Streamflow Prediction Research Articles

Enhancing hydrological modeling with transformers: a case study for 24-h streamflow prediction.

In this paper, we address the critical task of 24-h streamflow forecasting using advanced deep-learning models, with a primary focus on the transformer architecture which has seen limited application in this specific task. We compare the performance of five different models, including persistence, long short-term memory (LSTM), Seq2Seq, GRU, and transformer, across four distinct regions. The evaluation is based on three performance metrics: Nash-Sutcliffe Efficiency (NSE), Pearson's r, and normalized root mean square error (NRMSE). Additionally, we investigate the impact of two data extension methods: zero-padding and persistence, on the model's predictive capabilities. Our findings highlight the transformer's superiority in capturing complex temporal dependencies and patterns in the streamflow data, outperforming all other models in terms of both accuracy and reliability. Specifically, the transformer model demonstrated a substantial improvement in NSE scores by up to 20% compared to other models. The study's insights emphasize the significance of leveraging advanced deep learning techniques, such as the transformer, in hydrological modeling and streamflow forecasting for effective water resource management and flood prediction.

Improving the probabilistic drought prediction with soil moisture information under the ensemble streamflow prediction framework

Reliable drought prediction should be preceded to prevent damage from potential droughts. In this context, this study developed a hydrological drought prediction method, namely ensemble drought prediction (EDP) to reflect drought-related information under the ensemble streamflow prediction framework. After generating an ensemble of standardized runoff index by converting the ensemble of generated streamflow, the results were adopted as the prior distribution. Then, precipitation forecast and soil moisture were used to update the prior EDP. The EDP + A model included the precipitation forecast with the PDF-ratio method, and the observed soil moisture index was reflected in the former EDP and EDP + A via Bayes’ theorem, resulting in the EDP + S and EDP + AS models. Eight basins in Korea with more than 30 years of observation data were applied with the proposed methodology. As a result, the overall performance of the four EDP models yielded improved results than the climatological prediction. Moreover, reflecting soil moisture yielded improved evaluation metrics during short-term drought predictions, and in basins with larger drainage areas. Finally, the methodology presented in this study was more effective during periods with less intertemporal variabilities.

A multi-model evaluation of probabilistic streamflow predictions via residual error modelling

Probabilistic streamflow predictions are valuable tools for predictive uncertainty estimation, hydrologic risk management, and support for decision-making in water resources. Usually, predictive uncertainty quantification is developed and assessed using only a single hydrological model, making it difficult to generalize to other model configurations. To tackle this issue, we assess changes in the model performance ranking of diverse streamflow models by applying a residual error model post-processing approach to multiple basins and multiple models. This assessment employed 141 basins from the Great Lakes watershed covering the USA and Canada, and 13 diverse streamflow models, which are evaluated using deterministic and probabilistic performance metrics. As the first study to implement probabilistic methods to diverse streamflow models applied to a multitude of basins, the analysis here examines the dependence of probabilistic streamflow estimation quality on model quality. Our findings show that streamflow model choice influences the robustness of probabilistic predictions. It was found that moving from deterministic to probabilistic predictions using a post-processing approach does not change the streamflow model performance ranking for the best and worst deterministic models, but models of intermediate rank in deterministic evaluation do not have consistent ranking when evaluated in probabilistic mode. Post-processing residual errors of long short-term memory (LSTM) network models are consistently the best-performing model in terms of deterministic and probabilistic metrics. This study highlights the significance of combining deterministic streamflow model predictions with residual error models for improving the quality and increasing the value of hydrological predictions, quantifying uncertainty, and facilitating decision-making in operational water management. It also clarifies the degree to which probabilistic predictions depend upon good model performance and can compensate for poor model performance.

Deep Learning Approaches for Stream Flow and Peak Flow Prediction: A Comparative Study

Stream flow prediction is crucial for effective water resource management, flood prevention, and environmental planning. This study investigates the performance of various deep neural network architectures, including LSTM, biLSTM, GRU, and biGRU models, in stream flow and peak stream flow predictions. Traditional methods for stream flow forecasting have relied on hydrological models and statistical techniques, but recent advancements in machine learning and deep learning have shown promising results in improving prediction accuracy. The study compares the performance of the models using comprehensive evaluations with 1-6 input steps for both general stream flow and peak stream flow predictions. Additionally, a detailed analysis is conducted specifically for the biLSTM model, which demonstrated high performance results. The biLSTM model is evaluated for 1-4 ahead forecasting, providing insights into its specific strengths and capabilities in capturing the dynamics of stream flow. Results show that the biLSTM model outperforms other models in terms of prediction accuracy, especially for peak stream flow forecasting. Scatter plots illustrating the forecasting performances of the models further demonstrate the effectiveness of the biLSTM model in capturing temporal dependencies and nonlinear patterns in stream flow data. This study contributes to the literature by evaluating and comparing the performance of deep neural network models for general and peak stream flow prediction, highlighting the effectiveness of the biLSTM model in improving the accuracy and reliability of stream flow forecasts.

