Predicting monthly streamflow is essential for hydrological analysis and water resource management. Recent advancements in deep learning, particularly long short-term memory (LSTM) and recurrent neural networks (RNN), exhibit extraordinary efficacy in streamflow forecasting. This study employs RNN and LSTM to construct data-driven streamflow forecasting models. Sensitivity analysis, utilizing the analysis of variance (ANOVA) method, also is crucial for model refinement and identification of critical variables. This study covers monthly streamflow data from 1979 to 2014, employing five distinct model structures to ascertain the most optimal configuration. Application of the models to the Zarrine River basin in northwest Iran, a major sub-basin of Lake Urmia, demonstrates the superior accuracy of the RNN algorithm over LSTM. At the outlet of the basin, quantitative evaluations demonstrate that the RNN model outperforms the LSTM model across all model structures. The S3 model, characterized by its inclusion of all input variable values and a four-month delay, exhibits notably exceptional performance in this aspect. The accuracy measures applicable in this particular context were RMSE (22.8), R² (0.84), and NSE (0.8). This study highlights the Zarrine River’s substantial impact on variations in Lake Urmia’s water level. Furthermore, the ANOVA method demonstrates exceptional performance in discerning the relevance of input factors. ANOVA underscores the key role of station streamflow, upstream station streamflow, and maximum temperature in influencing the model’s output. Notably, the RNN model, surpassing LSTM and traditional artificial neural network (ANN) models, excels in accurately mimicking rainfall–runoff processes. This emphasizes the potential of RNN networks to filter redundant information, distinguishing them as valuable tools in monthly streamflow forecasting.

Precise forecasting of streamflow is crucial for the proper supervision of water resources. The purpose of the present investigation is to predict successive-station streamflow using the Gated Recurrent Unit (GRU) model and to quantify the impact of input information (i.e., precipitation) uncertainty on the GRU model’s prediction using the Generalized Likelihood Uncertainty Estimation (GLUE) computation. The Zarrineh River basin in Lake Urmia, Iran, was nominated as the case study due to the importance of the location and its significant contribution to the lake inflow. Four stations in the basin were considered to predict successive-station streamflow from upstream to downstream. The GRU model yielded highly accurate streamflow prediction in all stations. The future precipitation data generated under the Representative Concentration Pathway (RCP) scenarios were used to estimate the effect of precipitation input uncertainty on streamflow prediction. The p-factor (inside the uncertainty interval) and r-factor (width of the uncertainty interval) indices were used to evaluate the streamflow prediction uncertainty. GLUE predicted reliable uncertainty ranges for all the stations from 0.47 to 0.57 for the r-factor and 61.6% to 89.3% for the p-factor.

Climate change and excessive greenhouse gas emissions profoundly impact hydrological cycles, particularly in arid and semi-arid regions, necessitating assessments of their effects on water resource management, agriculture, soil fertility, nutrient transport, hydropower generation, and flood risk. This study investigates climate change repercussions on streamflow in the Zarrineh River Basin, Iran, across three decadal intervals (2020-2029, 2055-2064, and 2090-2099) aiming to develop effective adaptation and mitigation strategies. Four General Circulation Models (GCMs), chosen based on distinct Representative Concentration Pathways (RCPs) determined by the annual mean temperature gradient, are employed. These models generate daily maximum (Tmax) and minimum (Tmin) temperatures along with precipitation data. Subsequently, these variables are integrated into the Soil and Water Assessment Tool (SWAT) model to analyze river flow alterations for each decadal timeframe. Comparison between future projections and observed climate data reveals a gradual decline in precipitation and Tmax, coupled with a substantial increase in Tmin. The average precipitation diminishes from 0.77 mm in the period 1985-1994 to a range of 0.42-0.28 mm in 2090-2099. The simulated flow at the basin outlet highlights that the GCM with the highest annual mean temperature gradient yields the lowest streamflow, while conversely, the model with the lowest gradient generates the highest. Consequently, streamflow experiences a decline from 52 m³/s in 1985-1994 to a range of 41-20 m³/s in 2090-2099.