Streamflow Model Research Articles

An explainable Bayesian gated recurrent unit model for multi-step streamflow forecasting

An explainable Bayesian gated recurrent unit model for multi-step streamflow forecasting

Streamflow modeling using the PyTOPKAPI model and remotely sensed rainfall: a case study of the Gilgel Ghibe catchment in Ethiopia

ABSTRACT Remote sensing contributes valuable information to streamflows. Usually, streamflow is directly measured through ground-based hydrological monitoring stations. However, in many countries like Ethiopia, ground-based hydrological monitoring networks are either sparse or nonexistent. The lack of reliable in situ observational data severely limits our ability to manage water resources in a well-informed way in these regions. In such cases, satellite remote sensing is an alternative means of acquiring such information. In this study, the application of remotely sensed rainfall data in streamflow modeling for the Gilgel Ghibe catchment in Ethiopia is reported. Ten years (2001–2010) of satellite-based-precipitation-products (SBPPs) from Tropical Rainfall Measuring Mission (TRMM) and WaterBase, were combined with a PyTOPKAPI model to generate daily streamflows. We compared the results with that of the observed streamflows at the Gilgel Ghibe Nr, Assendabo gauging station using four statistical tools (bias, R2, NS, and RMSE). The result indicates that the bias-adjusted SBPPs agree well with gauged-rainfall. Without bias-adjustment, the SBPPs tend to overestimate the simulated streamflows. We further conclude that the general streamflow patterns were well captured at daily time scale from SBPPs after bias-adjustment. However, the simulated streamflow using gauged-rainfall is superior to those obtained from SBPPs including bias-adjusted ones.

Review of gridded climate products and their use in hydrological analyses reveals overlaps, gaps, and the need for a more objective approach to selecting model forcing datasets

Abstract. Climate forcing data accuracy drives performance of hydrologic models and analyses, yet each investigator needs to select from among the numerous gridded climate dataset options and justify their selection for use in a particular hydrologic model or analysis. This study aims to provide a comprehensive compilation and overview of gridded datasets (precipitation, air temperature, humidity, wind speed, solar radiation) and considerations for historical climate product selection criteria for hydrologic modeling and analyses based on a review and synthesis of previous studies conducting dataset intercomparisons. All datasets summarized here span at least the conterminous US (CONUS), and many are continental or global in extent. Gridded datasets built on ground-based observations (G; n= 20), satellite imagery (S; n= 20), and/or reanalysis products (R; n= 23) are compiled and described, with focus on the characteristics that hydrologic investigators may find useful in discerning acceptable datasets (variables, coverage, resolution, accessibility, and latency). We provide best-available-science recommendations for dataset selection based on a thorough review, interpretation, and synthesis of 29 recent studies (past 10 years) that compared the performance of various gridded climate datasets for hydrologic analyses. No single best source of gridded climate data exists, but we identified several common themes that may help guide dataset selection in future studies: Gridded daily temperature datasets improved when derived over regions with greater station density. Similarly, gridded daily precipitation data were more accurate when derived over regions with higher-density station data, when used in spatially less-complex terrain, and when corrected using ground-based data. In mountainous regions and humid regions, R precipitation datasets generally performed better than G when underlying data had a low station density, but there was no difference for higher station densities. G datasets were generally more accurate in representing precipitation and temperature data than S or R datasets, although this did not always translate into better streamflow modeling. We conclude that hydrologic analyses would benefit from guided dataset selection by investigators, including justification for selecting a specific dataset, and improved gridded datasets that retain dependencies among climate variables and better represent small-scale spatial variability in climate variables in complex topography. Based on this study, the authors' overall recommendations to hydrologic modelers are to select the gridded dataset (from Tables 1, 2, and 3) (a) with spatial and temporal resolutions that match modeling scales, (b) that are primarily (G) or secondarily (SG and RG) derived from ground-based observations, (c) with sufficient spatial and temporal coverage for the analysis, (d) with adequate latency for analysis objectives, and (e) that includes all climate variables of interest (so as to better represent interdependencies).

