Explore the vast range of titles available.

Management of the freshwater resources in a sustained manner requires the information and understanding of the surface water hydrology and streamflow is of key importance in this nexus. This study evaluates the performance of eight different precipitation products (APHRODITE, CHRS CCS, CHRS CDR, CHIRPS, CPC Global, GPCC, GPCP, and PERSIANN) for streamflow prediction in two sub-catchments (Chirah and Dhoke Pathan) of the data-scarce Soan River Basin (SRB) in Pakistan. A modified version of the hydrological model HBV (Hydrologiska Byråns Vattenbalansavdelning) known as HBV-light was used to generate streamflow. The model was separately calibrated and validated with observed and estimated precipitation data for streamflow simulation with optimized parameterization. The values of R2, NSE, KGE and PBIAS obtained during the calibration (validation) period for the Chirah sub-catchment were 0.64, 0.64, 0.68 and −5.6% (0.82, 0.81, 0.88 and 7.4%). On the other hand, values of R2, NSE, KGE, and PBIAS obtained during the calibration (validation) period for the Dhoke Pathan sub-catchment were 0.85, 0.85, 0.87, and −3.4% (0.82, 0.7, 0.73 and 6.9%). Different ranges of values were assigned to multiple efficiency evaluation metrics and the performance of precipitation products was assessed. Generally, we found that the performance of the precipitation products was improved (higher metrics values) with increasing temporal and spatial scale. However, our results showed that APHRODITE was the only precipitation product that outperformed other products in simulating observed streamflow at both temporal scales for both Chirah and Dhoke Pathan sub-catchments. These results suggest that with the long-term availability of continuous precipitation records with fine temporal and spatial resolutions, APHRODITE has the high potential to be used for streamflow prediction in this semi-arid river basin. Other products that performed better were GPCC, GPCP, and CHRS CCS; however, their scope was limited either to one catchment or a specific time scale. These results will also help better understand surface water hydrology and in turn, would be useful for better management of the water resources.

The management of water resources depends heavily on hydrological prediction, and advances in machine learning (ML) present prospects for improving predictive modelling capabilities. This study investigates the use of a variety of widely used machine learning algorithms, such as CatBoost, ElasticNet, k-Nearest Neighbors (KNN), Lasso, Light Gradient Boosting Machine Regressor (LGBM), Linear Regression (LR), Multilayer Perceptron (MLP), Random Forest (RF), Ridge, Stochastic Gradient Descent (SGD), and the Extreme Gradient Boosting Regression Model (XGBoost), to predict the river inflow of the Garudeshwar watershed, a key element in planning for flood control and water supply. The substantial engineering feature used in the study, which incorporates temporal lag and contextual data based on Indian seasons, leads it distinctiveness. The study concludes that the CatBoost method demonstrated remarkable performance across various metrics, including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R-squared (R2) values, for both training and testing datasets. This was accomplished by an in-depth investigation and model comparison. In contrast to CatBoost, XGBoost and LGBM demonstrated a higher percentage of data points with prediction errors exceeding 35% for moderate inflow numbers above 10,000. CatBoost established itself as a reliable method for hydrological time-series modelling, easily managing both categorical and continuous variables, and thereby greatly enhancing prediction accuracy. The results of this study highlight the value and promise of widely used machine learning algorithms in hydrology and offer valuable insights for academics and industry professionals.

This study proposes a new hybrid model for monthly streamflow predictions by coupling a physically based distributed hydrological model with a deep learning (DL) model. Specifically, a simplified hydrological model is first developed by optimally selecting grid cells from a distributed hydrological model according to their soil moisture characteristics. It is then driven by bias corrected general circulation model (GCM) predictions to generate soil moistures for the forecasting months. Finally, model‐simulated soil moisture along with other predictors from multiple sources are used as inputs of the DL model to predict future monthly streamflows. The proposed hybrid model, using the simplified Variable Infiltration Capacity (VIC) as the hydrological model and the combination of Convolutional Neural Network and Gated Recurrent Unit (CNN‐GRU) as the DL model, is applied to predict 1‐, 3‐, and 6‐month ahead reservoir inflows for the Danjiangkou Reservoir in China. The results show that the hybrid model consistently performs better than VIC and CNN‐GRU models with great improvement in Kling‐Gupta efficiency (KGE) values for lead times up to 6 months. Additional tests indicate that hybrid models based on CNN‐GRU outperform those based on LASSO, XGBoost, CNN, and GRU models. Moreover, compared with the distributed hydrological model, the hybrid model greatly reduces the computation burden of rolling prediction. It also saves decision‐makers the time and effort of trying different combinations of predictors, which is indispensable when building DL models. Overall, the new hybrid model demonstrates great potential for monthly streamflow prediction where training data are limited. Key Points Deep learning and physically based distributed hydrological models are coupled for monthly streamflow predictions A simplified hydrological model is developed on the basis of the distributed model to reduce computational cost in streamflow predictions The hybrid model is an efficient and accurate surrogate tool for real‐time monthly streamflow predictions

