Kling-Gupta Efficiency Research Articles

Revisiting the tension water storage capacity distribution in conceptual rainfall-runoff modeling: A large-sample approach

Accurately characterizing the spatial variability of tension water storage capacity (TWC) within a catchment is challenging due to limited in-situ hydrologic data availability. Conventional conceptual rainfall-runoff models typically rely on an empirically specified TWC distribution. However, this empirical distribution lacks a physical foundation and fails to effectively redistribute critical hydrologic components, such as local capacity and contributing area, to real-world contexts. To overcome this limitation, the topographic wetness index (TWI) and its generalized form (GTWI) are introduced to bridge local topographic information with hydrologic components. Four TWC distribution curves are contrived based on the empirical parabolic distribution, empirical linear distribution, TWI, and GTWI, respectively. The effects of these alternate TWC distributions on streamflow are investigated within the framework of the HYdrologic MODel (HYMOD) across 460 Australian catchments. The results illustrate that the GTWI-based HYMOD (GTHYMOD) outperforms other models in terms of daily streamflow, with high Kling-Gupta Efficiency (KGE) attained in 74.8% of the study catchments during the validation period. The eastern coast of Australian catchments presents a superior streamflow performance compared to that in the western coast. GTHYMOD demonstrates its superiority in characterizing spatial variability, an aspect HYMOD lacked. This study has the potential to refine the empirical TWC distribution from a physical perspective and advance our comprehension of underlying hydrologic behaviors.

Runoff Prediction of Tunxi Basin under Projected Climate Changes Based on Lumped Hydrological Models with Various Model Parameter Optimization Strategies

Runoff is greatly influenced by changes in climate conditions. Predicting runoff and analyzing its variations under future climates are crucial for ensuring water security, managing water resources effectively, and promoting sustainable development within the catchment area. As the key step in runoff modeling, the calibration of hydrological model parameters plays an important role in models’ performance. Identifying an efficient and reliable optimization algorithm and objective function continues to be a significant challenge in applying hydrological models. This study selected new algorithms, including the strategic random search (SRS) and sparrow search algorithm (SSA) used in hydrology, gold rush optimizer (GRO) and snow ablation optimizer (SAO) not used in hydrology, and classical algorithms, i.e., shuffling complex evolution (SCE-UA) and particle swarm optimization (PSO), to calibrate the two-parameter monthly water balance model (TWBM), abcd, and HYMOD model under the four objective functions of the Kling–Gupta efficiency (KGE) variant based on knowable moments (KMoments) and considering the high and low flows (HiLo) for monthly runoff simulation and future runoff prediction in Tunxi basin, China. Furthermore, the identified algorithm and objective function scenario with the best performance were applied for runoff prediction under climate change projections. The results show that the abcd model has the best performance, followed by the HYMOD and TWBM models, and the rank of model stability is abcd > TWBM > HYMOD with the change of algorithms, objective functions, and contributing calibration years in the history period. The KMoments based on KGE can play a positive role in the model calibration, while the effect of adding the HiLo is unstable. The SRS algorithm exhibits a faster, more stable, and more efficient search than the others in hydrological model calibration. The runoff obtained from the optimal model showed a decrease in the future monthly runoff compared to the reference period under all SSP scenarios. In addition, the distribution of monthly runoff changed, with the monthly maximum runoff changing from June to May. Decreases in the monthly simulated runoff mainly occurred from February to July (10.9–56.1%). These findings may be helpful for the determination of model parameter calibration strategies, thus improving the accuracy and efficiency of hydrological modeling for runoff prediction.