Streamflow modeling in the Colombian Andes: insights from watersheds with diverse physical properties and climate patterns

Streamflow modeling in the Colombian Andes: insights from watersheds with diverse physical properties and climate patterns

Stream flow modeling using SWAT model and performance evaluation in Adhaim watershed

https://ejuow.uowasit.edu.iq Understanding the hydrological cycle and finding data crucial for water management require a foundational understanding of basin-scale simulation. To create the most accurate stream flow modeling possible, data from the weather stations was combined with input from other maps of the research area, such as soil, land cover, land use (LCLU), and digital elevation model (DEM). Regarding Adhaim Watershed, period 2000 to 2013SWAT model calibration was done using the Sequential Uncertainty Fitting (SUFI–2) technique and the Nash–Sutcliffe simulation efficiency (NSE) and coefficient of determination (R2). This included an initial calibration from 2000/1/1 to 31/9/2009 which was then validated for 1/10/2010 to 31/12/2013 using daily streamflow values. Adhaim Watershed's whole area was determined to be 11816.82 km2. Grasslands make up 41.01% of the total area. Additionally, 28% of LCLU came from croplands and desolate regions in equal measure. A hydrological type D clay soil was discovered, along with the watershed's primary slope (0–5). The mean streamflow of Adhaim was determined to be 22.m3/????????????, and upon calibration, it was found to be 30 ????3/????????????.

Machine Learning Classification Strategy to Improve Streamflow Estimates in Diverse River Basins in the Colorado River Basin

AbstractStreamflow in the Colorado River Basin (CRB) is significantly altered by human activities including land use/cover alterations, reservoir operation, irrigation, and water exports. Climate is also highly varied across the CRB which contains snowpack‐dominated watersheds and arid, precipitation‐dominated basins. Recently, machine learning methods have improved the generalizability and accuracy of streamflow models. Previous successes with LSTM modeling have primarily focused on unimpacted basins, and few studies have included human impacted systems in either regional or single‐basin modeling. We demonstrate that the diverse hydrological behavior of river basins in the CRB are too difficult to model with a single, regional model. We propose a method to delineate catchments into categories based on the level of predictability, hydrological characteristics, and the level of human influence. Lastly, we model streamflow in each category with climate and anthropogenic proxy data sets and use feature importance methods to assess whether model performance improves with additional relevant data. Overall, land use cover data at a low temporal resolution was not sufficient to capture the irregular patterns of reservoir releases, demonstrating the importance of having high‐resolution reservoir release data sets at a global scale. On the other hand, the classification approach reduced the complexity of the data and has the potential to improve streamflow forecasts in human‐altered regions.

Hydrological Response to Climate Change: McGAN for Multi-Site Scenario Weather Series Generation and LSTM for Streamflow Modeling

This study focuses on the impacts of climate change on hydrological processes in watersheds and proposes an integrated approach combining a weather generator with a multi-site conditional generative adversarial network (McGAN) model. The weather generator incorporates ensemble GCM predictions to generate regional average synthetic weather series, while McGAN transforms these regional averages into spatially consistent multi-site data. By addressing the spatial consistency problem in generating multi-site synthetic weather series, this approach tackles a key challenge in site-scale climate change impact assessment. Applied to the Jinghe River Basin in west-central China, the approach generated synthetic daily temperature and precipitation data for four stations under different shared socioeconomic pathways (SSP1-26, SSP2-45, SSP3-70, SSP5-85) up to 2100. These data were then used with a long short-term memory (LSTM) network, trained on historical data, to simulate daily river flow from 2021 to 2100. The results show that (1) the approach effectively addresses the spatial correlation problem in multi-site weather data generation; (2) future climate change is likely to increase river flow, particularly under high-emission scenarios; and (3) while the frequency of extreme events may increase, proactive climate policies can mitigate flood and drought risks. This approach offers a new tool for hydrologic–climatic impact assessment in climate change studies.

Hydrological streamflow modeling at the inlet of Gilgel Gibe III dam of Ethiopia using soil and water assessment tool

