETWORK, MACHINE LEARNING-METHODS, SUPPORT VECTOR MACHINES, FUZZY INFERENCE SYSTEM, CLIMATE-CHANGE, HYDROLOGICAL SIMULATION, RUNOFF SIMULATIONS, GROUNDWATER LEVELS, FEATURE-SELECTION, TIME-SERIES

Abstract

Streamflow simulation in a snow dominated basin is complex due to the presence of a high number of interrelated hydrological processes. This complexity is affected by the delayed responses of the catchment to snow accumulation and snow melting processes. In this study, long short-term memory (LSTM) and artificial neural network (ANN) models were utilized for rainfall-runoff simulation in a snow dominated basin, the Carson River basin in the United States (US). The input structure of the models was determined using the simulated annealing algorithm with a naive Bayes model from a high dimensional feature space to represent the long-term impacts of historical events (i.e. the hysteresis effect) on current observations. Further, to represent the different responses of the catchment in the model structure, a base flow separation method was included in the simulation framework. The obtained performance indices, root mean square error, percentage bias, Nash-Sutcliffe and Kling-Gupta efficiencies are 0.331 m(3) s(-1), 13.00%, 0.848, and 0.852 for the ANN model and 0.235 m(3) s(-1), - 0.80%, 0.923, and 0.934 for the LSTM model, respectively. The proposed methodology was found to be promising for improving the streamflow simulation capability of LSTM and ANN models by only considering precipitation, temperature, and potential evapotranspiration as input variables. Analysing the flow duration curves indicated that the LSTM model is more efficient in representing different flow dynamics within the basin due to embedded cell states. Further, the uncertainty and reliability analyses were conducted by using expanded uncertainty (U-95), reliability, and resilience indices. The obtained U-95, reliability and resilience indices are 1.78-1.72 m(3) s(-1), 31.28-66.67% and 11.58-38.27% for the ANN and LSTM models, respectively, showed that the LSTM model produced less uncertainty and is more reliable. However, while lacking a memory component, the proposed methodology significantly contributes to the simulation capability of the ANN model in rainfall-runoff modelling. The results of this study indicated that the proposed methodology could enhance the learning capabilities of machine learning models in rainfall-runoff simulation.