Monthly Streamflow Forecasting Using ELM-IPSO Based on Phase Space Reconstruction

We have developed a hybrid model that integrates chaos theory and an extreme learning machine with optimal parameters selected using an improved particle swarm optimization (ELM-IPSO) for monthly runoff analysis and prediction. Monthly streamflow data covering a period of 55 years from Daiying hydrological station in the Chaohe River basin in northern China were used for the study. The Lyapunov exponent, the correlation dimension method, and the nonlinear prediction method were used to characterize the streamflow data. With the time series of the reconstructed phase space matrix as input variables, an improved particle swarm optimization was used to improve the performance of the extreme learning machine. Finally, the optimal chaotic ensemble learning model for monthly streamflow prediction was obtained. The accuracy of the predictions of the streamflow series (linear correlation coefficient of about 0.89 and efficiency coefficient of about 0.78) indicate the validity of our approach for predicting streamflow dynamics. The developed method had a higher prediction accuracy compared with an auto-regression method, an artificial neural network, an extreme learning machine with genetic algorithm and with PSO algorithm, suggesting that ELM-IPSO is an efficient method for monthly streamflow prediction.

     

Methodology for Estimating Streamflow by Water Balance and Rating Curve Methods Based on Logistic Regression

Both water balance (WB) and rating curve (RC) are methods for estimating streamflow. The first is mostly used to estimate reservoir outflows, while the second is usually adopted in hydrometeorological network streamflow gauges. While WB uses hourly collected data, the RC estimates streamflow using current water level and extrapolation techniques. The objective of this study was to analyze variations in the reservoir’s hourly outflow at Queimado Hydroelectric Power Plant (HPP Queimado) and to propose a method to evaluate whether the estimate of the daily outflows, obtained by the WB method, is similar to the flow values obtained at a conventional station. The logistic regression (LR) model was used because it is a method that adopts binary, categorically dependent variables to identify the event of interest. The results showed that the values of streamflow, obtained from an average of two daily readings, were a good representation of the flows in the region. The LR was able to identify atypical data, especially in the rainy season. This means that data consistency analysis can be faster and safer, when adequately employed and considering the proposed conditions, contributing to both management policies and the management of water resources.

     

Performance Enhancement of Rainfall Pattern – Water Level Prediction Model Utilizing Self-Organizing-Map Clustering Method

During recent two decades, Artificial Neural Network (ANN) has become one of the most widely used methods in hydrology. One solution for better capturing the existing non-linear and complex nature of data is to develop new hybrid approaches. These hybrid models can be developed in a way that two or more techniques are combined in order to benefit from the advantages of these available approaches and eliminate their limitations. The main scope of this paper is to improve the performance of rainfall-water level modeling by combining ANN with Self Organizing Map (SOM) as an unsupervised clustering method. The proposed method in this study consists of two phases. In the first phase, with the aim of reducing the complexity and dimensionality of input data, a two-step clustering using SOM technique is carried out. Then, in the second phase, separate ANN models are used to model each cluster of data, and final results are obtained by combining the outputs of all models. The proposed new hybrid approach is evaluated using real hydrological data of Johor River. The results of the study indicate that the new proposed SOM-ANN hybrid model has a better performance in daily rainfall-water level forecasting compared to ANN model alone.     

An Ensemble Modeling Approach to Forecast Daily Reservoir Inflow Using Bidirectional Long- and Short-Term Memory (Bi-LSTM), Variational Mode Decomposition (VMD), and Energy Entropy Method