Accurate rainfall-runoff modeling is crucial for effective watershed management, hydraulic infrastructure safety, and flood mitigation. However, predicting rainfall-runoff remains challenging due to the nonlinear interplay between hydro-meteorological and topographical variables. This study introduces a hybrid Gaussian process regression (GPR) model integrated with K-means clustering (GPR-K-means) for short-term rainfall-runoff forecasting. The Orgeval watershed in France serves as the study area, providing hourly precipitation and streamflow data spanning 1970–2012. The performance of the GPR-K-means model is compared with standalone GPR and principal component regression (PCR) models across four forecasting horizons: 1-hour, 6-hour, 12-hour, and 24-hour ahead. The results reveal that the GPR-K-means model significantly improves forecasting accuracy across all lead times, with a Nash-Sutcliffe Efficiency (NSE) of approximately 0.999, 0.942, 0.891, and 0.859 for 1-hour, 6-hour, 12-hour, and 24-hour forecasts, respectively. These results outperform other ML models, such as Long Short-Term Memory, Support Vector Machines, and Random Forest, reported in the literature. The GPR-K-means model demonstrates enhanced reliability and robustness in hourly streamflow forecasting, emphasizing its potential for broader application in hydrological modeling. Furthermore, this study provides a novel methodology for combining clustering and Bayesian regression techniques in surface hydrology, contributing to more accurate and timely flood prediction.

Long-term streamflow forecasting is a critical step when planning and managing water resources. Advanced techniques in deep learning have been proposed for forecasting streamflow. Applying these methods in long-term streamflow prediction is an issue that has received less attention. Four models, including Adaptive Neuro-Fuzzy Inference Systems (ANFIS), Artificial Neural Networks (ANN), Bidirectional Long-Short Term Memory (BiLSTM), and hybrid Convolutional Neural Network (CNN)-Gated Recurrent Unit (GRU)-LSTM, are applied to forecast the long-term daily streamflow of the Colorado River in the U.S. The proper time lag for input series creation is determined using partial autocorrelation. 60% of the data (1921–1981) is used for training, whereas 40% (1981–2021) is used to evaluate the model’s performance. The results of the studied models are assessed by Using four indices: the Mean Absolute Error (MAE), the Normalized Root Mean Square Error (NRMSE), the Correlation Coefficient (r), and the Nash–Sutcliffe Coefficient (ENS). As a result of the testing step, the ANFIS model with NRMSE = 0.118, MAE = 26.16 (m3/s), r = 0.966, and ENS = 0.933 was more accurate than other studied models. Despite their complexity, the BiLSTM and CNN-GRU-LSTM models did not outperform the others. Comparing these models to ANN and ANFIS, it is evident that their performance is not superior.

Streamflow estimation plays a significant role in water resources management, especially for flood mitigation, drought warning, and reservoir operation. Hence, the current study examines the prediction capability of three well-known machine learning algorithms (Support Vector Regression (SVR), Artificial Neural Network with backpropagation (ANN-BP), and Extreme Learning Machine (ELM)) for the monthly and daily streamflows of four rivers in the United States. For model development, three main predictor variables (P, Tmax, and Tmin) and their antecedent values were considered. The SVM-RFE feature selection method was used to select the most appropriate predictor variable.The performance of the developed models was tested using four evaluation statistics. The results indicate that (1) except some improvements, the accuracy of all models decreases at the daily scale compared to that at the monthly scale; (2) the SVR has the best performance among the three models at the monthly and daily scales, while the ANN-BP model has the worse performance; (3) the ELM has better generalization performance than the ANN-BP for streamflow simulation at the monthly and daily scales; and (4) all models fail to predict the streamflow for the Carson River as a snowmelt-dominated basin. Generally, findings of the current study indicate that the SVR model produces better results than the ELM and ANN-BP for streamflow simulation at the monthly and daily scales.

Physically based hydrologic models require significant effort and extensive information for development, calibration, and validation. The study explored the use of the random forest regression (RFR), a supervised machine learning (ML) model, as an alternative to the physically based Soil and Water Assessment Tool (SWAT) for predicting streamflow in the Rio Grande Headwaters near Del Norte, a snowmelt-dominated mountainous watershed of the Upper Rio Grande Basin. Remotely sensed data were used for the random forest machine learning analysis (RFML) and RStudio for data processing and synthesizing. The RFML model outperformed the SWAT model in accuracy and demonstrated its capability in predicting streamflow in this region. We implemented a customized approach to the RFR model to assess the model’s performance for three training periods, across 1991–2010, 1996–2010, and 2001–2010; the results indicated that the model’s accuracy improved with longer training periods, implying that the model trained on a more extended period is better able to capture the parameters’ variability and reproduce streamflow data more accurately. The variable importance (i.e., IncNodePurity) measure of the RFML model revealed that the snow depth and the minimum temperature were consistently the top two predictors across all training periods. The paper also evaluated how well the SWAT model performs in reproducing streamflow data of the watershed with a conventional approach. The SWAT model needed more time and data to set up and calibrate, delivering acceptable performance in annual mean streamflow simulation, with satisfactory index of agreement (d), coefficient of determination (R2), and percent bias (PBIAS) values, but monthly simulation warrants further exploration and model adjustments. The study recommends exploring snowmelt runoff hydrologic processes, dust-driven sublimation effects, and more detailed topographic input parameters to update the SWAT snowmelt routine for better monthly flow estimation. The results provide a critical analysis for enhancing streamflow prediction, which is valuable for further research and water resource management, including snowmelt-driven semi-arid regions.