Improving carbon flux estimation in tea plantation ecosystems: A machine learning ensemble approach

Tea plant (Camellia sinensis) is a major global crop consumed as a drink after water. Quantifying carbon flux, specifically the net ecosystem exchange (NEE), in tea plantations is essential for determining carbon sequestration and ecosystem carbon balance. The Eddy covariance (EC) system is widely used for continuous monitoring of carbon flux but high costs associated with installation and maintenance limit its widespread adoption. In addition, EC flux data is often discarded due to malfunction of instruments caused by adverse weather conditions. Therefore, additional approaches for estimating NEE are necessary to overcome these challenges and ensure accurate NEE measurement. For this purpose, three standalone tree-based machine learning (ML) models were used for NEE estimation using EC flux data collected from tea ecosystem located in subtropical region (Danyang county of Zhenjiang city) of China. To address the accuracy limitations inherent in standalone ML models, the ensemble mechanism based on voting regressor method was proposed. In addition, k-fold cross-validation based on early stopping process was also used to enhance the performance of standalone ML models. Based on visual plots (scatter diagram, heatMap, Taylor diagram) and performing indices (root-mean-square error (RMSE), determination coefficient (R2), mean absolute error (MAE), mean absolute percentage error (MAPE), Nash–Sutcliffe efficiency (NSE), correlation coefficient (r), Kling Gupta Efficiency (KGE) and index of agreement (d)), the findings indicated that non-linear ensemble-generalized regression neural network (NLE-GRNN) significantly improved standalone ML model's results. In current study, the highest NSE, r and d in case of standalone ML model (DT) achieved 0.49, 0.73 and 0.75 respectively while our proposed NLE-GRNN model improved 48 % in NSE value (NSE = 0.97), 25 % in r value (r = 0.98) and 24 % in d value (d = 0.99). Likewise, NLE-GRNN significantly reduce errors (MAE, MAPE and RMSE) and provides NEE estimate closet to the observed value. The impact of climatic variables on NEE using shapley additive explanations (SHAP) analysis revealed that Rg (solar radiation) and Tair (air temperature) were the prime factors controlling NEE variation in the tea ecosystem. Considering the high accuracy and stability of the studied ML models, it is recommended to apply developed ensemble ML model (NLE-GRNN) for significant improvement of NEE estimate in the tea biomes or other ecosystems.

Daily Runoff Prediction Based on FA-LSTM Model

Accurate and reliable short-term runoff prediction plays a pivotal role in water resource management, agriculture, and flood control, enabling decision-makers to implement timely and effective measures to enhance water use efficiency and minimize losses. To further enhance the accuracy of runoff prediction, this study proposes a FA-LSTM model that integrates the Firefly algorithm (FA) with the long short-term memory neural network (LSTM). The research focuses on historical daily runoff data from the Dahuangjiangkou and Wuzhou Hydrology Stations in the Xijiang River Basin. The FA-LSTM model is compared with RNN, LSTM, GRU, SVM, and RF models. The FA-LSTM model was used to carry out the generalization experiment in Qianjiang, Wuxuan, and Guigang hydrology stations. Additionally, the study analyzes the performance of the FA-LSTM model across different forecasting horizons (1–5 days). Four quantitative evaluation metrics—mean absolute error (MAE), root mean square error (RMSE), coefficient of determination (R2), and Kling–Gupta efficiency coefficient (KGE)—are utilized in the evaluation process. The results indicate that: (1) Compared to RNN, LSTM, GRU, SVM, and RF models, the FA-LSTM model exhibits the best prediction performance, with daily runoff prediction determination coefficients (R2) reaching as high as 0.966 and 0.971 at the Dahuangjiangkou and Wuzhou Stations, respectively, and the KGE is as high as 0.965 and 0.960, respectively. (2) FA-LSTM model was used to conduct generalization tests at Qianjiang, Wuxuan and Guigang hydrology stations, and its R2 and KGE are 0.96 or above, indicating that the model has good adaptability in different hydrology stations and strong robustness. (3) As the prediction period extends, the R2 and KGE of the FA-LSTM model show a decreasing trend, but the whole model still showed feasible forecasting ability. The FA-LSTM model introduced in this study presents an effective new approach for daily runoff prediction.