Daily inflow forecasts provide important decision support for the operations and management of reservoirs. Accurate and reliable forecasting plays an important role in the optimal management of water resources. Numerous studies have shown that decomposition integration models have good prediction capacity. Considering the nonlinearity and unsteady state of daily incoming flow data, a hybrid model of adaptive variational mode decomposition (VMD) and bidirectional long- and short-term memory (Bi-LSTM) based on energy entropy was developed for daily inflow forecast. The model was analyzed using the mean absolute error (MAE), the root means square error (RMSE), Nash–Sutcliffe efficiency coefficient (NSE), and correlation coefficient (r). A historical daily inflow series of the Baozhusi Hydropower Station, China, is investigated by the proposed VMD-BiLSTM with hybrid models. For comparison, BP, GRNN, ELMAN, SVR, LSTM, Bi-LSTM, EMD-LSTM, and VMD-LSTM, were adopted and analyzed for evaluation and analyzed. We found that the proposed model, with MAE?=?38.965, RMSE?=?64.783, and NSE?=?95.7%, was superior to the other models. Therefore, the hybrid model is robust and efficient for forecasting highly nonstationary and nonlinear streamflow. It can be used as the preferred data-driven tool to predict the daily inflow flow, which can ensure the safe operation of hydropower stations in reservoirs. As an interdisciplinary field spanning both machine learning and hydrology, daily inflow forecasting can become an important breakthrough in the application of deep learning to hydrology.

     

Season Algorithm-Multigene Genetic Programming: A New Approach for Rainfall-Runoff Modelling

Genetic programming (GP) is recognized as a robust machine learning method for rainfall-runoff modelling. However, it may produce lagged forecasts if autocorrelation feature of runoff series is not taken carefully into account. To enhance timing accuracy of GP-based rainfall-runoff models, the paper proposes a new rainfall-runoff model that integrates season algorithm (SA) with multigene-GP (MGGP). The proposed SA-MGGP model was trained and validated for single- and two- and three-day ahead streamflow forecasts at Haldizen Catchment, Trabzon, Turkey. Timing and prediction accuracy of the proposed model were assessed in terms of different efficiency criteria. In addition, the efficiency results were compared to those of monolithic GP, MGGP, and SA-GP forecasting models developed in the present study as the benchmarks. The outcomes indicated that SA augments timing accuracy of GP-based models in the range 250% to 500%. It is also found that MGGP may identify underlying structure of the rainfall-runoff process slightly better than monolithic GP at the study catchment.     

A Novel Hybrid Decompose-Ensemble Strategy with a VMD-BPNN Approach for Daily Streamflow Estimating

Streamflow estimation is highly significant for water resource management. In this work, we improve the accuracy and stability of streamflow estimation through a novel hybrid decompose-ensemble model that employs variational mode decomposition (VMD) and back-propagation neural networks (BPNN). First, the latest decomposition algorithm, namely, VMD, was used to extract multiscale features that were subsequently learned and ensembled by the BPNN model to obtain the final estimate streamflow results. The historical daily streamflow series of Laoyukou and Wushan hydrological stations in China were analysed by VMD-BPNN, by a single GBRT and BPNN model, ensemble empirical mode decomposition (EEMD) models. The results confirmed that the VMD outperformed a single-estimation model without any decomposition and EEMD-based models; moreover, ensemble estimations using the BPNN model development technique were consistently better than a general summation method. The VMD-BPNN model’s estimation performance was superior to that of five other models at the Wushan station (GBRT, BPNN, EEMD-BPNN-SUM, VMD-BPNN-SUM, and EEMD-BPNN) using evaluation criteria of the root-mean-square error (RMSE?=?2.62 m³/s), the Nash–Sutcliffe efficiency coefficient (NSE?=?0. 9792) and the mean absolute error (MAE?=?1.38 m³/s). The proposed model also had a better performance in estimating higher-magnitude flows with a low criterion for MAE. Therefore, the hybrid VMD-BPNN model could be applied as a promising approach for short-term streamflow estimating.