Ensemble Forecasts of Extreme Flood Events with Weather Forecasts, Land Surface Modeling and Deep Learning

Integrating numerical weather forecasts that provide ensemble precipitation forecasts, land surface hydrological modeling that resolves surface and subsurface hydrological processes, and artificial intelligence techniques that correct the forecast bias, known as the “meteo-hydro-AI” approach, has emerged as a popular flood forecast method. However, its performance during extreme flood events across different interval basins has received less attention. Here, we evaluated the meteo-hydro-AI approach for forecasting extreme flood events from headwater to downstream sub-basins in the Luo River basin during 2010–2017, with forecast lead times up to 7 days. The proposed meteo-hydro approach based on ECMWF weather forecasts and the Conjunctive Surface-Subsurface Process version 2 land surface model with a spatial resolution of 1 km captured the flood hydrographs quite well. Compared with the ensemble streamflow prediction (ESP) approach based on initial conditions, the meteo-hydro approach increased the Nash-Sutcliffe efficiency of streamflow forecasts at the three outlet stations by 0.27–0.82, decreased the root-mean-squared-error by 22–49%, and performed better in reliability and discrimination. The meteo-hydro-AI approach showed marginal improvement, which suggested further evaluations with larger samples of extreme flood events should be carried out. This study demonstrated the potential of the integrated meteo-hydro-AI approach for ensemble forecasting of extreme flood events.

A hybrid deep learning approach for streamflow prediction utilizing watershed memory and process-based modeling

Abstract Accurate streamflow prediction is essential for optimal water management and disaster preparedness. While data-driven methods’ performance often surpasses process-based models, concerns regarding their ‘black-box’ nature persist. Hybrid models, integrating domain knowledge and process modeling into a data-driven framework, offer enhanced streamflow prediction capabilities. This study investigated watershed memory and process modeling-based hybridizing approaches across diverse hydrological regimes – Korean and Ethiopian watersheds. Following watershed memory analysis, the Soil and Water Assessment Tool (SWAT) was calibrated using the recession constant and other relevant parameters. Three hybrid models, incorporating watershed memory and residual error, were developed and evaluated against standalone long short-term memory (LSTM) models. Hybrids outperformed the standalone LSTM across all watersheds. The memory-based approach exhibited superior and consistent performance across training, evaluation periods, and regions, achieving 17–66% Nash–Sutcliffe efficiency coefficient improvement. The residual error-based technique showed varying performance across regions. While hybrids improved extreme event predictions, particularly peak flows, all models struggled at low flow. Korean watersheds’ significant prediction improvements highlight the hybrid models’ effectiveness in regions with pronounced temporal hydrological variability. This study underscores the importance of selecting a specific hybrid approach based on the desired objectives rather than solely relying on statistical metrics that often reflect average performance.

Fair Graph Learning Using Constraint-Aware Priority Adjustment and Graph Masking in River Networks

Accurate prediction of water quality and quantity is crucial for sustainable development and human well-being. However, existing data-driven methods often suffer from spatial biases in model performance due to heterogeneous data, limited observations, and noisy sensor data. To overcome these challenges, we propose Fair-Graph, a novel graph-based recurrent neural network that leverages interrelated knowledge from multiple rivers to predict water flow and temperature within large-scale stream networks. Additionally, we introduce node-specific graph masks for information aggregation and adaptation to enhance prediction over heterogeneous river segments. To reduce performance disparities across river segments, we introduce a centralized coordination strategy that adjusts training priorities for segments. We evaluate the prediction of water temperature within the Delaware River Basin, and the prediction of streamflow using simulated data from U.S. National Water Model in the Houston River network. The results showcase improvements in predictive performance and highlight the proposed model's ability to maintain spatial fairness over different river segments.