Significance of Multi-Variable Model Calibration in Hydrological Simulations within Data-Scarce River Basins: A Case Study in the Dry-Zone of Sri Lanka

Traditional hydrological model calibration using limitedly available streamflow data often becomes inadequate, particularly in dry climates, as the flow regimes may abruptly vary from arid conditions to devastating floods. Newly available remote-sensing-based datasets can be supplemented to overcome such inadequacies in hydrological simulations. To address this shortcoming, we use multi-variable-based calibration by setting up and calibrating a lumped-hydrological model using observed streamflow and remote-sensing-based soil moisture data from Soil Moisture Active Passive Level 4. The proposed method was piloted at the Maduru Oya River Basin, Sri Lanka, as a proof of concept. The relative contributions from streamflow and soil moisture were assessed and optimised via the Kling–Gupta Efficiency (KGE). The Generalized Reduced Gradient non-linear solver function was used to optimise the Tank Model parameters. The findings revealed satisfactory performance in streamflow simulations under single-variable model validation (KGE of 0.85). Model performances were enhanced by incorporating soil moisture data (KGE of 0.89), highlighting the capability of the proposed multi-variable calibration technique for improving the overall model performance. Further, the findings of this study highlighted the instrumental role of remote sensing data in representing the soil moisture dynamics of the study area and the importance of using multi-variable calibration to ensure robust hydrological simulations of river basins in dry climates.

A combined extended triple collocation and cumulative distribution function merging framework for improved daily precipitation estimates over mainland China

Accurate monitoring of daily precipitation is essential for many applications, such as simulation and prediction of watershed water-related disasters. However, precipitation data from satellite and gauge-based precipitation products face challenges in capturing true observations because of their large uncertainties. To improve daily precipitation estimates, this study proposed a new merging framework, ETCCCDF, that combines an extended triple collocation (ETCC) with maximized correlation and cumulative distribution function (CDF) matching with reduced bias. The ETCCCDF framework was applied to systematically integrate three independent precipitation products from SM2RAIN-ASCAT satellite soil moisture estimator, IMERG Early Run satellite retrieval, and CPC unified gauge-based analysis. A new merged precipitation product, with a fine spatiotemporal resolution of 0.25°/1 d, was developed and then thoroughly evaluated using 2304 stations over mainland China from 2007 to 2014. The results showed that the ETCCCDF framework significantly improved the precipitation representation in terms of the correlation, bias, and absolute difference, and it increased modified Kling-Gupta efficiency value relative to any of the parent precipitation products, demonstrating the effectiveness of the proposed merging framework. In addition, the ETCCCDF framework is more robust than the ETCC, triple collocation (TC) merging, and combined strategy of TC with CDF, in which CDF matching successfully corrects the precipitation biases in collocation fusions. The accuracy of the merged products in heavy rainfall estimation during Typhoon Morakot in 2009 and Typhoon Fitow in 2013 was further evaluated. The results confirmed that the ETCCCDF-merged product performed satisfactorily for heavy rainfall events and presented superior statistical scores. This study proves that the ETCCCDF framework is a promising solution for obtaining high-quality precipitation data, particularly for limited-gauge areas.

Two-stage meta-ensembling machine learning model for enhanced water quality forecasting

Accurate short-term forecasting of water quality variables (WQVs) such as dissolved oxygen (DO) and chlorophyll-a (Chl-a) is crucial for the effective management of aquatic resources. This study introduces a robust two-stage optimization-ensembling framework that integrates the Grey Wolf Optimizer (GWO) and the Non-dominated Sorting Genetic Algorithm II (NSGA-II) to enhance the forecasting capabilities of machine learning (ML) models. Focusing on Small Prespa Lake, Greece, we implemented an array of diverse ML techniques, including eXtreme Gradient Boosting (XGB), Gradient Boosting Regressor (GBR), Light Gradient-Boosting Machine (LightGBM), and Multilayer Perceptron (MLP). These models were fine-tuned using GWO to optimize their performance over critical WQVs predicted six hours in advance. Our methodology employed rigorous data preprocessing techniques, including lag time feature engineering and principal component analysis (PCA), to handle the high dimensionality of the dataset. Optimal lag times ranging from 6 to 24 hour were evaluated, with the 24-hour lag proving to be the most effective in utilizing historical data to enhance forecasting accuracy. The GWO not only facilitated hyperparameter tuning but also demonstrated a notable improvement (7.6%) in the Kling-Gupta Efficiency (KGE) over conventional randomized search methods. Subsequently, the NSGA-II was utilized for multi-objective optimization, constructing powerful model ensembles that outperformed the individual GWO-optimized models by up to a 7% in KGE. In comparision to a standard genetic algorithm-based ensemble, the NSGA-II ensemble demonstrated superior effectiveness in balancing solution quality. This innovative approach not only establishes a new benchmark in water quality forecasting but also contributes substantially to proactive environmental monitoring and management strategies.