     

Improving Annual Streamflow Prediction by Extracting Information from High-frequency Components of Streamflow

Annual streamflow prediction is of great significance to the sustainable utilization of water resources, and predicting it accurately is challenging due to changes in streamflow have strong nonlinearity and uncertainty. To improve the prediction accuracy of annual streamflow, this study proposes a new hybrid prediction model based on extracting information from high-frequency components of streamflow. In the proposed model, the original streamflow data is decomposed by ensemble empirical mode decomposition (EEMD) into several intrinsic mode functions (IMFs) with different frequencies. Then, the dominant component and residual component are identified from the high-frequency components IMF1 and IMF2 using singular spectrum analysis (SSA), and the residual components are accumulated as a new component. Finally, all the components, including the new component that is not noise, are modelled by support vector machine (SVM), and the SVM is optimized by grey wolf optimizer (GWO). To analyse and verify the proposed model, the annual streamflow data are collected from the Liyuan River and Taolai River in the Heihe River Basin, and six models, autoregressive integrated moving average (ARIMA), cross validation (CV)-SVM, GWO-SVM, EEMD-ARIMA, EEMD-GWO-SVM and modified EEMD-GWO-SVM are considered as comparison models. The results indicate that the prediction performance of the proposed model is obviously better than that of other reference models, and extracting valuable information from high-frequency components can effectively improve annual streamflow prediction. Thus, the high-frequency components contained in the original streamflow series have an important impact on obtaining accurate streamflow prediction, and the proposed model makes full use of the high-frequency components and provides a reliable method for streamflow prediction.

     

A Comparative Study of Linear Stochastic with Nonlinear Daily River Discharge Forecast Models

Accurate forecast of the magnitude and timing of the flood peak river discharge and the extent of inundated areas during major storm events are a vital component of early warning systems around the world that are responsible for saving countless lives every year. This study assesses the forecast accuracy of two different linear and non-linear approaches to predict the daily river discharge. A new linear stochastic method is produced by evaluating a detailed comparison between three pre-processing approaches, differencing, standardization, spectral analysis, and trend removal. Daily river discharge values of the Bow River with strong seasonal and non-seasonal correlations located in Alberta, Canada were utilized in this study. The stochastic term for this daily flow time series is calculated with an auto-regressive integrated moving average. We found that seasonal differencing is the best stationarization method for periodic effect elimination. Moreover, the proposed non-linear Group Method of Data Handling (GMDH) model could overcome the known accuracy limitations of the classical GMDH models that use only two inputs in each neuron from the adjacent layer. The proposed new non-linear GMDH-based method (named GS-GMDH) can improve the structure of the classical linear GMDH. The GS-GMDH model produced the most accurate forecasts in the Bow River case study with statistical indices such as the coefficient of determination and Nash-Sutcliffe for the daily discharge time series higher than 97% and relative error less than 6%. Finally, an explicit equation for estimation of the daily discharge of the Bow River is developed using the proposed GS-GMDH model to showcase the practical application of the new method in flood forecasting and management.

     

Stochastic Simulation of Daily Suspended Sediment Concentration Using Multivariate Copulas

An estimation of daily suspended sediment concentration (SSC) is required for water resource and environmental management. The traditional methods for simulating daily SSC focus on modeling the SSCs themselves, whereas the cross-correlation structure between SSC and streamflow has received only minor attention. To address this issue, we propose a stochastic method to generate long-term daily SSC using multivariate copula functions that account for temporal and cross dependences in daily SSCs. We use the conditional copula method to construct daily multivariate distributions to alleviate the complications and workload of parameter estimations using high-dimensional copulas. The observed daily streamflow and SSC data are normalized using the normal quantile transform method to relax the computationally intensive model of building daily marginal distributions. Daily SSCs can thus be simulated through the multivariate conditional distribution using previous daily SSC and concurrent daily streamflow values. The proposed method is rigorously examined by application to a case study at the Pingshan station in the Jinsha River Basin, China, and compared with the bivariate copula method. The results show that the proposed method has a high degree of accuracy, in preserving the statistics and temporal correlation of daily SSC observations, and better preserves the lag-0 cross correlation compared with the bivariate copula method. The multivariate copula framework proposed here can accurately and efficiently generate long-term daily SSC data for water resource and environmental management, which play a critical role in accurately estimating the frequency and magnitude of extreme SSC events.

