Streamflow Forecasting Research Articles

Exploring the applicability of the experiment-based ANN and LSTM models for streamflow estimation

The Yeşilırmak River Basin in northern Türkiye is crucial for the region’s water supply, agriculture, hydroelectric power generation, and clean drinking water. The primary goal of this study is to determine which modeling approach is most appropriate for various locations within the basin and how well meteorological data can predict river flow rates. Hydrological and meteorological forecasting both depend on the prediction of river flow rates. An artificial neural network (ANN), Univariate and Multivariate Long Short-Term Memory (LSTM) models have been utilized for streamflow forecasting. This research aims to determine the best model for several provinces in the basin area and give decision-makers a tool for reliable river flow rate estimates by combining LSTM and ANN models. According to research findings, the supervised multivariate LSTM model performed better than the unsupervised model in accuracy and precision. The sliding window methodology is suitable for estimating river flow based on meteorological datasets because it offers a primary method for reinterpreting time-series data in a supervised learning style. Compared to LSTM models, the ANN model that has been statistically optimized through experiments (DoE) design performs better in forecasting the river flow rate in the Yeşilırmak River basin (R2 = 0.98, RMSE = 0.18). The study’s findings provided prospective cognitive models for the strategic management of water resources by forecasting future data from flow monitoring stations.

Performance Evaluation of a National Seven-Day Ensemble Streamflow Forecast Service for Australia

The Australian Bureau of Meteorology offers a national operational 7-day ensemble streamflow forecast service covering regions of high environmental, economic, and social significance. This semi-automated service generates streamflow forecasts every morning and is seamlessly integrated into the Bureau’s Hydrologic Forecasting System (HyFS). Ensemble rainfall forecasts, European Centre for Medium-Range Weather Forecasts (ECMWF), and Poor Man’s Ensemble (PME), available in the Numerical Weather Prediction (NWP) suite, are used to generate these streamflow forecasts. The NWP rainfall undergoes pre-processing using the Catchment Hydrologic Pre-Processer (CHyPP) before being fed into the GR4H rainfall–runoff model, which is embedded in the Short-term Water Information Forecasting Tools (SWIFT) hydrological modelling package. The simulated streamflow is then post-processed using Error Representation and Reduction In Stages (ERRIS). We evaluated the performance of the operational rainfall and streamflow forecasts for 96 catchments using four years of operational data between January 2020 and December 2023. Performance evaluation metrics included the following: CRPS, relative CRPS, CRPSS, and PIT-Alpha for ensemble forecasts; NSE, PCC, MAE, KGE, PBias, and RMSE; and three categorical metrics, CSI, FAR, and POD, for deterministic forecasts. The skill scores, CRPS, relative CRPS, CRPSS, and PIT-Alpha, gradually decreased for both rainfall and streamflow as the forecast horizon increased from Day 1 to Day 7. A similar pattern emerged for NSE, KGE, PCC, MAE, and RMSE as well as for the categorical metrics. Forecast performance also progressively decreased with higher streamflow volumes. Most catchments showed positive performance skills, meaning the ensemble forecast outperformed climatology. Both streamflow and rainfall forecast skills varied spatially across the country—they were generally better in the high-runoff-generating catchments, and poorer in the drier catchments situated in the western part of the Great Dividing Range, South Australia, and the mid-west of Western Australia. We did not find any association between the model forecast skill and the catchment area. Our findings demonstrate that the 7-day ensemble streamflow forecasting service is robust and draws great confidence from agencies that use these forecasts to support decisions around water resource management.

Synergistic approach for streamflow forecasting in a glacierized catchment of western Himalaya using earth observation and machine learning techniques

Synergistic approach for streamflow forecasting in a glacierized catchment of western Himalaya using earth observation and machine learning techniques

Event-based evaluation of operational ENSO forecasting models in 2002–2020: Implications for seasonal water resources management

