Search Results (58)

This Scoping Review methodically synthesizes methodological trends in predictive uncertainty (PU) quantification for short-to-seasonal hydrological modeling-based forecasting. The analysis encompasses 572 studies from 2017 to 2024, with the objective of addressing the central question: What are the emerging trends, best practices, and gaps in this field? In accordance with the six-stage protocol that is aligned with PRISMA-ScR standards, 92 studies were selected for in-depth evaluation. The results of the study indicate the presence of three predominant patterns: (1) exponential growth in the applications of machine learning and artificial intelligence; (2) geographic concentration in Chinese, North American, and European watersheds; and (3) persistent operational barriers, particularly in data-scarce tropical regions with limited flood and streamflow forecasting validation. Hybrid statistical-AI modeling frameworks have been shown to enhance forecast accuracy and PU quantification; however, these frameworks are encumbered by constraints in computational demands and interpretability, with inadequate validation for extreme events highlighting critical gaps. The review emphasizes standardized metrics, broader validation, and adaptive postprocessing to enhance applicability, advocating robust frameworks integrating meteorological input to hydrological output postprocessing for minimizing uncertainty chains and supporting water management. This study provides an updated field mapping, identifies knowledge gaps, and prioritizes research for the operational integration of advanced PU quantification. Full article

The Sylhet Division of Bangladesh, highly susceptible to monsoon flooding, requires effective flood risk management to reduce socio-economic losses. Flood frequency analysis is an essential aspect of flood risk management and plays a crucial role in designing hydraulic structures. This study applies regional flood frequency analysis (RFFA) using L-moments to identify homogeneous hydrological regions and estimate extreme flood quantiles. Records from 26 streamflow gauging stations were used, including streamflow data along with corresponding physiographic and climatic characteristic data, obtained from GIS analysis and ERA5 respectively. Most stations showed no significant monotonic trends, temporal correlations, or spatial dependence, supporting the assumptions of stationarity and independence necessary for reliable frequency analysis, which allowed the use of cluster analysis, discordancy measures, heterogeneity tests for regionalization, and goodness-of-fit tests to evaluate candidate distributions. The Generalized Logistic (GLO) distribution performed best, offering robust quantile estimates with narrow confidence intervals. Multiple Non-Linear Regression models, based on catchment area, elevation, and other parameters, reasonably predicted ungauged basin peak discharges (R² = 0.61–0.87; RMSE = 438–2726 m³/s; MAPE = 41–74%) at different return periods, although uncertainty was higher for extreme events. Four homogeneous regions were identified, showing significant differences in hydrological behavior, with two regions yielding stable estimates and two exhibiting greater extreme variability. Full article

The study aims to assess future streamflow forecasts in the Godavari basin of India under climate change scenarios. The primary objective of the Coupled Model Inter-comparison Project Phase 6 (CMIP6) was to evaluate future streamflow forecasts across different catchments in the Godavari basin, India, with an emphasis on understanding the impacts of climate change. This study employed both conceptual and machine learning models to assess how changing precipitation patterns and temperature variations influence streamflow dynamics. Seven satellite precipitation products CMORPH, Princeton Global Forcing (PGF), Tropical Rainfall Measuring Mission (TRMM), Climate Prediction Centre (CPC), Infrared Precipitation with Stations (CHIRPS), and Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks (PERSIANN-CDR) were evaluated in a gridded precipitation evaluation over the Godavari River basin. Results of Multi-Source Weighted-Ensemble Precipitation (MSWEP) had a Nash–Sutcliffe efficiency (NSE), coefficient of determination (R²), and root mean square error (RMSE) of 0.806, 0.831, and 56.734 mm/mon, whereas the Tropical Rainfall Measuring Mission had 0.768, 0.846, and 57.413 mm, respectively. MSWEP had the highest accuracy, the lowest false alarm ratio, and the highest Peirce’s skill score (0.844, 0.571, and 0.462). Correlation and pairwise correlation attribution approaches were used to assess the input parameters, which included a two-day lag of streamflow, maximum and minimum temperatures, and several precipitation datasets (IMD, EC-Earth3, EC-Earth3-Veg, MIROC6, MRI-ESM2-0, and GFDL-ESM4). CMIP6 datasets that had been adjusted for bias were used in the modeling process. R, NSE, RMSE, and R² assessed the model’s effectiveness. RF and M5P performed well when using CMIP6 datasets as input. RF demonstrated adequate performance in testing (0.4 < NSE < 0.50 and 0.5 < R² < 0.6) and extremely good performance in training (0.75 < NSE < 1 and 0.7 < R < 1). Likewise, M5P demonstrated good performance in both training and testing (0.4 < NSE < 0.50 and 0.5 < R² < 0.6). While RF was the best performer for both datasets, Indian Meteorological Department outperformed all CMIP6 datasets in streamflow modeling. Using the Indian Meteorological Department gridded precipitation, RF’s NSE, R, R², and RMSE values during training were 0.95, 0.979, 0.937, and 30.805 m³/s. The test results were 0.681, 0.91, 0.828, and 41.237 m³/s. Additionally, the Multi-Layer Perceptron (MLP) model demonstrated consistent performance across both the training and assessment phases, reinforcing the reliability of machine learning approaches in climate-informed hydrological forecasting. This study underscores the significance of incorporating climate change projections into hydrological modeling to enhance water resource management and adaptation strategies in the Godavari basin and similar regions facing climate-induced hydrological shifts. Full article