Applicability of seasonal forecasts from dynamical models for reservoir management practices

Despite the availability of reliable seasonal forecasts of Indian Summer Monsoon Rainfall (ISMR), the use of dynamical models driven by these forecasts for reservoir level management is limited. Reservoir water management can specially be useful if it can be done several months in advance, in view of an impending drought/flood scenario. The applicability of seasonal forecasts from the Monsoon Mission (MM) seasonal forecast model for seasonal and monthly inflow forecasts for tropical Indian reservoirs (Mula and Kangsabati) is studied using the Soil and Water Assessment Tool (SWAT) hydrological model, at a lead time of 3 months. Long-term observed inflow datasets are used for calibration and validation of SWAT-Calibration and Uncertainty Procedure (CUP) with Sequential Uncertainty Fitting (SUFI)-2 algorithm using insitumeteorological data. Observed inflows and inflow simulations are compared with simulated inflow using SWAT with same calibrated parameters, but with forcing derived from reforecasts from the MM model. The SWAT-CUP calibrated well with reasonable Nash Sutcliffe Efficiency (NSE) (Mula = 0.75, Kangsabati = 0.79) and Percentage Bias (PBIAS) (Mula = -28%, Kangsabati = 17%) for both reservoirs. The skill scores for streamflow predictions vary from 0.6-0.70 during the monsoon season, indicating reasonable accuracy for these predictions. The SWAT-MM model has a reasonable skill with 0.52-0.53 NSE and 26%-40% PBIAS. Therefore, SWAT-MM-based model has a good potential to forecast monthly and seasonal reservoir inflow for various agro-climatic zones of India. These forecasts when used in real-time, can serve as a guideline for managing the reservoir storage and release, and hence proving to be of great socio-economic importance.

Coupling the remote sensing data-enhanced SWAT model with the bidirectional long short-term memory model to improve daily streamflow simulations

Global climate change has led to an increase in the frequency and scale of extreme weather events worldwide, and there is an urgent need to develop better-performing hydrological models to improve the accuracy of streamflow simulations and to facilitate water resource planning and management. The Soil and Water Assessment Tool (SWAT) has a notable physical foundation and is widely used in hydrological research. However, it uses a simplified vegetation growth model, introducing uncertainty into the simulation results. This study focused on improving the model based on remotely sensed phenological and leaf area index (LAI) data. Phenological data were used to define vegetation dormancy, and the LAI data replaced the corresponding data simulated by the original model. This approach improved the accuracy of the model in describing vegetation dynamics. Then, the enhanced SWAT model was coupled with the bidirectional long short-term memory (BiLSTM) model to validate the simulation of hydrological processes upstream of the Hei River. During model validation, the performance of the enhanced SWAT model in simulating streamflow (R2 = 0.835, NSE = 0.819) was better than that of the original SWAT model (R2 = 0.821, NSE = 0.805). In terms of simulating evapotranspiration, the enhanced SWAT model demonstrated even greater advantages. During the verification period, compared to those of the SWAT model, the R2 and NSE values of the enhanced SWAT model for daily-scale simulations increased from 0.196 and −0.269 to 0.777 and 0.732, respectively. The R2 and NSE values for monthly-scale simulations increased from 0.782 and 0.678 to 0.906 and 0.851, respectively. Simultaneously, the performance levels of two coupling approaches in streamflow prediction were compared, i.e., direct coupling of the original SWAT and BiLSTM models (SWAT-BiLSTM) and coupling of the enhanced SWAT and BiLSTM models (enhanced SWAT-BiLSTM). The results showed that the enhanced SWAT-BiLSTM model always performed better than the SWAT-BiLSTM model during the entire simulation period, especially the enhanced SWAT-BiLSTM model, which could more accurately predict peak streamflow changes. This study demonstrated that coupling an improved physical model with deep learning models could improve the streamflow prediction accuracy.

Predictability of monthly streamflow by considering complexity measures

Natural fluid flow systems exhibit turbulent and chaotic behavior that determines their high-level complexity. Chaos has an accurate mathematical definition, while turbulence is a property of fluid flow without an accurate mathematical definition. Using the Kolmogorov complexity (KC) and its derivative (KC spectrum), permutation entropy (PE), and Lyapunov exponent (LE), we considered how chaos affected the predictability of natural fluid flow systems. This paper applied these measures to investigate the turbulent, complex and chaotic behaviors of monthly streamflow of rivers from Bosnia and Herzegovina, the United States, and the Mendoza Basin (Argentina) and evaluated their time horizons using the Lyapunov time (LT). Based on the measures applied for river streamflow, we derived four modes of the interrelationship between turbulence, complexity, and chaos. Finally, using the measures, we clustered rivers with similar time horizons representing their predictability.