Given the practical implications of El Niño-Southern Oscillation (ENSO) forecasting for developing decision support systems and its importance in global climate prediction on seasonal to interannual scales, significant efforts have been made to enhance ENSO forecasts. This study presents an event-based evaluation of ENSO forecasts and discusses the implications of such forecasts to water resources management. Using ENSO forecasts for the period 2002–2020, this study evaluates and compares the results of two types of forecasting models, i.e., statistical and dynamical models, in predicting Sea Surface Temperatures (SSTs). Forecasting skills are evaluated for distinct target seasons via two metrics, spearman correlation and mean squared error. In addition, the performance of the two types of models at different lead times are also evaluated. Results reveal that the forecasting skills of these models are comparable, both of which exhibit higher forecasting skills for the boreal fall-winter season and lower skills for the boreal spring season. Event-based analyses show that dynamical and statistical models under-forecast SST anomaly at the onset month for El Niño events, although the forecasting error diminishes with a reduced forecasting lead for most occasions. For La Niña events, SST anomaly forecasting errors could be positive or negative. It is also difficult for the models to accurately predict the quick shift from one ENSO phase to another. Factors that contribute to such challenges are discussed. The implication of ENSO forecasts for water resources management, mainly streamflow forecasts, for a regional water supply utility in the southeastern United States is also discussed. Results from this study provide insights into ENSO forecasting skills and their practical implications.

Ensemble learning using multivariate variational mode decomposition based on the Transformer for multi-step-ahead streamflow forecasting

Accurate streamflow forecasting is critical in the domain of water resources management. However, the inherently non-stationary and stochastic nature of streamflow poses a significant challenge to achieving accuracy in streamflow forecasting. In this study, we introduce an MVMD-ensembled Transformer model (MVMD-Transformer), which incorporates the MVMD for concurrent time–frequency analysis of streamflow and related potential influencing variables. The model aligns common modes in the decomposition results, ensuring that the different variables corresponding to each mode have the same center frequency. This alignment overcomes frequency mismatches and helps uncover the intrinsic patterns and essential features between streamflow and associated variables. During the forecasting phase, the Transformer component of the MVMD-Transformer model establishes connections among streamflow and other influencing variables across pairs of nodes in each mode. We tested the performance of the MVMD-Transformer model in forecasting streamflow across 1-, 3-, 5-, and 7-day horizons within the Shiyang River, Heihe River, and Shule River basins situated in the Hexi Corridor of Northwest China. The MVMD-Transformer model harnesses MVMD to concurrently decompose both predictor variables (precipitation, air temperature, air pressure, soil moisture) and the response variable (streamflow). Subsequently, the modes drived from the MVMD were fed into the Transformer, serving as the predictive analytics engine, to forecast streamflow. Furthermore, we conducted a comprehensive performance evaluation by comparing the MVMD-Transformer model against four alternatives: the VMD-ensembled Transformer model (VMD-Transformer), CEEMDAN-ensembled Transformer model (CEEMDAN-Transformer), stand-alone Transformer model, and LSTM model. The results indicate that MVMD-Transformer outperformed all other models, achieving Nash-Sutcliffe coefficient (NSE) values exceeding 0.85 in the majority of the forecasting scenarios. This superior performance highlights the proficiency of the MVMD approach in more accurately unraveling the intricate interdependencies between streamflow and its various potential influencing variables, thus significantly improving the precision of streamflow forecasting.

River stream flow prediction through advanced machine learning models for enhanced accuracy

The Narmada River basin, a significant water resource in central India, plays a crucial role in supporting agricultural, industrial, and domestic water supply. Effective management of this basin requires accurate streamflow forecasting, which has become increasingly important. This study delves into streamflow forecasting using historical data from five major river stations, covering the upper reaches in the East and middle sections. The dataset spans from 1978 to 2020 and undergoes rigorous screening and preparation, including normalization using StandardScaler. The research adopts a comprehensive approach, developing models for training on 70 % of historical data, validation on the most current 15 %, and testing against future targets with another 15 % of the data. To achieve precise predictions, a suite of machine learning models is employed, including CatBoost, LGBM (Light Gradient Boosting Machine), Random Forest, and XGBoost. Performance evaluation of these models relies on key indices such as mean squared error (MSE), mean absolute error (MAE), root mean square error (RMSE), root mean square percent error (RMSPE), normalized root mean squared error (NRMSE), and R-squared (R2). Notably, among these models, Random Forest emerges as the most robust for streamflow prediction, showcasing its effectiveness in handling the complexities of hydrological forecasting. This research contributes significantly to the field of streamflow forecasting in the Narmada River basin by providing insights into the performance of various machine learning models. The findings not only enhance our understanding of watershed dynamics but also highlight the pivotal role that machine learning can play in improving hydrological forecasting for sustainable watershed management.