Recent studies have shown the potential of transformer-based neural networks in increasing prediction capacity. However, classical transformers present several problems such as computational time complexity and high memory requirements, which make Long Sequence Time-Series Forecasting (LSTF) challenging. The contribution to the prediction of time series of flood events using deep learning techniques is examined, with a particular focus on evaluating the performance of the Informer model (a particular implementation of transformer architecture), which attempts to address the previous issues. The predictive capabilities of the Informer model are explored and compared to statistical methods, stochastic models and traditional deep neural networks. The accuracy, efficiency as well as the limits of the approaches are demonstrated via numerical benchmarks relating to real river streamflow applications. Using daily flow data from the River Test in England as the main case study, we conduct a rigorous evaluation of the Informer efficacy in capturing the complex temporal dependencies inherent in streamflow time series. The analysis is extended to encompass diverse time series datasets from various locations (>100) in the United Kingdom, providing insights into the generalizability of the Informer. The results highlight the superiority of the Informer model over established forecasting methods, especially regarding the LSTF problem. For a forecast horizon of 168 days, the Informer model achieves an NSE of 0.8 and maintains a MAPE below 10%, while the second-best model (LSTM) only achieves −0.63 and 25%, respectively. Furthermore, it is observed that the dependence structure of time series, as expressed by the climacogram, affects the performance of the Informer network. Full article

In recent years, deep learning (DL) methods, such as recurrent neural networks (RNN). have been used for streamflow prediction. In this study, the monthly inflow into the Dez Dam reservoir from 1955 to 2018 in southwestern Iran was simulated using various types of RNNs, including long short-term memory (LSTM), bidirectional long short-term memory (Bi-LSTM), gated recurrent unit (GRU), and stacked long short-term memory (Stacked LSTM). It was observed that considering flow discharge, temperature, and precipitation as inputs to the models yields the best results. Additionally, wavelet transform was employed to enhance the accuracy of the RNNs. Among the RNNs, the GRU model exhibited the best performance in simulating monthly streamflow without using wavelet transform, with RMSE, MAE, NSE, and R² values of 0.061 m³/s, 0.038 m³/s, 0.556, and 0.642, respectively. Moreover, in the case of using wavelet transform, the Bi-LSTM model with db5 mother wavelet and decomposition level 5 was able to simulate the monthly streamflow with high accuracy, yielding RMSE, MAE, NSE, and R² values of 0.014 m³/s, 0.008 m³/s, 0.9983, and 0.9981, respectively. Uncertainty analysis was conducted for the two mentioned superior models. To quantify the uncertainty, the concept of the 95 percent prediction uncertainty (95PPU) and the p-factor and r-factor criteria were utilized. For the GRU, the p-factor and r-factor values were 82% and 1.28, respectively. For the Bi-LSTM model, the p-factor and r-factor values were 94% and 1.06, respectively. The obtained p-factor and r-factor values for both models are within the acceptable and reliable range. Full article