Effects of digital elevation model resolution on rain-on-grid simulations: a case study in a Slovenian watershed

ABSTRACT The study evaluates the rain-on-grid (RoG) hydraulic model’s sensitivity to digital elevation model (DEM) resolution when simulating an extreme flood in Slovenia. The RoG model is validated against a high-resolution benchmark, showing strong agreement with a Kling-Gupta efficiency of 0.913 and Pearson correlation of 0.964 for a 1 m DEM. Differences are observed in peak shapes and concentration times, attributed to rainfall propagation in RoG grids. DEM resolution significantly impacts performance, with the largest decrease between resolutions of 1 and 5 m. Coarser DEMs yielded higher depths, indicating slope decreases and terrain smoothing. The study concludes that high-resolution DEMs (<1 m) are needed for adequate RoG performance, while commercially available coarser DEMs (30 m) degraded accuracy and should be avoided using this method. Differences from semi-empirical concentration time models are also discussed, and emphasis is placed also on the impacts on water velocity and numerical stability.

Improving Subsurface Soil Moisture Estimation Using a 2‐Dimensional Data Assimilation Framework Incorporated With a Dual State‐Parameter Scheme

AbstractAccurate subsurface soil moisture (SM) estimation is critical for vegetation growth, drought monitoring, and climate change mitigation, yet remains a significant challenge. Previous data assimilation (DA) approaches are limited to only surface SM assimilation. In this study, we utilized the proxy subsurface SM estimated via the exponential filter method (ExpF) as another assimilation variable in our 2‐dimensional DA. Meanwhile, the dual updating DA scheme was implemented to simultaneously update model parameters and states. The two DA pathways were incorporated into the proposed framework (DA_1E_D), which enhanced the subsurface SM accuracy, with the effects of 2‐dimensional assimilation being more significant. Under 2‐dimensional DA, the information transfer between layers was more accurately characterized, leading to overall improvements with unbiased root‐mean‐square error (ubRMSE) reductions of 0.015 and 0.005 m3 · m−3, and Kling–Gupta efficiency (KGE) increases of 0.248 and 0.067 for surface and subsurface SM, respectively, across five SM networks. The soil thickness (d2) and hydraulic conductivity exponent (expt2) are the most influential parameters affecting subsurface SM dynamics through model propagation. DA_1E_D also outperformed ExpF in subsurface SM accuracy, particularly in SM networks with weak surface‐subsurface correlation, achieving an average ubRMSE reduction of 0.003 m3 · m−3 and an average KGE increase of 0.202. It was also applied to Soil Moisture Active Passive data at regional scale, demonstrating significant improvements. The model surface‐subsurface SM coupling was adjusted toward the actual coupling after subsurface assimilation and dual updating. This study may provide new insights into the diagnosis and refinements of the model representation of surface‐subsurface processes.

Runoff Simulation in Data-Scarce Alpine Regions: Comparative Analysis Based on LSTM and Physically Based Models

