Developing a novel layer network structure for a LSTM model to predict mean monthly river streamflow

Abstract

In this research, novel innovative DDN layer network structures by hybridizing double-LSTM model with an addition layer (+) (i.e., 2LSTM and 2LSTM + layer network models) are developed purposefully to enhance prediction performance of the mean monthly Maroon River streamflow (MRSFm) in Iran from October 1987 to September 2017. For doing so, to select the most effective parameters on MRSFm, the Pearson's correlation coefficient (PCC) and Cosine amplitude sensitivity (CAS) as features selection process are carried out for potential meteorological variables in the study area (i.e., average monthly temperature (Tm), evaporation (ETm), and precipitation (Pm)) and target (MRSFm). The results show that Tm and ETm have an insignificant influence on MRSFm, thus, only Pm is used as the most effective input variable in predicting MRSFm. Due to a well-balanced network model's structural outline in the suggested novel hybrid 2LSTM + model, it accordingly yields to a suitable total learnable parameter (TLP) compared to ordinary standalone LSTM and GRU as the benchmark models developed in the similar meta-parameters. This model under the optimal meant meta-parameters tuned i.e., state activation functions (SAF) = tanh-softsign, numbers of hidden neurons (NHN) = 75, dropout rate (P-rate) = 0.5, performs best among the models with an R2 of 0.68, NSE of 0.63, PBIAS of 41%, KGE of 0.79, and RMSE of 19.24 m3/s. Comparatively, a standard gated recurrent units (GRU) and LSTM as benchmark models using the optimal scenario generate the following results: R2 are 0.57 and 0.67, NSE are 0.53 and 0.61, PBIAS are 109 and 49%, KGE are 0.63 and 0.79, and RMSE are 21.11 and 19.32 m3/s, respectively. Generally, in all models, in the equal NHN, rising P-rate value reduces convergence time.