AbstractComprehensive approach is a pre‐requisite to improve the estimation of variability in streamflow data for designing water supply systems, generating hydropower, determining environmental flows, allocating water, and conducting pollution studies that need a comprehensive approach. There is a need to model streamflow data to develop effective water policy plans when sufficient data are unavailable. This study aims at assessing the accuracy and applicability of the Soil and Water Assessment Tool (SWAT) model in predicting streamflow at the inlet of the Gilgel Gibe III dam watershed in Ethiopia. Historical meteorological data from nine available stations between 1987 and 2017 were used to predict the streamflow. The SWAT model was calibrated and validated for two different time periods (1997–1999 and 2003–2004) using SWATCUP program and SUFI‐2 technique. Calibration and validation were based on monthly observed discharges at the Abelti and Gojeb stations. The results showed acceptable values of R2, Nash–Sutcliffe modeling efficiency (NSE), and percent bias (PBIAS). At the Abelti station and Gojeb station, the calibration and validation results were 0.82, 0.79, and −10.1%; 0.88, 0.84, and −14.4%; and 0.86, 0.79, and 14.1% for calibration and 0.88, 0.8, and 11.1% for validation, respectively. The prediction uncertainty of 95% was consistent with the observed discharge. The mean annual runoff was 440.08 m3/s, demonstrating the model's effectiveness in simulating streamflow at the dam's inlet. The calibrated and validated model can be used to study the effects of climate and land use changes; analyze water quality and sediment yield; and inform future water policy plans, dam construction planning, and flood disaster risk management.

Toward reproducible and interoperable environmental modeling: Integration of HydroShare with server-side methods for exposing large-extent spatial datasets to models

Reproducible environmental modelling often relies on spatial datasets as inputs, typically manually subset for specific areas. Yet, models can benefit from a data distribution approach facilitated by online repositories, and automating processes to foster reproducibility. This study introduces a method leveraging diverse state-scale spatial datasets to create cohesive packages for GIS-based environmental modelling. These datasets were generated and shared via GeoServer and THREDDS Data Server connected to HydroShare, contrasting with conventional distribution methods. Using the Regional Hydro-Ecologic Simulation System (RHESSys) across three U.S. catchment-scale watersheds, we demonstrate minimal errors in spatial inputs and model streamflow outputs compared to traditional approaches. This spatial data-sharing method facilitates consistent model creation, fostering reproducibility. Its broader impact allows scientists to tailor the method to various use cases, such as exploring different scales beyond state-scale or applying it to other online repositories using existing data distribution systems, eliminating the need to develop their own.

Integrated hydrological modelling and streamflow characterization of Gangotri Glacier meltwater

Runoff from glaciated catchments is an integrated process that includes glacier melt, snowmelt, rainfall and surface and subsurface runoff of meltwater from glacierized and non-glacierized areas. Monitoring and quantifying the contribution of the hydrologic components (snow, ice and rain) to river discharge in the Himalayan basins is essential for decision-making in the water sector, particularly in water resources management and flood risk reduction in the region. An attempt has been made to characterize and hydrologically model streamflow (Bhagirathi River) for the Gangotri Glacier (Central Himalaya, India). A semi-distributed conceptual hydrological model is used for the streamflow modelling and assessing the major streamflow components (snow melt, glacier melt and rainfall runoff). Initially, the model was calibrated using the available in situ hydro-meteorological records for the ablation seasons of 2013–14 to 2015–16 (3 years), and further validated for the ablation seasons of 2016–17 to 2018–19 (3 years). The model performed well for all the studied years except for some months, where abrupt changes in the contrasting weather parameters (precipitation and temperature) were recorded. In the Gangotri Glacier Valley (upper Bhagirathi River catchment), snowmelt contributed the largest portion (55.5%) to total streamflow followed by glacier melt (29.7%) and rainfall runoff components (14.7%).

Enhancing streamflow simulations with gated recurrent units deep learning models in the flood prone region with low-convergence streamflow data

Highly accurate streamflow simulations are essential for water resources and river management. However, there are longstanding challenges for streamflow modeling in the hydrology field. As a result, deep learning methods have been introduced as novel tools and are being used in simulation. This paper proposes a novel approach that utilizes unconventional data preprocessing techniques to improve the accuracy of daily streamflow predictions in flood-prone regions. We applied this approach to a flood-prone area in western Iran and simulated daily streamflow using a deep learning Gated Recurrent Unit (GRU) method under various data selection scenarios. These scenarios focused on identifying the optimal combination of input variables, time steps, and outlier removal techniques. The outlier removal methods investigated in this study include Mahalanobis distance, critical section removal, Z-score, and no removal. The average rainfall of the area, data driven precipitation, Normalized Difference Vegetation Index (NDVI), surface soil moisture, groundwater baseflows, and streamflow in the hydrometric station were evaluated using correlation control method, and inputs with the lowest correlation were removed. Based on the results obtained from the deep learning models produced in the research, it was found that the GRU model, with various modified inputs using Z-score removal, had the best performance. The model had an average of Root Mean Squared Error (RMSE) at 5.24 mm and R2 (Coefficient of Determination) at 0.91 during training, while during validation, it had an RMSE of 7.74 mm and R2 of 0.83. Considering using relatively low convergence data in streamflow simulation in this study, it can be said that the listed scenarios showed an appropriate result in dealing with the data and recognizing the complex pattern of the daily streamflow, and the future studies will show the improvement of the GRU models if higher convergence data will be used.