Runoff simulation is essential for effective water resource management and plays a pivotal role in hydrological forecasting. Improving the quality of runoff simulation and forecasting continues to be a highly relevant research area. The complexity of the terrain and the scarcity of long-term runoff observation data have significantly limited the application of Physically Based Models (PBMs) in the Qinghai–Tibet Plateau (QTP). Recently, the Long Short-Term Memory (LSTM) network has been found to be effective in learning the dynamic hydrological characteristics of watersheds and outperforming some traditional PBMs in runoff simulation. However, the extent to which the LSTM works in data-scarce alpine regions remains unclear. This study aims to evaluate the applicability of LSTM in alpine basins in QTP, as well as the simulation performance of transfer-based LSTM (T-LSTM) in data-scarce alpine regions. The Lhasa River Basin (LRB) and Nyang River Basin (NRB) were the study areas, and the performance of the LSTM model was compared to that of PBMs by relying solely on the meteorological inputs. The results show that the average values of Nash–Sutcliffe efficiency (NSE), Kling–Gupta efficiency (KGE), and Relative Bias (RBias) for B-LSTM were 0.80, 0.85, and 4.21%, respectively, while the corresponding values for G-LSTM were 0.81, 0.84, and 3.19%. In comparison to a PBM- the Block-Wise use of TOPMEDEL (BTOP), LSTM has an average enhancement of 0.23, 0.36, and −18.36%, respectively. In both basins, LSTM significantly outperforms the BTOP model. Furthermore, the transfer learning-based LSTM model (T-LSTM) at the multi-watershed scale demonstrates that, when the input data are somewhat representative, even if the amount of data are limited, T-LSTM can obtain more accurate results than hydrological models specifically calibrated for individual watersheds. This result indicates that LSTM can effectively improve the runoff simulation performance in alpine regions and can be applied to runoff simulation in data-scarce regions.

Satellite-Based PT-SinRH Evapotranspiration Model: Development and Validation from AmeriFlux Data

The Priestley–Taylor model of the Jet Propulsion Laboratory (PT-JPL) evapotranspiration (ET) model is relatively simple and has been widely used based on meteorological and satellite data. However, soil moisture (SM) constraints include a vapor pressure deficit (VPD) that causes large uncertainty. In this study, we proposed a PT-SinRH model by introducing a sine function of air relative humidity (RH) to replace RHVPD to characterize SM constraints, which can improve the accuracy of ET estimations. The PT-SinRH model is validated by eddy covariance (EC) data from 2000–2020. These data were collected by AmeriFlux at 28 sites on the conterminous United States (CONUS), and the land cover types of the sites vary from croplands to wetlands, grasslands, shrub lands and forests. The validation results from daily scale-based on-site and satellite data inputs showed that the PT-SinRH model estimates fit the observations with a coefficient of determination (R2) of 0.55, root-mean-square error (RMSE) of 17.5 W/m2, bias of −1.2 W/m2 and Kling–Gupta efficiency (KGE) of 0.70. Additionally, the PT-SinRH model based on reanalysis and satellite data inputs has an R2 of 0.49, an RMSE of 20.3 W/m2, a bias of −8.6 W/m2 and a KGE of 0.55. The PT-SinRH model showed better accuracy when using the site-measured meteorological data than when using reanalysis meteorological data as inputs. Additionally, compared with the PT-JPL model, the results demonstrate that our approach, i.e., PT-SinRH, improved ET estimates, increasing the R2 and KGE by 0.02 and decreasing the RMSE by about 0.6 W/m2. This simple but accurate method permits us to investigate the decadal variation in regional ET over the land.

Enhancing Hydrological Variable Prediction through Multitask LSTM Models

Deep learning models possess the capacity to accurately forecast various hydrological variables, encompassing flow, temperature, and runoff, notably leveraging Long Short-Term Memory (LSTM) networks to exhibit exceptional performance in capturing long-term dynamics. Nonetheless, these deep learning models often fixate solely on singular predictive tasks, thus overlooking the interdependencies among variables within the hydrological cycle. To address this gap, our study introduces a model that amalgamates Multitask Learning (MTL) and LSTM, harnessing inter-variable information to achieve high-precision forecasting across multiple tasks. We evaluate our proposed model on the global ERA5-Land dataset and juxtapose the results against those of a single-task model predicting a sole variable. Furthermore, experiments explore the impact of task weight allocation on the performance of multitask learning. The results indicate that when there is positive transfer among variables, multitask learning aids in enhancing predictive performance. When jointly forecasting first-layer soil moisture (SM1) and evapotranspiration (ET), the Nash–Sutcliffe Efficiency (NSE) increases by 19.6% and 4.1%, respectively, compared to the single-task baseline model; Kling–Gupta Efficiency (KGE) improves by 8.4% and 6.1%. Additionally, the model exhibits greater forecast stability when confronted with extreme data variations in tropical monsoon regions (AM). In conclusion, our study substantiates the applicability of multitask learning in the realm of hydrological variable prediction.