Some previous studies have proved that prediction models using traditional overall decomposition sampling (ODS) strategy are unreasonable because the subseries obtained by the ODS strategy contain future information to be predicted. It is, therefore, necessary to put forward a new sampling strategy to fix this defect and also to improve the accuracy and reliability of decomposition-based models. In this paper, a stepwise decomposition sampling (SDS) strategy according to the practical prediction process is introduced. Moreover, an innovative input selection framework is proposed to build a strong decomposition-based monthly streamflow prediction model, in which sunspots and atmospheric circulation anomaly factors are employed as candidate input variables to enhance the prediction accuracy of monthly streamflow in addition to regular inputs such as precipitation and evaporation. Meanwhile, the partial correlation algorithm is employed to select optimal input variables from candidate input variables including precipitation, evaporation, sunspots, and atmospheric circulation anomaly factors. Four basins of the U.S. MOPEX project with various climate characteristics were selected as a case study. Results indicate that: (1) adding teleconnection factors into candidate input variables helps enhance the prediction accuracy of the support vector machine (SVM) model in predicting streamflow; (2) the innovative input selection framework helps to improve the prediction capacity of models whose candidate input variables interact with each other compared with traditional selection strategy; (3) the SDS strategy can effectively prevent future information from being included into input variables, which is an appropriate substitute of the ODS strategy in developing prediction models; (4) as for monthly streamflow, the hybrid variable model decomposition-support vector machine (VMD-SVM) models, using an innovative input selection framework and the SDS strategy, perform better than those which have not adopted this framework in all study areas. Generally, the findings of this study showed that the hybrid VMD-SVM model combining the SDS strategy and innovative input selection framework is a useful and powerful tool for practical hydrological prediction work in the context of climate change.

From a watershed management perspective, streamflow need to be predicted accurately using simple, reliable, and cost-effective tools. Present study demonstrates the first applications of a novel optimized deep-learning algorithm of a convolutional neural network (CNN) using BAT metaheuristic algorithm (i.e., CNN-BAT). Using the prediction powers of 4 well-known algorithms as benchmarks – multilayer perceptron (MLP-BAT), adaptive neuro-fuzzy inference system (ANFIS-BAT), support vector regression (SVR-BAT) and random forest (RF-BAT), the CNN-BAT model is tested for daily streamflow (Qt) prediction in the Korkorsar catchment in northern Iran. Fifteen years of daily rainfall (Rt) and streamflow data from 1997 to 2012 were collected and used for model development and evaluation. The dataset was divided into two groups for building and testing models. The correlation coefficient (r) between rainfall and streamflow with and without antecedent events (i.e., Rt-1, Rt-2, etc.) (as the input variables) and Qt (as the output variable) served as the basis for constructing different input scenarios. Several quantitative and visually-based evaluation metrics were used to validate and compare the model’s performance. The results indicate that Rt was the most effective input variable on Qt prediction and the integration of Rt, Rt-1, and Qt-1 was the optimal input combination. The evaluation metrics show that the CNN-BAT algorithm outperforms the other algorithms. The Friedman and Wilcoxon signed-rank test indicates that the prediction power of CNN-BAT algorithm is significantly/statistically different from the other developed algorithms.

Daily hydrological modelling is among the most challenging tasks in water resource management, particularly in terms of streamflow prediction in semi-arid areas. Various methods were applied in order to deal with this complex phenomenon, but recently data-driven models have taken a better space, given their ability to solve prediction problems in time series. In this study, we have employed the Long Short-Term Memory (LSTM) network to simulate the daily streamflow over the Ait Ouchene watershed (AIO) in the Oum Er-Rbia river basin in Morocco, based on a temporal sequence of in situ and remotely sensed hydroclimatic data ranging from 2001 to 2010. The analysis adopted in this work is based on three-dimension input required by the LSTM model (1); the input samples used three splitting approaches: 70% of the dataset as training, splitting the data considering the hydrological year and the cross-validation method; (2) the sequence length; (3) and the input features using two different scenarios. The prediction results demonstrate that the LSTM performs poorly using the default data input scenario, whereas the best results during the testing were found in a sequence length of 30 days using approach 3 (R2 = 0.58). In addition, the LSTM fed with the lagged data input scenario using the Forward Feature Selection (FFS) method provides high performance accuracy using approach 2 (R2 = 0.84) in a sequence length of 20 days. Eventually, in applications related to water resources management where data are limited, the use of the deep learning technique is able to create high predictive accuracy, which can be enhanced with the right combination subset of features by using FFS.