Improved monthly streamflow prediction using integrated multivariate adaptive regression spline with K-means clustering: implementation of reanalyzed remote sensing data

This study investigates monthly streamflow modeling at Kale and Durucasu stations in the Black Sea Region of Turkey using remote sensing data. The analysis incorporates key meteorological variables, including air temperature, relative humidity, soil wetness, wind speed, and precipitation. The study also investigates the accuracy of multivariate adaptive regression (MARS) with Kmeans clustering (MARS-Kmeans) by comparing it with single MARS, M5 model tree (M5Tree), random forest regression (RF), multilayer perceptron neural network (MLP). In the first modeling stage, principal component regression is applied to diverse input combinations, both with and without lagged streamflow (Q), resulting in twenty-three and twenty input combinations, respectively. Results demonstrate the critical role of including lagged Q for improved model accuracy, as models without lagged Q exhibit significant performance degradation. The second stage involves a comparative analysis of the MARS-Kmeans model with other machine-learning models, utilizing the best-input combination. MARS-Kmeans, incorporating three clusters, consistently outperforms other models, showcasing superior accuracy in predicting monthly streamflow.

Evaluation of regionalization parameters for stream flow prediction in ungauged catchments of Rift Valley Lakes Basin, Ethiopia

Evaluation of regionalization parameters for stream flow prediction in ungauged catchments of Rift Valley Lakes Basin, Ethiopia

On optimization of calibrations of a distributed hydrological model with spatially distributed information on snow

Abstract. In northern cold-temperate countries, a large portion of annual streamflow is produced by spring snowmelt, which often triggers floods. It is important to have spatial information about snow variables such as snow water equivalent (SWE), which can be incorporated into hydrological models, making them more efficient tools for improved decision-making. The present research implements a unique spatial pattern metric in a multi-objective framework for calibration of hydrological models and attempts to determine whether raw SNODAS (SNOw Data Assimilation System) data can be utilized for hydrological model calibration. The spatial efficiency (SPAEF) metric is explored for spatially calibrating SWE. Different calibration experiments are performed combining Nash–Sutcliffe efficiency (NSE) for streamflow and root-mean-square error (RMSE) and SPAEF for SWE, using the Dynamically Dimensioned Search (DDS) and Pareto Archived Dynamically Dimensioned Search multi-objective optimization (PADDS) algorithms. Results of the study demonstrate that multi-objective calibration outperforms sequential calibration in terms of model performance (SWE and discharge simulations). Traditional model calibration involving only streamflow produced slightly higher NSE values; however, the spatial distribution of SWE could not be adequately maintained. This study indicates that utilizing SPAEF for spatial calibration of snow parameters improved streamflow prediction compared to the conventional practice of using RMSE for calibration. SPAEF is further implied to be a more effective metric than RMSE for both sequential and multi-objective calibration. During validation, the calibration experiment incorporating multi-objective SPAEF exhibits enhanced performance in terms of NSE and Kling–Gupta efficiency (KGE) compared to calibration experiment solely based on NSE. This observation supports the notion that incorporating SPAEF computed on raw SNODAS data within the calibration framework results in a more robust hydrological model. The novelty of this study is the implementation of SPAEF with respect to spatially distributed SWE for calibrating a distributed hydrological model.

Assessing Objective Functions in Streamflow Prediction Model Training Based on the Naïve Method

Reliable streamflow forecasting is a determining factor for water resource planning and flood control. To better understand the strengths and weaknesses of newly proposed methods in streamflow forecasting and facilitate comparisons of different research results, we test a simple, universal, and efficient benchmark method, namely, the naïve method, for short-term streamflow prediction. Using the naïve method, we assess the streamflow forecasting performance of the long short-term memory models trained with different objective functions, including mean squared error (MSE), root mean squared error (RMSE), Nash–Sutcliffe efficiency (NSE), Kling–Gupta efficiency (KGE), and mean absolute error (MAE). The experiments over 273 watersheds show that the naïve method attains good forecasting performance (NSE > 0.5) in 88%, 65%, and 52% of watersheds at lead times of 1 day, 2 days, and 3 days, respectively. Through benchmarking by the naïve method, we find that the LSTM models trained with squared-error-based objective functions, i.e., MSE, RMSE, NSE, and KGE, perform poorly in low flow forecasting. This is because they are more influenced by training samples with high flows than by those with low flows during the model training process. For comprehensive short-term streamflow modeling without special demand orientation, we recommend the application of MAE instead of a squared-error-based metric as the objective function. In addition, it is also feasible to perform logarithmic transformation on the streamflow data. This work underscores the critical importance of appropriately selecting the objective functions for model training/calibration, shedding light on how to effectively evaluate the performance of streamflow forecast models.