Comparative Analysis of Snowmelt-Driven Streamflow Forecasting Using Machine Learning Techniques

The rapid advancement of machine learning techniques has led to their widespread application in various domains, including water resources. However, snowmelt modeling remains an area that has not been extensively explored. In this study, we propose a state-of-the-art (SOTA) deep learning sequential model, leveraging a Temporal Convolutional Network (TCN), for snowmelt forecasting of the Hindu Kush Himalayan (HKH) region. To evaluate the performance of our proposed model, we conducted a comparative analysis with other popular models, including Support Vector Regression (SVR), Long Short-Term Memory (LSTM), and Transformer models. Furthermore, nested cross-validation (CV) was used with five outer folds and three inner folds, and hyperparameter tuning was performed on the inner folds. To evaluate the performance of the model, the Mean Absolute Error (MAE), Root-Mean-Square Error (RMSE), R square (R2), Kling–Gupta Efficiency (KGE), and Nash–Sutcliffe Efficiency (NSE) were computed for each outer fold. The average metrics revealed that the TCN outperformed the other models, with an average MAE of 0.011, RMSE of 0.023, R2 of 0.991, KGE of 0.992, and NSE of 0.991 for one-day forecasts of streamflow. The findings of this study demonstrate the effectiveness of the proposed deep learning model as compared to traditional machine learning approaches for snowmelt-driven streamflow forecasting. Moreover, the superior performance of this TCN highlights its potential as a promising deep learning model for similar hydrological applications.

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.

Hybridization of deep learning, nonlinear system identification and ensemble tree intelligence algorithms for pan evaporation estimation

A reliable pan evaporation (Epan) estimation over a daily scale is vital for sustainable water and agriculture management, especially for designing water use allocations, irrigation system management, and demand and utilization assessments. However, designing a reliable computational methodology is a challenging task for Epan estimation due to its stochastic and random characteristics. In this study, the potential of five machine learning (ML) models namely Hammerstein-Weiner (HW), Random Forest (RF), Boosted Regression Tree (BRT), Long Short-Term Memory (LSTM), and Stepwise Linear Regression (SWLR) models were evaluated for Epan modeling in Lake Hawassa catchment, Ethiopia. Afterward, hybrid SWLR-LSTM, SWLR-RF, SWLR-BRT, and SWLR-HW models were developed to benefit from the strength of the non-linear and linear characteristics of the models. The estimation results were evaluated using determination coefficient (R2), Nash-Sutcliffe efficiency (NSE), mean absolute error (MAE) and Root Mean Square Error (RMSE), Index of Agreement (IA) and Kling-Gupta efficiency (KGE). The performance analysis result of individual models showed that the RF model led to more accurate estimation with NSE = 0.938, IA = 0.956, R2 = 0.94, KGE = 0.852, RMSE = 0.483 mm/day and Pbias = -1.193 mm/day during the validation phase. Among the hybrid models, SWLR-RF provides the best predictive performance improving SWLR, HW, LSTM, BRT and RF by 26.563 %, 21.348 %, 15.577 %, 9.091 % and 3.514 %, respectively based on the validation phase NSE value. Generally, the results of the current study demonstrated the capability of deep learning, ensemble tree and hybrid linear-nonlinear models for Epan estimation in the data-scarce catchment.