Daily Streamflow Forecasting Using Networks of Real-Time Monitoring Stations and Hybrid Machine Learning Methods

Considering the increased risk of urban flooding and drought due to global climate change and rapid urbanization, the imperative for more accurate methods for streamflow forecasting has intensified. This study introduces a pioneering approach leveraging the available network of real-time monitoring stations and advanced machine learning algorithms that can accurately simulate spatial–temporal problems. The Spatio-Temporal Attention Gated Recurrent Unit (STA-GRU) model is renowned for its computational efficacy in forecasting streamflow events with a forecast horizon of 7 days. The novel integration of the groundwater level, precipitation, and river discharge as predictive variables offers a holistic view of the hydrological cycle, enhancing the model’s accuracy. Our findings reveal that for a 7-day forecasting period, the STA-GRU model demonstrates superior performance, with a notable improvement in mean absolute percentage error (MAPE) values and R-square (R2) alongside reductions in the root mean squared error (RMSE) and mean absolute error (MAE) metrics, underscoring the model’s generalizability and reliability. Comparative analysis with seven conventional deep learning models, including the Long Short-Term Memory (LSTM), the Convolutional Neural Network LSTM (CNNLSTM), the Convolutional LSTM (ConvLSTM), the Spatio-Temporal Attention LSTM (STA-LSTM), the Gated Recurrent Unit (GRU), the Convolutional Neural Network GRU (CNNGRU), and the STA-GRU, confirms the superior predictive power of the STA-LSTM and STA-GRU models when faced with long-term prediction. This research marks a significant shift towards an integrated network of real-time monitoring stations with advanced deep-learning algorithms for streamflow forecasting, emphasizing the importance of spatially and temporally encompassing streamflow variability within an urban watershed’s stream network.

Exploring the potential of deep learning for streamflow forecasting: A comparative study with hydrological models for seasonal and perennial rivers

Improving streamflow prediction plays a significant role in flood warning, mitigation and development purposes. Therefore, this paper aims to compare the prediction capability of a useful conceptual hydrologic model hydrologiska byråns vattenbalansavdelning (HBV) enhanced and equipped with an automatic calibration procedure (Genetic Algorithm) along with two well-known deep learning (DL) algorithms, including Long-Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). This study was concentrated on the daily streamflow of two river basins with diverse climatic and hydrological conditions, namely the Halilrood River with fragmented and intermittent flows (located in Iran) and the Tweed River with a permanent stream flow (Located across the border of Scotland and northern England). These were particularly selected to address both seasonal and perennial riverine cases. For reproducing the streamflow, 10-year records of the daily discharge, precipitation, and temperature (from satellite and ground resources), and evapotranspiration were used as the main input data. The accuracy of the implemented models was assessed using several indices. The findings show that 1) the LSTM and GRU show better accuracy than the employed hydrologic model for estimating daily discharges (especially in the seasonal river basin); 2) the DL approaches need only meteorological data inputs (precipitation and temperature) and are independent of involved uncertainties in hydrological modeling such as physical characteristics of basins; and 3) best streamflow simulations were achieved by the LSTM (best agreement with the observations). In general, LSTM has the highest priority to be connected with online hydrological rainfall-runoff simulations and dynamical forecast models.

Monthly streamflow forecasting based on meteorological data from a nearby station

ABSTRACT Monthly streamflow forecasting is critical for improving water resource management. In this study, several base-classifier data-mining algorithms – conjunctive rule (CR), isotonic regression (ISOR), sequential minimal optimization regression (SMOR) – as well as several hybrid data-mining techniques – disjoint aggregating or dagging (DA)-CR, DA-ISOR, and DA-SMOR – that combine dagging with these algorithms were developed and applied to forecasting streamflow 3 and 12 months into the future (i.e., Qt+3 and Qt+12) based on meteorological data from a nearby station. Thirty years of data (from 1988 to 2018) that included precipitation, minimum relative humidity, maximum relative humidity, evaporation, hours of sunshine, maximum temperature, minimum temperature, wind speed, and streamflow were collected at the Kermanshah synoptic station were input to develop and evaluate several models. Varying combinations of the input data were tested to find the optimal set to employ. The models were validated and compared using several quantitative statistical indices. Though all satisfactorily predicted monthly streamflow, the hybrid models (DA-CR, DA-ISOR, and DA-SMOR) outperformed the base-classifier models (CR, ISOR, and SMOR), proving that dagging improved data-mining models significantly. Of the hybrid models, D-SMOR was the best. The models developed in this study are cost-effective tools for quick and accurate monthly streamflow forecasting.