     

Long Term Streamflow Forecasting Using a Hybrid Entropy Model

In this paper, the development and evaluation of an entropy based hybrid data driven model coupled with input selection approach and wavelet transformation is investigated for long-term streamflow forecasting with 10 years lead time. To develop and test the models, data including 45 years of monthly streamflow time series from Taleghan basin, located in northwest of Tehran, are employed. For this purpose, first the performance of a maximum entropy forecasting model is evaluated. To boost the accuracy, an auto-correlation method with %95 confidence levels was carried out to determine the optimum order of the entropy model. Nevertheless, the basic entropy model, as expected, was only able to reach Nash-Sutcliffe efficiency (NSE) index of 0.35 during the test period. On the other hand, data driven models such as artificial neural networks (ANN) have shown to yield good accuracy in modeling complicated and nonlinear systems. Thus, to improve the performance of the maximum entropy model, an entropy-based hybrid model using evolutionary ANN (ENN) was proposed for further investigation. The proposed model with seasonality index substantially improved the test NSE to 0.51 and provided more accurate results than the basic entropy model. Moreover, when wavelet transform was applied to preprocess the input data, the model shows a slight improvement (NSE?=?0.54).     

Daily Mean Streamflow Prediction in Perennial and Non-Perennial Rivers Using Four Data Driven Techniques

This study examines and compares the performance of four new attractive artificial intelligence techniques including artificial neural network (ANN), hybrid wavelet-artificial neural network (WANN), Genetic expression programming (GEP), and hybrid wavelet-genetic expression programming (WGEP) for daily mean streamflow prediction of perennial and non-perennial rivers located in semi-arid region of Zagros mountains in Iran. For this purpose, data of daily mean streamflow of the Behesht-Abad (perennial) and Joneghan (non-perennial) rivers as well as precipitation information of 17 meteorological stations for the period 1999–2008 were used. Coefficient of determination (R²) and root mean square error (RMSE) were used for evaluating the applicability of developed models. This study showed that although the GEP model was the most accurate in predicting peak flows, but in overall among the four mentioned models in both perennial and non-perennial rivers, WANN had the best performance. Among input patterns, flow based and coupled precipitation-flow based patterns with negligible difference to each other were determined to be the best patterns. Also this study confirmed that combining wavelet method with ANN and GEP and developing WANN and WGEP methods results in improving the performance of ANN and GEP models.     

Modelling Rainfall Runoff Relations Using HEC-HMS and IHACRES for a Single Rain Event in an Arid Region of Jordan

The HEC-HMS and IHACRES rainfall runoff models were applied to simulate a single streamflow event in Wadi Dhuliel arid catchment that occurred on 30–31/01/2008. Streamflow estimation was performed on the basis of an hourly scale. The aim of this study was to develop a new framework of rainfall-runoff model applications in arid catchments by integrating a re-adjusted satellite-derived rainfall dataset (GSMaP_MVK+) to determine the location of the rainfall storm. The HEC-HMS model was applied using the HEC-GeoHMS extension in ArcView 3.3 while the IHACRES is Java-based version model. The HEC-HMS model input data include soil type, land use/land cover, and slope. By contrast, the lumped model IHACRES was also applied, based on hourly rainfall and temperature data. Both models were calibrated and validated using the observed streamflow data set collected at Al-Za’atari discharge station. The performance of IHACRES showed some weaknesses, while the flow comparison between the calibrated streamflow results fits well with the observed streamflow data in HEC-HMS. The Nash-Sutcliffe efficiency (E_f) for the two models was 0.51 and 0.88 respectively.     