Combining wavelet-enhanced feature selection and deep learning techniques for multi-step forecasting of urban water demand

Abstract Urban water demand (UWD) forecasting is essential for water supply network optimization and management, both in business-as-usual scenarios, as well as under external climate and socio-economic stressors. Different machine learning and deep learning models have shown promising forecasting skills in various areas of application. However, their potential to forecast multi-step ahead UWD has not been fully explored. Modelling uncertain UWD patterns and accounting for variations in water demand behaviors require techniques that can extract time-varying information and multi-scale changes. In this research, we comparatively investigate different state-of-the-art machine learning- and deep learning-based predictive models on 1-day- and 7-day-ahead UWD forecasting, using daily demand data from the city of Milan, Italy. The contribution of this paper is two-fold. First, we compare the forecasting performance of different machine learning and deep learning models on single- and multi-step daily UWD forecasting. These models include Artificial Neural Network (ANN), Support Vector Regression (SVR), Light Gradient Boosting Machine (LightGBM), and Long Short-Term Memory network with and without an attention mechanism (LSTM and AM-LSTM). We benchmark their prediction accuracy against autoregressive time series models. Second, we investigate the potential enhancement in predictive accuracy by incorporating the wavelet transform and feature selection performed by LightGBM into these models. Results show that, overall, wavelet-enhanced feature selection improves the model predictive performance. The hybrid model combining wavelet-enhanced feature selection via LightGBM with LSTM (WT-LightGBM-(AM)-LSTM) can achieve high levels of accuracy with Nash-Sutcliffe Efficiency larger than 0.95 and Kling–Gupta Efficiency higher than 0.93 for both 1-day- and 7-day-ahead UWD forecasts. Furthermore, performance is shown to be robust under the influence of external stressors causing sudden changes in UWD.

Global-scale evaluation of precipitation datasets for hydrological modelling

Abstract. Precipitation is the most important driver of the hydrological cycle, but it is challenging to estimate it over large scales from satellites and models. Here, we assessed the performance of six global and quasi-global high-resolution precipitation datasets (European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis version 5 (ERA5), Climate Hazards group Infrared Precipitation with Stations version 2.0 (CHIRPS), Multi-Source Weighted-Ensemble Precipitation version 2.80 (MSWEP), TerraClimate (TERRA), Climate Prediction Centre Unified version 1.0 (CPCU), and Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks-Cloud Classification System-Climate Data Record (PERSIANN-CCS-CDR, hereafter PERCCDR) for hydrological modelling globally and quasi-globally. We forced the WBMsed global hydrological model with the precipitation datasets to simulate river discharge from 1983 to 2019 and evaluated the predicted discharge against 1825 hydrological stations worldwide, using a range of statistical methods. The results show large differences in the accuracy of discharge predictions when using different precipitation input datasets. Based on evaluation at annual, monthly, and daily timescales, MSWEP followed by ERA5 demonstrated a higher correlation (CC) and Kling–Gupta efficiency (KGE) than other datasets for more than 50 % of the stations, whilst ERA5 was the second-highest-performing dataset, and it showed the highest error and bias for about 20 % of the stations. PERCCDR is the least-well-performing dataset, with a bias of up to 99 % and a normalised root mean square error of up to 247 %. PERCCDR only show a higher KGE and CC than the other products for less than 10 % of the stations. Even though MSWEP provided the highest performance overall, our analysis reveals high spatial variability, meaning that it is important to consider other datasets in areas where MSWEP showed a lower performance. The results of this study provide guidance on the selection of precipitation datasets for modelling river discharge for a basin, region, or climatic zone as there is no single best precipitation dataset globally. Finally, the large discrepancy in the performance of the datasets in different parts of the world highlights the need to improve global precipitation data products.

Comprehensive Hydrological Analysis of the Buha River Watershed with High-Resolution SHUD Modeling