Influence of long-term observed trends on the performance of seasonal hydroclimate forecasts

Skillful forecasts of hydroclimate variables are essential for operational water management, agricultural planning, and food supply. Several studies have attempted to improve the skill of raw forecasts either by post-processing or by incorporating sea surface conditions into raw forecasts. However, to the best of our knowledge, limited to no study has investigated temporal trend, which is present in observed records but is absent from retrospective forecasts (also known as, hindcasts). The current study understands that a temporal trend can be yielded in raw meteorological forecasts by i) updating surface boundary forcings and ii) applying statistical models for either post-processing meteorological forecasts or issuing streamflow forecasting using weather forecasts as predictors. To analytically derive the relationship between temporal trend and forecast performance, this study applies three statistical approaches for post-processing season-ahead hindcasts of the Indian monsoon obtained from three general circulation models (GCM). The findings show that raw hindcasts of the Indian monsoons typically ignore the temporal trend present in the observed records. Furthermore, analytical derivations confirm that the absence of a trend in GCM hindcasts significantly influences post-processing performance. Moreover, a semi-parametric approach could not overcome the limitations of a parametric linear model in yielding a temporal trend in the hindcasts. Potential reasons for the absence of a trend in the hindcast is also discussed.

Investigating the potential of EMA-embedded feature selection method for ESVR and LSTM to enhance the robustness of monthly streamflow forecasting from local meteorological information

Accurate forecast of monthly streamflow is helpful to improve the social capability in risk management. Diverse input features are crucial to the accuracy of machine learning-based monthly streamflow forecast models. The embedded feature selection (EFS) method based on binary-coded metaheuristic algorithm is adept at parallel optimization of feature selection and model hyperparameter. It has been rarely studied coupled with deep learning models in monthly streamflow forecasting. This study further investigated the potential of EFS method using the well-known Long short-term memory network (LSTM) and a state-of-the-art model named Extreme support vector regression (ESVR), with the Evolutionary mating algorithm (EMA) as the search algorithm. The benchmark models were established using EMA for hyperparameter optimization without feature selection. Ten basins with distinct hydroclimate characteristics minimally impacted by human activities from the Catchment Attributes and Meteorology for Large-sample Studies (CAMELS) data set were used to comprehensively examine the proposed models. Nonparametric approaches including the Friedman test and Wilcoxon signed ranks test were utilized to rank the models and detect the significance of the performance variation brought by EFS. The kernel ESVR model coupled with EFS-EMA (EFS-KESVREMA) ranked the first in the 1-month-ahead experiment with NSE = 0.734–0.944. EFS-ESVREMA and EFS-LSTMEMA ranked second and third, with NSE = 0.746–0.94 and NSE = 0.701–0.94 respectively. The results also demonstrated that EFS-EMA helps the benchmark models improve prediction accuracy at a confidence level of 95 % but it has no obvious effect on the standard SVR. As the forecast horizon increased to 3- and 5-month-ahead, EFS-ESVREMA maintained a reliable performance. Whereas EFS-LSTMEMA experienced a significant accuracy decrease in the 5-month-ahead experiment. The proposed models and relevant findings in this study have certain reference value for researchers in monthly streamflow forecasting.

A hybrid model enhancing streamflow forecasts in paddy land use-dominated catchments with numerical weather prediction model-based meteorological forcings

The development of a streamflow forecasting tool becomes a challenging task due to the sophisticated nonlinear catchment response, varying crop management practices, and limited in situ data availability. For real-time streamflow forecasting with up to 10-days lead-time, this study investigates the potential of SWAT-pothole (PSWAT) module forced with bias-corrected Global Forecasting System (GFS) meteorological variables; wherein the error-updating is carried out for the streamflow forecasts simulated by PSWAT. The error is updated by hierarchical data-driven sub-models, such as AutoRegressive (AR), AutoRegressive Moving Average with eXogenous inputs (ARMAX), Wavelet-based Neural Network (WNN), Wavelet-based Non-linear AutoRegressive with eXogenous inputs (WNARX), Long-Short Term Memory (LSTM), and a novel Wavelet-based Bidirectional LSTM (WBiLSTM). The efficacy of the standalone PSWAT module is tested against the hybrid models in the Brahmani-Baitarani (≈ 49,000 km2) compound River Basin in eastern India. The results revealed that the novel PSWAT-WBiLSTM hybrid model is the best for reliable streamflow forecasts up to 8-days’ and 9-days’ lead-times in the Brahmani and Baitarani River basins, respectively. Conclusively, this model can be a potential medium-range streamflow forecasting tool for paddy-dominated catchments.