Assessment of future climate change impacts on hydrological behavior of Richmond River Catchment

This study evaluated the impacts of future climate change on the hydrological response of the Richmond River Catchment in New South Wales (NSW), Australia, using the conceptual rainfall-runoff modeling approach (the Hydrologiska Byrans Vattenbalansavdelning (HBV) model). Daily observations of rainfall, temperature, and streamflow and long-term monthly mean potential evapotranspiration from the meteorological and hydrological stations within the catchment for the period of 1972–2014 were used to run, calibrate, and validate the HBV model prior to the streamflow prediction. Future climate signals of rainfall and temperature were extracted from a multi-model ensemble of seven global climate models (GCMs) of the Coupled Model Intercomparison Project Phase 3 (CMIP3) with three regional climate scenarios, A2, A1B, and B1. The calibrated HBV model was then forced with the ensemble mean of the downscaled daily rainfall and temperature to simulate daily future runoff at the catchment outlet for the early part (2016–2043), middle part (2044–2071), and late part (2072–2099) of the 21st century. All scenarios during the future periods present decreasing tendencies in the annual mean streamflow ranging between 1% and 24.3% as compared with the observed period. For the maximum and minimum flows, all scenarios during the early, middle, and late parts of the century revealed significant declining tendencies in the annual mean maximum and minimum streamflows, ranging between 30% and 44.4% relative to the observed period. These findings can assist the water managers and the community of the Richmond River Catchment in managing the usage of future water resources in a more sustainable way.     

潮白河生态流量估算及恢复保障措施

针对潮白河水资源过度开发导致的生态与环境问题,从生态流量的视角进行分析,以潮白河控制性水文站———戴营、下堡站47年(1956年-2002年)的实测日径流资料为基础,利用水文指标法(IHA)及范围变化法(RVA)计算潮白河流量均值、极值及其发生时间、频率、历时和变动率等5组33个指标,对比分析人类活动影响较小的参照期(1956年-1974年)与人类活动影响强烈的影响期(1975年-2003年)的系列水文指标的变化,分析影响期内潮白河流量与目标范围的差距,明确生态流量的恢复目标,提出了实现恢复目标的保障措施。     

Using Optimized Deep Learning to Predict Daily Streamflow: A Comparison to Common Machine Learning Algorithms

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 (Q_t) prediction in the Korkorsar catchment in northern Iran. Fifteen years of daily rainfall (R_t) 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., R_t-1, R_t-2, etc.) (as the input variables) and Q_t (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 R_t was the most effective input variable on Q_t prediction and the integration of R_t, R_t-1, and Q_t-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.

     

施工导流超标洪水风险率估计的水文模拟方法

利用系统辨识技术，根据实测日径流系列建立了日径流过程的随机模拟模型. 由该模型模拟出多组导流工程服务年限中的日径流过程，经统计得出各种风险率下的设计流量与超标洪水发生次数的关系， 从而把风险率、施工年限、设计流量和超标洪水发生次数紧密联系起来， 为合理选择导流设计流量提供了依据。     

Multi-Criteria Process-Based Calibration Using Functional Data Analysis to Improve Hydrological Model Realism

It has been argued that rainfall-runoff model calibration based solely on streamflow is not sufficient to evaluate the realism of a hydrological model to represent the internal fluxes. Therefore, model calibration has evolved to evaluating model performance using a number of hydrological signatures that link the model to the underlying processes. However, this approach uses goodness-of-fit measures, unable to describe the entire dynamic of time series, to evaluate model consistency and to simulate hydrological signatures. The present paper develops a stepwise multicriteria calibration using hydrograph partitioning and calibration criteria defined on the basis of Functional Data Analysis (FDA), a statistical tool that conserves all important features of the hydrograph by approximating times series as a single function. The aim of this approach is to improve model realism by scrutinizing model components and by evaluating its ability to reproduce the entire flow dynamic. The proposed approach is compared to a calibration against daily streamflow only. The stepwise calibration improved the estimation of the flood curve, the annual peak volume as well as the performance of the model at sites other than the calibration station.     