Comparison of the performance of SWAT and hybrid M5P tree models in rainfall-runoff simulation.

Stream flow forecasting is a crucial aspect of hydrology and water resource management. This study explores stream flow forecasting using two distinct models: the Soil and Water Assessment Tool (SWAT) and a hybrid M5P model tree. The research specifically targets the daily stream flow predictions at the MH Halli gauge stations, located along the Hemvati River in Karnataka, India. A 14-year dataset spanning from 2003 to 2017 is divided into two subsets for model calibration and validation. The SWAT model's performance is evaluated by comparing its predictions to observed stream flow data. Residual time series values resulting from this comparison are then resolved using the M5P model tree. The findings reveal that the hybrid M5P tree model surpasses the SWAT model in terms of various evaluation metrics, including root-mean-square error, coefficient of determination (R2), Nash-Sutcliffe efficiency, and degree of agreement (d) for the MH Halli stations. In conclusion, this study shows the effectiveness of the hybrid M5P tree model in stream flow forecasting. The research contributes valuable insights into improved water resource management and underscores the importance of selecting appropriate models based on their performance and suitability for specific hydrological forecasting tasks.

A new interpretable streamflow prediction approach based on SWAT-BiLSTM and SHAP.

Streamflow is a crucial variable for assessing the available water resources for both human and environmental use. Accurate streamflow prediction plays a significant role in water resource management and assessing the impacts of climate change. This study explores the potential of coupling conceptual hydrological models based on physical processes with machine learning algorithms to enhance the performance of streamflow simulations. Four coupled models, namely SWAT-Transformer, SWAT-LSTM, SWAT-GRU, and SWAT-BiLSTM, were constructed in this research. SWAT served as a transfer function to convert four meteorological features, including precipitation, temperature, relative humidity, and wind speed, into six hydrological features: soil water content, lateral flow, percolation, groundwater discharge, surface runoff, and evapotranspiration. Machine learning algorithms were employed to capture the underlying relationships between these ten feature variables and the target variable (streamflow) to predict daily streamflow in the Sandu-River Basin (SRB). Among the four coupled models and the calibrated SWAT model, SWAT-BiLSTM exhibited the best streamflow simulation performance. During the calibration period (training period), it achieved R2 and NSE values of 0.92 and 0.91, respectively, and maintained them at 0.90 during the validation period (testing period). Additionally, the performance of all four coupled models surpassed that of the calibrated SWAT model. Compared to the tendency of the SWAT model to underestimate streamflow, the absolute values of PBIAS for all coupled models are below 10%, which indicates that there is no significant systematic bias evident. SHapley Additive exPlanations (SHAP) were used to analyze the impact of different feature variables on streamflow prediction. The results indicated that precipitation contributed the most to streamflow prediction, with a global importance of 29.7%. Hydrological feature variable output by the SWAT model played a dominant role in the Bi-LSTM's prediction process. Coupling conceptual hydrological models with machine learning algorithms can significantly enhance the predictive performance of streamflow. The application of SHAP improves the interpretability of the coupled models and enhances researchers' confidence in the prediction results.

Hydrological Verification of Two Rainfall Short-Term Forecasting Methods with Floods Anticipation Perspective

Abstract Flood forecasting remains a significant challenge, particularly when dealing with basins characterized by small drainage areas (i.e., 103 km2 or lower with response time in the range 0.5–10 h) especially because of the rainfall prediction uncertainties. This study aims to investigate the performances of streamflow predictions using two short-term rainfall forecast methods. These methods utilize a combination of a nowcasting extrapolation algorithm and numerical weather predictions by employing a three-dimensional variational assimilation system, and nudging assimilation techniques, meteorological radar, and lightning data that are frequently updated, allowing new forecasts with high temporal frequency (i.e., 1–3 h). A distributed hydrological model is used to convert rainfall forecasts into streamflow prediction. The potential of assimilating radar and lightning data, or radar data alone, is also discussed. A hindcast experiment on two rainy periods in the northwest region of Italy was designed. The selected skill scores were analyzed to assess their degradation with increasing lead time, and the results were further aggregated based on basin dimensions to investigate the catchment integration effect. The findings indicate that both rainfall forecast methods yield good performance, with neither definitively outperforming the other. Furthermore, the results demonstrate that, on average, assimilating both radar and lightning data enhances the performance.