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. Full article

Changes in water quality are closely linked to seasonal fluctuations in streamflow, and a thorough understanding of how these variations interact across different time scales is important for the efficient management of surface water bodies such as rivers, lakes, and reservoirs. The aim of this study is to explore the potential connection between streamflow, rainfall, and water quality and propose an optimised ensemble model for the prediction of a water quality index (WQI). This study modelled the changes in five water quality parameters such as ammonia nitrogen (NH₃-N), phosphate (PO₄³⁻), pH, turbidity, total dissolved solids (TDS), and their associated WQI caused by rainfall and streamflow. The analysis was conducted across three temporal scales, weekly, monthly, and seasonal, using a generalised additive model (GAM) in Toowoomba, Australia. TDS, turbidity, and WQI exhibited a significant nonlinear variation with the changes in streamflow in the weekly and monthly scales. Additionally, pH demonstrated a significant linear to weakly linear correlation with discharge across the three temporal scales. For the accurate prediction of WQI, this study proposed an ensemble model integrating an extreme gradient boosting (XGBoost) and Bayesian optimisation (BO) algorithm, using streamflow as an input across the same temporal scales. The results for the three temporal scales provided the best accuracy of monthly data, based on the accuracy metrics R² (0.91), MAE (0.20), and RMSE (0.42). The comparison between the test and predicted data indicated that the prediction model overestimated the WQI at some points. This study highlights the efficiency of integrating rainfall, streamflow, and water quality correlations for WQI prediction, which can provide valuable insights for guiding future water management strategies in similar catchment areas, especially amidst changing climatic conditions. Full article

This study examines the contribution of rainfall data (RF) in improving the streamflow-forecasting accuracy of advanced machine learning (ML) models in the Syr Darya River Basin. Different sets of scenarios included rainfall data from different weather stations located in various geographical locations with respect to the flow monitoring station. Long short-term memory (LSTM)-based models were used to examine the contribution of rainfall data on streamflow-forecasting performance by investigating five scenarios whereby RF data from different weather stations were incorporated depending on their geographical positions. Specifically, the All-RF scenario included all rainfall data collected at 11 stations; Upstream-RF (Up-RF) and Downstream-RF (Down-RF) included only the rainfall data measured upstream and downstream of the streamflow-measuring station; Pearson-RF (P-RF) only included the rainfall data exhibiting the highest level of correlation with the streamflow data, and the Flow-only (FO) scenario included streamflow data. The evaluation metrics used to quantitively assess the performance of the models included the RMSE, MAE, and the coefficient of determination, R². Both ML models performed best in the FO scenario, which shows that the diversity of input features (hydrological and meteorological data) did not improve the predictive accuracy regardless of the positions of the weather stations. The results show that the P-RF scenarios yielded better prediction accuracy compared to all the other scenarios including rainfall data, which suggests that only rainfall data upstream of the flow monitoring station tend to make a positive contribution to the model’s forecasting performance. The findings evidence the suitability of simple monolayer LSTM-based networks with only streamflow data as input features for high-performance and budget-wise river flow forecast applications while minimizing data processing time. Full article

Streamflow prediction is crucial for planning future developments and safety measures along river basins, especially in the face of changing climate patterns. In this study, we utilized monthly streamflow data from the United States Bureau of Reclamation and meteorological data (snow water equivalent, temperature, and precipitation) from the various weather monitoring stations of the Snow Telemetry Network within the Upper Colorado River Basin to forecast monthly streamflow at Lees Ferry, a specific location along the Colorado River in the basin. Four machine learning models—Random Forest Regression, Long short-term memory, Gated Recurrent Unit, and Seasonal AutoRegresive Integrated Moving Average—were trained using 30 years of monthly data (1991–2020), split into 80% for training (1991–2014) and 20% for testing (2015–2020). Initially, only historical streamflow data were used for predictions, followed by including meteorological factors to assess their impact on streamflow. Subsequently, sequence analysis was conducted to explore various input-output sequence window combinations. We then evaluated the influence of each factor on streamflow by testing all possible combinations to identify the optimal feature combination for prediction. Our results indicate that the Random Forest Regression model consistently outperformed others, especially after integrating all meteorological factors with historical streamflow data. The best performance was achieved with a 24-month look-back period to predict 12 months of streamflow, yielding a Root Mean Square Error of 2.25 and R-squared ($R^2$) of 0.80. Finally, to assess model generalizability, we tested the best model at other locations—Greenwood Springs (Colorado River), Maybell (Yampa River), and Archuleta (San Juan) in the basin. Full article