Ensemble learning of decomposition-based machine learning models for multistep-ahead daily streamflow forecasting in northwest China

ABSTRACT Accurate daily streamflow forecasts remain challenging in arid regions. A Bayesian model averaging (BMA) ensemble learning strategy was proposed to forecast 1-, 2-, and 3-day-ahead streamflow in Dunhuang Oasis, northwest China. The efficiency of BMA was compared with four decomposition-based machine learning and deep learning models. Satisfactory forecasts were achieved with all proposed models at all lead times; however, based on Nash-Sutcliffe efficiency values of 0.976, 0.967, and 0.957, BMA achieved the greatest accuracy for 1-, 2-, and 3-day-ahead streamflow forecasts, respectively. Uncertainty analysis confirmed the reliability of BMA in yielding consistently accurate streamflow forecasts. Thus, BMA could provide an efficient alternative approach to multistep-ahead daily streamflow forecasting. The incorporation of data decomposition techniques (e.g. variational mode decomposition) and deep learning algorithms (e.g. deep belief network) into BMA may provide worthy technical references for supervised learning of streamflow systems in data-scarce regions.

Investigating Mountain Watershed Headwater‐To‐Groundwater Connections, Water Sources, and Storage Selection Behavior With Dynamic‐Flux Particle Tracking

AbstractClimate change will impact mountain watershed streamflow both directly—with changing precipitation amounts and variability—and indirectly—through temperature shifts altering snowpack, melt, and evapotranspiration. To understand how these complex processes will affect ecosystem functioning and water resources, we need tools to distinguish connections between water sources (rain/snowmelt), groundwater storage, and exit fluxes (streamflow/evapotranspiration), and to determine how these connections change seasonally and as climate shifts. Here, we develop novel watershed‐scale approaches to understand water source, storage, and exit flux connections using a dynamic‐flux particle tracking model (EcoSLIM) applied in California's Cosumnes Watershed, which connects the Sierra Nevada and Central Valley. This work develops new visualizations and applications to provide mechanistic understanding that underpins the interpretation of isotopic field data at watershed scales to distinguish sources, flow paths, residence times, and storage selection. In our simulations, streamflow comes primarily from snow‐derived water while evapotranspiration generally comes from rain. Most streamflow starts above 1,000 m while evapotranspiration is sourced relatively evenly across the watershed and is generally younger than streamflow. Modeled streamflow consists primarily of water sourced from precipitation in the previous 5 years but before the current water year, while ET consists primarily of water from precipitation in the current water year. ET, and to a lesser extent streamflow, are both younger than water in groundwater storage. However, snowmelt‐derived streamflow preferentially discharges older water from snow‐derived storage. Dynamic‐flux particle tracking and new approaches presented here enable novel model‐tracer comparisons in large‐scale watersheds to better understand watershed behavior in a changing climate.

Testing the Feasibility of an Agent-Based Model for Hydrologic Flow Simulation

Modeling streamflow is essential for understanding flow inundation. Traditionally, this involves hydrologic and numerical models. This research introduces a framework using agent-based modeling (ABM) combined with data-driven modeling (DDM) and Artificial Intelligence (AI). An agent-driven model simulates streamflow and its interactions with river courses and surroundings, considering hydrologic phenomena related to precipitation, water level, and discharge as well as channel and basin characteristics causing increased water levels in the Medio River. A five-year dataset of hourly precipitation, water level, and discharge measurements was used to simulate streamflow. The model’s accuracy was evaluated using statistical metrics like correlation coefficient (r), coefficient of determination (R2), root mean squared error (RMSE), and percentage error in peak discharge (Qpk). The ABM’s simulated peak discharge (Qpk) was compared with the measured peak discharge across four experimental scenarios. The best simulations occurred in scenario 3, using only rainfall and streamflow data. Data management and visualization facilitated input, output, and analysis. This study’s ABM combined with DDM and AI offers a novel approach for simulating streamflow and predicting floods. Future studies could extend this framework to other river basins and incorporate advanced sensor data to enhance the accuracy and responsiveness of flood forecasting.