On time-horizons based post-processing of flow forecasts

Post-processing raw stream flow forecasts are generally understood as estimating the univariate predictive density of stage or discharge values at selected future time steps, which is conditional on a single or multiple streamflow forecasts and observations up to the forecast start time to. The predictive density indicates to a forecaster in the most comprehensive way which flood level is likely to be expected. To this end, a variety of post-processing methods were proposed, which have respective strengths and weaknesses. These methods focus near-exclusively on the probabilistic forecast of the predictand at a single set future time ti, without addressing the predictive capability over the sequence of temporal sub-horizons (to, t1] ⊂ (to, t2] ⊂ … ⊂ (to, tk] nested into the overall forecast horizon. Here, we demonstrate the advantages of time-horizon dependent processing of streamflow forecasts, which evaluates the evolution of the predictive density over the sub-horizons by considering the temporal correlation among forecast ensemble members in addition to their cross-correlation with observations. The resulting probabilistic forecast consists of a multivariate distribution of stages and/or discharges at lagged forecasting times. These multivariate predictive distributions have the advantage of providing the likelihood of exceeding a critical threshold during the forecasting horizon while simultaneously offering valuable insights into the expected time of such exceedance. This approach supports not only decisions on issuing timely flood warnings but also the planing and roll-out of mitigating actions.

The Forecast of Streamflow through Göksu Stream Using Machine Learning and Statistical Methods

Forecasting streamflow in stream basin systems plays a crucial role in facilitating effective urban planning to mitigate floods. In addition to employing intricate hydrological modeling systems, machine learning and statistical techniques offer an alternative means for streamflow forecasts. Nonetheless, the precision and dependability of these methods are subjects of paramount importance. This study rigorously investigates the effectiveness of three distinct machine learning techniques and two statistical approaches when applied to streamflow data from the Göksu Stream in the Marmara Region of Turkey, spanning from 1984 to 2022. Through a comparative analysis of these methodologies, this examination aims to contribute innovative advancements to the existing methodologies used in the prediction of streamflow data. The methodologies employed include machine learning methods such as Extreme Gradient Boosting (XGBoost), Random Forest (RF), and Support Vector Machine (SVM) and statistical methods such as Simple Exponential Smoothing (SES) and Autoregressive Integrated Moving Average (ARIMA) model. In the study, 444 data points between 1984 and 2020 were used as training data, and the remaining data points for the period 2021–2022 were used for streamflow forecasting in the test validation period. The results were evaluated using various metrics, such as the correlation coefficient (r), mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), coefficient of determination (R2), and Nash–Sutcliffe efficiency (NSE). Upon analyzing the results, it was found that the model generated using the XGBoost algorithm outperformed other machine learning and statistical techniques. Consequently, the models implemented in this study demonstrate a high level of accuracy in predicting potential streamflow in the river basin system.

An explainable multiscale LSTM model with wavelet transform and layer-wise relevance propagation for daily streamflow forecasting

Developing an accurate and reliable daily streamflow forecasting model is important for facilitating the efficient resource planning and management of hydrological systems. In this study, an explainable multiscale long short-term memory (XM-LSTM) model is proposed for effective daily streamflow forecasting by integrating the à trous wavelet transform (ATWT) for decomposing data, the Boruta algorithm for identifying model inputs, and the layer-wise relevance propagation (LRP) for explaining the prediction results. The proposed XM-LSTM is tested by performing multi-step-ahead forecasting of daily streamflow at four stations in the middle and lower reaches of the Yangtze River basin and compared with the X-LSTM. The X-LSTM is formed by coupling the long short-term memory (LSTM) with the LRP. For comparison, the inputs of these two models are identified by the Boruta selection algorithm. The results show that all models exhibit good ability to forecast daily streamflow, however, the prediction performance decreases as the lead time increases. The XM-LSTM provides a better forecasting performance than the X-LSTM, suggesting the ability of the ATWT to improve the LSTM for daily streamflow forecasting. Moreover, the correlation scores analysis by the LRP shows that the ATWT can extract useful information that influences the daily streamflow from the raw predictors, and the water level has the most significant contribution to streamflow prediction. Accordingly, the XM-LSTM model can be viewed as a potentially useful approach for increasing the accuracy and explainability of streamflow forecasting.