This study utilizes the Simulator of Hydrologic Unstructured Domains (SHUD) model and the China Meteorological Forces Dataset (CMFD) to investigate the hydrological dynamics of the Buha River watershed, a critical tributary of Qinghai Lake, from 1979 to 2018. By integrating high-resolution terrestrial and meteorological data, the SHUD model simulates streamflow variations and other hydrological characteristics, providing valuable insights into the region’s water balance and runoff processes. Key findings reveal a consistent upward trend in precipitation and temperature over the past four decades, despite minor deviations in daily precipitation intensity and relative humidity data. The SHUD model demonstrates high accuracy on a monthly scale, with Nash–Sutcliffe Efficiency (NSE) values of 0.72 for the calibration phase and 0.61 for the validation phase. The corresponding Kling–Gupta Efficiency (KGE) values are 0.73 and 0.49, respectively, underscoring the model’s applicability for hydrological forecasting and water resource management. Notably, the annual runoff ratios for the Buha River fluctuate annually between 0.11 and 0.21, with significant changes around 2007 correlating with a shift in Qinghai Lake’s water levels. The analysis of water balance indicates a net leakage over long-term periods, with spatial alterations in leakage and replenishment along the river. Furthermore, snow accumulation, which increases with altitude, significantly contributes to streamflow during the melting season. Despite the Buha River basin’s importance, research on its hydrology remains limited due to data scarcity and minimal human activity. This study enhances the understanding of the Buha River’s hydrological processes and highlights the necessity for improved dataset accuracy and model parameter optimization in future research.

IMERG BraMaL: An improved gridded monthly rainfall product for Brazil based on satellite‐based IMERG estimates and machine learning techniques

AbstractPrecipitation is one of the main components of the hydrological cycle and its precise quantification is fundamental to providing information for the understanding and prediction of physical processes. Precipitation observations based on ground‐based devices (manual and automatic rain gauges) are highly accurate but have limited spatial coverage. On the other hand, remote sensing products cover large areas but with lower accuracy. In this context, this study aims to provide a more accurate monthly precipitation estimating product, with lower latency than other products but without directly relying on field data. The methodology consists of applying a machine learning method (k‐nearest neighbours algorithm) to satellite‐based remote sensing data (IMERG Early Run product) and re‐analysis‐based (MERRA‐2) variables with a particular connection to precipitation. The method was applied over the Brazilian territory, which features a large range of precipitation regimes. This methodology resulted in the development of an adjusted IMERG product (IMERG BraMaL). Compared with the original IMERG products (Early Run and Final Run), IMERG BraMaL has improved the evaluated metrics between ground‐based and satellite data in almost all analyses. For instance, KGE (Kling‐Gupta efficiency) went from lower values (0.70 and 0.82 for Early and Late Run, respectively) to values above 0.86 in the IMERG BraMaL. The adjusted product also presented superior performance statistics compared with other global precipitation products (CHIRPS, PERSIANN‐CDR, and MSWEP). The main advantages of IMERG BraMaL compared with IMERG Final Run are (i) much faster availability to the end‐users; (ii) non‐dependency on any field data, allowing its application in areas where rain gauge data is unavailable or of low quality; (iii) the non‐relationship of errors to local features; and (iv) the much‐improved estimations in regions in Brazil where, historically, satellite‐based products usually underestimate the observed data.

Improving runoff simulation in the Western United States with Noah-MP and variable infiltration capacity

Abstract. Streamflow predictions are critical for managing water resources and for environmental conservation, especially in the water-short Western United States. Land surface models (LSMs), such as the variable infiltration capacity (VIC) model and the Noah LSM with multiparameterization options (Noah-MP), play an essential role in providing comprehensive runoff predictions across the region. Virtually all LSMs require parameter estimation (calibration) to optimize their predictive capabilities. Here, we focus on the calibration of VIC and Noah-MP models at a 1/16° latitude–longitude resolution across the Western United States. We first performed global optimal calibration of parameters for both models for 263 river basins in the region. We find that the calibration significantly improves the models' performance, with the median daily streamflow Kling–Gupta efficiency (KGE) increasing from 0.37 to 0.70 for VIC, and from 0.22 to 0.54 for Noah-MP. In general, post-calibration model performance is higher for watersheds with relatively high precipitation and runoff ratios, and at lower elevations. At a second stage, we regionalize the river basin calibrations using the donor-basin method, which establishes transfer relationships for hydrologically similar basins, via which we extend our calibration parameters to 4816 hydrologic unit code (HUC)-10 basins across the region. Using the regionalized parameters, we show that the models' capabilities to simulate high and low flow conditions are substantially improved following calibration and regionalization. The refined parameter sets we developed are intended to support regional hydrological studies and hydrological assessments of climate change impacts.