Temporal Dynamics and Predictive Modelling of Streamflow and Water Quality Using Advanced Statistical and Ensemble Machine Learning Techniques

Temporal Dynamics and Predictive Modelling of Streamflow and Water Quality Using Advanced Statistical and Ensemble Machine Learning Techniques

Streamflow prediction model for agriculture dominated tropical watershed using machine learning and hierarchical predictor selection algorithms

Study regionRana watershed, located in the mid-Mahanadi River basin in the state of Odisha, India. Study focusThis study attempted to develop a generalizable machine learning (ML)-based streamflow prediction model implementing prediction selection algorithms to the physiographic characteristics, and hydro-meteorological data collected for Rana Watershed. New hydrological insightsThe pertinent predictors identified were land use/ land cover (LULC), one and two-day lagged rainfall, one-day lagged PET, and one-day lagged streamflow and its categorized flow regime. The random forest algorithm, which outperformed the other five algorithms evaluated, was trained using identified predictors to develop a streamflow prediction model called “stRFlow”. The mean absolute error, root mean squared error, coefficient of determination, and Nash-Sutcliffe efficiency during training were 0.753 m3/s, 3.584 m3/s, 0.973, and 0.972 and testing were 2.829 m3/s, 10.503 m3/s, 0.855, and 0.851, respectively. The Kling-Gupta efficiency was found to be 0.96 and 0.92 during training and testing, respectively. There was an enhancement to model proficiency with the addition of LULC to temporal predictors. Moreover, the partial auto-correlation factor for the streamflow and examining the categorization of specific lagged flow regimes enhanced the predictive capacities of “stRFlow”. Results depict the potential of stRFlow and the framework in streamflow modeling in similar hydroclimatic regions with applicability for practical and reliable streamflow predictions globally.

Comparative analysis of satellite and reanalysis data with ground‐based observations in Northern Ghana

AbstractAccurate predictions of streamflow and flood events are contingent upon the availability of reliable hydrometeorological data. In regions characterized by scarcity of ground‐based hydrometeorological observations, satellite and reanalysis data assume prominence as alternative predictors. Floods and droughts have emerged as a significant concern in Northern Ghana, yet the scarcity of ground‐based hydrometeorological data impedes effective prediction of these hydrological events. Consequently, the identification of suitable surrogate hydrometeorological data holds paramount importance in addressing these challenges. This study, therefore, assessed the accuracy of satellite and reanalysis data against ground‐based data in Northern Ghana. Rainfall and mean temperature spanning from 1998 to 2019 and soil moisture datasets from 2019 to 2022 were collected from GMet, ISMN (ground‐based), CHIRPS, PERSIANN‐CDR, ERA5, ARC2, MERRA‐2, TRMM and CFSR (satellite and reanalysis). Employing rigorous statistical measures, namely standard deviation, mean absolute error (MAE) and mean bias error (MBE), the accuracy of these datasets was thoroughly evaluated. The results revealed that CHIRPS and PERSIANN‐CDR exhibited superior accuracy in rainfall simulation, with CHIRPS demonstrating particularly consistent congruence with observed data. In terms of mean temperature prediction, ERA5 surpassed MERRA‐2 and CFSR. Regarding soil moisture assessments, both ERA5 and CFSR offered satisfactory simulations. Hence, our findings advocate for the preference of CHIRPS (for rainfall data), ERA5 (for temperature data) and a combination of CFSR/ERA5 (for soil moisture data) as dependable primary data sources for streamflow modelling, drought analysis, flood prediction and water resource management in the context of Northern Ghana.