Accurate monthly streamflow prediction is crucial for effective flood mitigation and water resource management. The present study proposes an innovative similarity-derived model (SDM), developed based on the observation that similar monthly streamflow patterns recur across different years under comparable hydrological and climate conditions. The model is applied to the Lancang River Basin in China. The model performance is compared with the commonly used support vector machine (SVM) and Mean methods. Evaluation measures such as RMSE, MAPE, and NSE confirm that SDM6 with a reference period of six months achieves the best performance, improving the Mean model by 79.9 m³/s in RMSE, 6.07% in MAPE, and 8.62% in NSE, and the SVM by 53.65 m³/s, 0.24%, and 5.53%, respectively. Full article

This paper presents two hydrological models developed for the Euphrates–Tigris Basin in Turkey. The first model is a linear regression-based model allowing the estimation of streamflow based on available hydroclimatic data (precipitation, temperature, evapotranspiration, etc.) with the use of clustering analysis. The second model consists of an elevation-based semi-distributed hydrological model (HBV model), allowing process-based modelling of the watershed. A set of performance metrics identified the HBV model as the best performance in terms of predicting streamflow (NSE = 0.752), while the RCA4-EU regression model of CORDEX showed the most robust performance. The results show the potential of regression models from a computational and data point of view in being integrated into physically based models wherein a hybrid approach might be beneficial. The comparison of conceptual models with statistical analyses of streamflow shows the potential of regression analysis when the regions are clustered in hydro-meteorologically homogeneous groups. The employment of the conceptual model HBV also provides significantly robust streamflow estimation for the region, which is especially important in estimating the hydropower potential of the region’s near future. Full article

Hydrological reaction to climate change anticipates water cycle alterations. To ensure long-term water availability and accessibility, it is essential to develop sustainable water management strategies and better hydrological models that can simulate peak flow. These efforts will aid in water resource planning, management, and climate change mitigation. This study develops and compares Sacramento, Australian Water Balance Model (AWBM), TANK, and SIMHYD conceptual models to simulate daily streamflow at Rajegaon station of the Pranhita subbasin in the Godavari basin of India. The study uses daily Indian Meteorological Department (IMD) gridded rainfall and temperature datasets. For 1987–2019, 70% of the models were calibrated and 30% validated. Pearson correlation (CC), Nash Sutcliffe efficiency (NSE), Root mean square error (RMSE), and coefficient of determination (CD) between the observed and simulated streamflow to evaluate model efficacy. The best conceptual (Sacramento) model selected to forecast future streamflow for the SSP126, SSP245, SSP370, and SSP585 scenarios for the near (2021–2040), middle (2041–2070), and far future (2071–2100) using EC-Earth3 data was resampled and bias-corrected using distribution mapping. In the far future, the SSP585 scenario had the most significant relative rainfall change (55.02%) and absolute rise in the annual mean temperature (3.29 °C). In the middle and far future, the 95th percentile of monthly streamflow in the wettest July is anticipated to rise 40.09% to 127.06% and 73.90% to 215.13%. SSP370 and SSP585 scenarios predicted the largest streamflow increases in all three time periods. In the near, middle, and far future, the SSP585 scenario projects yearly relative streamflow changes of 72.49%, 93.80%, and 150.76%. Overall, the findings emphasize the importance of considering the potential impacts of future scenarios on water resources to develop effective and sustainable water management practices. Full article