Leveraging historic streamflow and weather data with deep learning for enhanced streamflow predictions

ABSTRACT Streamflow information is crucial for effectively managing water resources. The declining number of active gauging stations in many rivers is a global concern, necessitating the need for reliable streamflow estimates. Deep learning techniques offer potential solutions, but their application in southern Africa remains largely underexplored. To fill this gap, this study evaluated the predictive performance of gated recurrent unit (GRU) and long short-term memory (LSTM) networks using two headwater catchments of the Steelpoort River, South Africa, as case studies. The model inputs included rainfall, maximum, and minimum temperature, as well as past streamflow, which was utilized in an autoregressive sense. The inclusion of streamflow in this way allowed for the incorporation of simulated streamflow values into the look-back window for predicting the streamflow of the testing set. Two modifications were required to the GRU and LSTM architectures to ensure physically consistent predictions, including a change in the activation function of the GRU/LSTM cells in the final hidden layer, and a non-negative constraint that was used in the dense layer. Models trained using commercial weather station data produced reliable streamflow estimates, while moderately accurate predictions were obtained using freely available gridded weather data.

Toward interpretable LSTM-based modeling of hydrological systems

Abstract. Several studies have demonstrated the ability of long short-term memory (LSTM) machine-learning-based modeling to outperform traditional spatially lumped process-based modeling approaches for streamflow prediction. However, due mainly to the structural complexity of the LSTM network (which includes gating operations and sequential processing of the data), difficulties can arise when interpreting the internal processes and weights in the model. Here, we propose and test a modification of LSTM architecture that is calibrated in a manner that is analogous to a hydrological system. Our architecture, called “HydroLSTM”, simulates the sequential updating of the Markovian storage while the gating operation has access to historical information. Specifically, we modify how data are fed to the new representation to facilitate simultaneous access to past lagged inputs and consolidated information, which explicitly acknowledges the importance of trends and patterns in the data. We compare the performance of the HydroLSTM and LSTM architectures using data from 10 hydro-climatically varied catchments. We further examine how the new architecture exploits the information in lagged inputs, for 588 catchments across the USA. The HydroLSTM-based models require fewer cell states to obtain similar performance to their LSTM-based counterparts. Further, the weight patterns associated with lagged input variables are interpretable and consistent with regional hydroclimatic characteristics (snowmelt-dominated, recent rainfall-dominated, and historical rainfall-dominated). These findings illustrate how the hydrological interpretability of LSTM-based models can be enhanced by appropriate architectural modifications that are physically and conceptually consistent with our understanding of the system.

Assessment of the Impact of Spatial Variability on Streamflow Predictions Using High-Resolution Modeling and Parameter Estimation: Case Study of Geumho River Catchment, South Korea

In this study, we analyzed the impact of model spatial resolution on streamflow predictions, focusing on high-resolution scenarios (<1 km) and flooding conditions at catchment scale. Simulation experiments were implemented for the Geumho River catchment in South Korea using Weather Research and the Forecasting Hydrological Modeling System (WRF-Hydro) with spatial resolutions of 100 m, 250 m, and 500 m. For the estimation of parameters, an automatic calibration tool based on the Model-Independent Parameter Estimation and Uncertainty Analysis (PEST) method was utilized. We assessed the hydrological predictions across different spatial resolutions considering calibrated parameters, calibration runtime, and accuracy of streamflow before and after calibration. For both Rainfall Events 1 and 2, significant improvements were observed after event-specific calibration in all resolutions. Particularly for 250 m resolution, NSE values of 0.8 or higher were demonstrated at lower gauging locations. Also, at a 250 m resolution, the changes in the calibrated parameter values (REFKDT) were minimized between Rainfall Events 1 and 2, implicating more effective calibration compared to the other resolutions. At resolutions of 100 m and 500 m, the optimal parameter values for the two events were distinctively different while more computational resources were required for calibration in Event 2 with drier antecedent conditions.