Выбор методов прогнозирования речного стока

The selection of methods for streamflow forecasting is considered, taking into account factors that limit the lead time and accuracy of forecasts, consumer requirements, and the results of applying these methods for specific water bodies. Methods that allow their mass implementation in an automated mode are recommended as the most effective. Examples of successful implementation of these recommendations in streamflow forecasting in Russia based on the methods developed at the Hydrometcentre of Russia are shown. The proposed recommendations are aimed to increase the scientific validity and efficiency of implementing operational decisions on the use of water resources and protection from dangerous hydrological events.

Краткосрочное и среднесрочное прогнозирование стока рек бассейна Дона

For the rivers of the Don basin, the Hydrometcentre of Russia has developed a methodology for daily short- and medium-range forecasting of streamflow and water levels. Average daily discharges and water levels are predicted throughout the year with a lead time of 1 to 10 days based on the hydrograph extrapolation method, which takes into account their values for the date of the forecast and for the previous 5 days. To estimate the parameters of the forecasting scheme, hydrological observation data for each river section are used. The technique gives satisfactory results and can be used within the framework of an automated system for preparing and issuing forecasts in order to provide necessary forecast information for making operational decisions on the use of water resources of the Don basin rivers and protecting the population from dangerous floods.

A novel additive regression model for streamflow forecasting in German rivers

Forecasting streamflows, essential for flood mitigation and the efficient management of water resources for drinking, agriculture and hydroelectric power generation, presents a formidable challenge in most real-world scenarios. In this study, two models, the first based on the Additive Regression of Radial Basis Function Neural Networks (AR-RBF) and the second based on the stacking with the Pace Regression of the Multilayer Perceptron and Random Forest (MLP-RF-PR), were compared for the prediction of short-term (1–3 days ahead) and medium-term (7 days ahead) daily streamflow rates of three different rivers in Germany: the Elbe River at Wittenberge, the Leine River at Herrenhausen, and the Saale River at Hof. The lagged values of streamflow rate, precipitation and temperature were considered for the modeling. Moreover, the Bayesian Optimization (BO) algorithm was used to assess the optimal number of lagged values and hyperparameters. Both models showed accurate predictions for short-term forecasting, with R2 for 1-day ahead predictions ranging from 0.939 to 0.998 for AR-RBF and from 0.930 to 0.996 for MLP-RF-PR, while MAPE ranged from 2.02 % to 8.99 % for AR-RBF and from 2.14 % to 9.68 % for MLP-RF-PR, when exogeneous variables were included. As the forecast horizon increased, a reduction in forecasting accuracy was observed. However, both models could still predict the overall flow pattern, even for 7-day-ahead predictions, with R2 ranging from 0.772 to 0.871 for AR-RBF and from 0.703 to 0.840 for MLP-RF-PR, while MAPE ranged from 10.60 % to 20.45 % for AR-RBF and from 10.44 % to 19.65 % for MLP-RF-PR. Overall, the outcomes of this study suggest that both AR-RBF and MLP-RF-PR can be reliable tools for the short- and medium-term streamflow rate prediction, requiring a short number of parameters to be optimized, making them easy to implement while reducing the calculation time required.

Dynamic Bayesian-Network-Based Approach to Enhance the Performance of Monthly Streamflow Prediction Considering Nonstationarity

In recognizing the pervasive nonstationarity of hydrometeorological variables, a paradigm shift towards alternative analytical methodologies is imperative for refining hydroclimatic data modeling and prediction. We introduce a novel approach leveraging nonstationary Graphical Modeling and Bayesian Networks (NGM-BNs) tailored for hydrometeorological applications. Demonstrated through monthly streamflow forecasting in the Kashgar River Basin of China, our method illuminates the temporal evolution of network relationships, underscoring the dynamism inherent in both input variables and modeling parameters. The key to our approach is identifying the most suitable time horizon (MST) for model updates, which is intricately problem-specific and crucial for peak performance. This methodology not only unveils changing predictor significance across varying flow conditions but also elucidates the fluctuating temporal links between variables, especially under the lens of climate change, for instance, the growing impact of snowmelt on the Kashgar Basin’s streamflow. Compared to stationary counterparts, our nonstationary Bayesian framework excels in capturing extreme events by adeptly accommodating temporal shifts, outperforming traditional models including both stationary and nonstationary variants of Support Vector Regression (SVR) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS).

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.