Influence of SMAP soil moisture retrieval assimilation on runoff estimation across South Asia

This study was designed to characterize and quantify the influence of surface soil moisture assimilation on estimated runoff (surface flow and baseflow) and hydraulically-routed streamflow across three large river basins in South Asia that are at risk of impending water stress. Soil Moisture Active Passive (SMAP) surface soil moisture retrievals were assimilated into the Noah-MP land surface model. The gridded runoff was hydraulically routed to obtain volumetric streamflow values for a river network using a runoff routing module (Hydrological Modeling and Analysis Platform, HyMAP). The open loop (OL, model-only) and data assimilated (DA, includes soil moisture retrieval assimilation) Noah-MP runoff estimates highlighted the improvements in estimated total runoff across irrigated areas. Soil moisture assimilation impacted baseflow more relative to surface runoff. The HyMAP-based OL and DA streamflow generally underestimated the streamflow at upstream stations and overestimated the streamflow at downstream stations within the Indus basin due to missing physics related to reservoir operations. For stations located in the Ganges–Brahmaputra basins, the OL and DA estimation performance varied. The OL and DA results showed that the assimilation of soil moisture retrievals improves gridded runoff and volumetric streamflow across irrigated areas. Considerable relative change in streamflow (>70% increase in magnitude relative to OL) is noted after assimilation across the highly irrigated lower Indus basin and high precipitation regions in Bangladesh. Improving the modeling system’s representativeness of ground conditions via inclusion of water management information could improve large-scale streamflow modeling across South Asia.

A spatio-temporal analysis of environmental fate and transport processes of pesticides and their transformation products in agricultural landscapes dominated by subsurface drainage with SWAT+

Pesticides are detected in surface water and groundwater, endangering the environment. In lowland regions with subsurface drainage systems, drained depressions become hotspots for transport of pesticides and their transformation products (TPs). This study focuses on detailed modelling of the degradation and transport of pesticides with different physico-chemical properties. The objective is to analyse complex hydrological transport processes, to understand the temporal and spatial dynamics of the degradation and transport of pesticides. The ecohydrological model SWAT+ simulates hydrological processes as well as agricultural management and pesticide degradation, and can therefore be used to develop pesticide loss reduction strategies. This study focuses on modelling of three pesticides (pendimethalin, diflufenican, and flufenacet), and two TPs, flufenacet-oxalic acid (FOA) and flufenacet sulfonic acid (FESA). The study area is a 100-hectare farmland in the northern German lowlands of Schleswig-Holstein that is characterized by an spacious drainage network of 6.3 km and managed according to common conventional agricultural practice.SWAT+ modelled streamflow with very good agreement between observed and simulated data during calibration and validation. Regarding pesticides, the model performance for highly mobile substances is better than for non-mobile pesticides. While the transport of the moderately to very mobile substances via tile drains played an important role in both wet and dry conditions, no transport via tile drains was modelled for the highly sorptive and non-mobile pendimethalin.In conclusion, the model can reliably represent the degradation of moderately to very mobile pesticides in small-scale tile drainage-dominated catchments, as well as surface runoff-induced peak loads. However, it has weaknesses in accounting for the subsurface transport of non-mobile substances, which can lead to an underestimation of the subsequent delivery after precipitation events and thus underestimates the total load.

Physically based vs. data-driven models for streamflow and reservoir volume prediction at a data-scarce semi-arid basin

Physically based or data-driven models can be used for understanding basinwide hydrological processes and creating predictions for future conditions. Physically based models use physical laws and principles to represent hydrological processes. In contrast, data-driven models focus on input–output relationships. Although both approaches have found applications in hydrology, studies that compare these approaches are still limited for data-scarce, semi-arid basins with altered hydrological regimes. This study aims to compare the performances of a physically based model (Soil and Water Assessment Tool (SWAT)) and a data-driven model (Nonlinear AutoRegressive eXogenous model (NARX)) for reservoir volume and streamflow prediction in a data-scarce semi-arid region. The study was conducted in the Tersakan Basin, a semi-arid agricultural basin in Türkiye, where the basin hydrology was significantly altered due to reservoirs (Ladik and Yedikir Reservoir) constructed for irrigation purposes. The models were calibrated and validated for streamflow and reservoir volumes. The results show that (1) NARX performed better in the prediction of water volumes of Ladik and Yedikir Reservoirs and streamflow at the basin outlet than SWAT (2). The SWAT and NARX models both provided the best performance when predicting water volumes at the Ladik reservoir. Both models provided the second best performance during the prediction of water volumes at the Yedikir reservoir. The model performances were the lowest for prediction of streamflow at the basin outlet (3). Comparison of physically based and data-driven models is challenging due to their different characteristics and input data requirements. In this study, the data-driven model provided higher performance than the physically based model. However, input data used for establishing the physically based model had several uncertainties, which may be responsible for the lower performance. Data-driven models can provide alternatives to physically-based models under data-scarce conditions.