Effect of calibration data series length on performance and optimal parameters of hydrological model

In order to assess the effects of calibration data series length on the performance and optimal parameter values of a hydrological model in ungauged or data-limited catchments (data are non-continuous and fragmental in some catchments), we used non-continuous calibration periods for more independent streamflow data for SIMHYD (simple hydrology) model calibration. Nash-Sutcliffe efficiency and percentage water balance error were used as performance measures. The particle swarm optimization (PSO) method was used to calibrate the rainfall-runoff models. Different lengths of data series ranging from one year to ten years, randomly sampled, were used to study the impact of calibration data series length. Fifty-five relatively unimpaired catchments located all over Australia with daily precipitation, potential evapotranspiration, and streamflow data were tested to obtain more general conclusions. The results show that longer calibration data series do not necessarily result in better model performance. In general, eight years of data are sufficient to obtain steady estimates of model performance and parameters for the SIMHYD model. It is also shown that most humid catchments require fewer calibration data to obtain a good performance and stable parameter values. The model performs better in humid and semi-humid catchments than in arid catchments. Our results may have useful and interesting implications for the efficiency of using limited observation data for hydrological model calibration in different climates.     

Prediction of Surface Flow by Forcing of Climate Forecast System Reanalysis Data

Meteorological data are key variables for hydrologists to simulate the rainfall-runoff process using hydrological models. The collection of meteorological variables is sophisticated, especially in arid and semi-arid climates where observed time series are often scarce. Climate Forecast System Reanalysis (CFSR) Data have been used to validate and evaluate hydrological modeling throughout the world. This paper presents a comprehensive application of the Soil and Water Assessment Tool (SWAT) hydrologic simulator, incorporating CFSR daily rainfall-runoff data at the Roodan study site in southern Iran. The developed SWAT model including CFSR data (CFSR model) was calibrated using the Sequential Uncertainty Fitting 2 algorithm (SUFI-2). To validate the model, the calibrated SWAT model (CFSR model) was compared with the observed daily rainfall-runoff data. To have a better assessment, terrestrial meteorological gauge stations were incorporated with the SWAT model (Terrestrial model). Visualization of the simulated flows showed that both CFSR and terrestrial models have satisfactory correlations with the observed data. However, the CFSR model generated better estimates regarding the simulation of low flows (near zero). The results of the uncertainty analysis showed that the CFSR model predicted the validation period more efficiently. This might be related with better prediction of low flows and closer distribution to observed flows. The Nash-Sutcliffe (NS) coefficient provided good- and fair-quality modeling for calibration and validation periods for both models. Overall, it can be concluded that CFSR data might be promising for use in the development of hydrological simulations in arid climates, such as southern Iran, where there are shortages of data and a lack of accessibility to the data.     

Relating Trends in Streamflow to Anthropogenic Influences: A Case Study of Himayat Sagar Catchment,India

Catchment development has been identified as a potentially major cause of streamflow change in many river basins in India. This research aims to understand changes in the Himayat Sagar catchment (HSC), India, where significant reductions in streamflow have been observed. Rainfall and streamflow trend analysis for 1980–2004 shows a decline in streamflow without significant changes in rainfall. A regression model was used to quantify changes in the rainfall-runoff relationship over the study period. We relate these streamflow trends to anthropogenic changes in land use, groundwater abstraction and watershed development that lead to increased ET (Evapotranspiration) in the catchment. Streamflow has declined at a rate of 3.6 mm/y. Various estimates of changes in evapotranspiration/irrigation water use were made. Well inventories suggested an increase of 7.2 mm/y in groundwater extractions whereas typical irrigation practices suggests applied water increased by 9.0 mm/y, while estimates of evapotranspiration using remote sensing data showed an increasing rate of 4.1 mm/y. Surface water storage capacity of various small watershed development structures increased by 2 mm over 7 years. It is concluded that the dominant hydrological process responsible for streamflow reduction is the increase in evapotranspiration associated with irrigation development, however, most of the anthropogenic changes examined are interrelated and occurred simultaneously, making separating out individual impacts very difficult.