Having a complete hydrological time series is crucial for water-resources management and modeling. However, this can pose a challenge in data-scarce environments where data gaps are widespread. In such situations, recurring data gaps can lead to unfavorable outcomes such as loss of critical information, ineffective model calibration, inaccurate timing of peak flows, and biased statistical analysis in various applications. Despite its importance, predicting monthly streamflow can be a complex task due to its connection to random dynamics and uncertain phenomena, posing significant challenges. This study introduces an ensemble machine-learning regression framework for modeling and predicting monthly streamflow time series with a high degree of accuracy. The framework utilizes historical data from multiple monthly streamflow datasets in the same region to predict missing monthly streamflow data. The framework selects the best features from all available gap-free monthly streamflow time-series combinations and identifies the optimal model from a pool of 12 machine-learning models, including random forest regression, gradient boosting regression, and extra trees regressor, among others. The model selection is based on cross-validation train-and-test set scores, as well as the coefficient of determination. We conducted modeling on 26 monthly streamflow time series and found that the gradient boosting regressor with bagging regressor produced the highest accuracy in 7 of the 26 instances. Across all instances, the models using this method exhibited an overall accuracy range of 0.9737 to 0.9968. Additionally, the use of either a bagging regressor or an AdaBoost regressor improved both the tree-based and gradient-based models, resulting in these methods accounting for nearly 80% of the best models. Between January 1960 and December 2021, an average of 40% of the monthly streamflow data was missing for each of the 26 stations. Notably, two crucial stations located in the economically significant lower Athabasca Basin River in Alberta province, Canada, had approximately 70% of their monthly streamflow data missing. To address this issue, we employed our framework to accurately extend the missing data for all 26 stations. These accurate extensions also allow for further analysis, including grouping stations with similar monthly streamflow behavior using Pearson correlation. Full article

Streamflow modelling is one of the most important elements for the management of water resources and flood control in the context of future climate change. With the advancement of numerical weather prediction and modern detection technologies, more and more high-resolution hydro-meteorological data can be obtained, while traditional physical hydrological models cannot make full use of them. In this study, a hybrid deep learning approach is proposed for the simulation of daily streamflow in two mountainous catchments of the Daqing River Basin, northern China. Two-dimensional high-resolution (1 km) output data from a WRF model were used as the model input, a convolutional neural network (CNN) model was used to extract the physical and meteorological characteristics of the catchment at a certain time, and the long short-term memory (LSTM) model was applied to simulate the streamflow using the time-series data extracted by the CNN model. To reduce model input noise and avoid overfitting, the Gamma test method was adopted and the correlations between the input variables were checked to select the optimal combination of input variables. The performance of the CNN-LSTM models was acceptable without using the Gamma test (i.e., with all WRF input variables included), with NSE and RMSE values of 0.9298 and 9.0047 m³/s, respectively, in the Fuping catchment, and 0.8330 and 1.1806 m³/s, respectively, in the Zijingguan catchment. However, it was found that the performance of the model could be significantly improved by the use of the Gamma test. Using the best combination of input variables selected by the Gamma test, the NSE of the Fuping catchment increased to 0.9618 and the RMSE decreased to 6.6366 m³/s, and the NSE of the Zijingguan catchment increased to 0.9515 and the RMSE decreased to 0.6366 m³/s. These results demonstrate the feasibility of the CNN-LSTM approach for flood streamflow simulation using WRF-downscaled high-resolution data. By using this approach to assess the potential impacts of climate change on streamflow with the abundant high-resolution meteorological data generated by different climate scenarios, water managers can develop more effective strategies for managing water resources and reducing the risks associated with droughts and floods. Full article

Streamflow prediction plays a vital role in water resources planning in order to understand the dramatic change of climatic and hydrologic variables over different time scales. In this study, we used machine learning (ML)-based prediction models, including Random Forest Regression (RFR), Long Short-Term Memory (LSTM), Seasonal Auto- Regressive Integrated Moving Average (SARIMA), and Facebook Prophet (PROPHET) to predict 24 months ahead of natural streamflow at the Lees Ferry site located at the bottom part of the Upper Colorado River Basin (UCRB) of the US. Firstly, we used only historic streamflow data to predict 24 months ahead. Secondly, we considered meteorological components such as temperature and precipitation as additional features. We tested the models on a monthly test dataset spanning 6 years, where 24-month predictions were repeated 50 times to ensure the consistency of the results. Moreover, we performed a sensitivity analysis to identify our best-performing model. Later, we analyzed the effects of considering different span window sizes on the quality of predictions made by our best model. Finally, we applied our best-performing model, RFR, on two more rivers in different states in the UCRB to test the model’s generalizability. We evaluated the performance of the predictive models using multiple evaluation measures. The predictions in multivariate time-series models were found to be more accurate, with RMSE less than 0.84 mm per month, R-squared more than 0.8, and MAPE less than 0.25. Therefore, we conclude that the temperature and precipitation of the UCRB increases the accuracy of the predictions. Ultimately, we found that multivariate RFR performs the best among four models and is generalizable to other rivers in the UCRB. Full article