River Flow Estimation and Forecasting by Using Two Different Adaptive Neuro-Fuzzy Approaches

This paper demonstrates the application of two different adaptive neuro-fuzzy (ANFIS) techniques for the estimation of monthly streamflows. In the first part of the study, two different ANFIS models, namely ANFIS with grid partition (ANFIS-GP) and ANFIS with sub clustering (ANFIS-SC), were used in one-month ahead streamflow forecasting and the results were evaluated. Monthly flow data from two stations, the Besiri Station on the Garzan Stream and the Baykan Station on the Bitlis Stream in the Firat-Dicle Basin of Turkey were used in the study. The effect of periodicity on the model’s forecasting performance was also investigated. In the second part of the study, the performance of the ANFIS techniques was tested for streamflow estimation using data from the nearby river. The results indicated that the performance of the ANFIS-SC model was slightly better than the ANFIS-GP model in streamflow forecasting.     

Intermittent Streamflow Forecasting by Using Several Data Driven Techniques

Forecasting intermittent streamflows is an important issue for water quality management, water supplies, hydropower and irrigation systems. This paper compares the accuracy of several data driven techniques, that is, adaptive neuro fuzzy inference system (ANFIS), artificial neural networks (ANNs) and support vector machine (SVM) for forecasting daily intermittent streamflows. The results are also compared with those of the local linear regression (LLR) and the dynamic local linear regression (DLLR). Intermittent streamflow data from two stations, Uzunkopru and Babaeski, in Thrace region located in north-western Turkey are used in the study. The root mean square error and correlation coefficient were used as comparison criteria. The comparison results indicated that the ANFIS, ANN and SVM models performed better than the LLR and DLLR models in forecasting daily intermittent streamflows. The ANN and ANFIS gave the best forecasts for the Uzunkopru and Babaeski stations, respectively.     

Comparison of performance of statistical models in forecasting monthly streamflow of Kizil River,China

This paper presents the application of autoregressive integrated moving average(ARIMA),seasonal ARIMA(SARIMA),and Jordan-Elman artificial neural networks(ANN)models in forecasting the monthly streamflow of the Kizil River in Xinjiang,China.Two different types of monthly streamflow data(original and deseasonalized data)were used to develop time series and Jordan-Elman ANN models using previous flow conditions as predictors.The one-month-ahead forecasting performances of all models for the testing period(1998-2005)were compared using the average monthly flow data from the Kalabeili gaging station on the Kizil River.The Jordan-Elman ANN models,using previous flow conditions as inputs,resulted in no significant improvement over time series models in one-month-ahead forecasting.The results suggest that the simple time series models(ARIMA and SARIMA)can be used in one-month-ahead streamflow forecasting at the study site with a simple and explicit model structure and a model performance similar to the Jordan-Elman ANN models.     

Investigation of Empirical Mode Decomposition in Forecasting of Hydrological Time Series

In this study, a nonparametric technique to set up a river stage forecasting model based on empirical mode decomposition (EMD) is presented. The approach is based on the use of the EMD and artificial neural networks (ANN) to forecast next month’s monthly streamflows. The proposed approach is applied to a real case study. The data from station on the Kizilirmak River in Turkey was used. The mean square errors (MSE), mean absolute errors (MAE) and correlation coefficient (R) statistics were used for evaluating the accuracy of the EMD-ANN model. The accuracy of the EMD-ANN model was then compared to the artificial neural networks (ANN) model. The results showed that EMD-ANN approach performed better than the ANN in predicting stream flows. The most accurate EMD-ANN model had MSE?=?0.0132, MAE?=?0.0883 and R?=?0.8012 statistics, respectively.     

A Comparative Study of Autoregressive,Autoregressive Moving Average,Gene Expression Programming and Bayesian Networks for Estimating Monthly Streamflow

In the recent years, artificial intelligence techniques have attracted much attention in hydrological studies, while time series models are rarely used in this field. The present study evaluates the performance of artificial intelligence techniques including gene expression programming (GEP), Bayesian networks (BN), as well as time series models, namely autoregressive (AR) and autoregressive moving average (ARMA) for estimation of monthly streamflow. In addition, simple multiple linear regression (MLR) was also used. To fulfill this objective, the monthly streamflow data of Ponel and Toolelat stations located on Shafarood and Polrood Rivers, respectively in Northern Iran were used for the period of October 1964 to September 2014. In order to investigate the models’ accuracy, root mean square error (RMSE), mean absolute error (MAE) and coefficient of determination (R²) were employed as the error statistics. The obtained results demonstrated that the single AR and ARMA time series models had better performance in comparison with the single GEP, BN and MLR methods. Furthermore, in this study, six hybrid models known as GEP-AR, GEP-ARMA, BN-AR, BN-ARMA, MLR-AR and MLR-ARMA were developed to enhance the estimation accuracy of the monthly streamflow. It was concluded that the developed hybrid models were more accurate than the corresponding single artificial intelligence and time series models. The obtained results confirmed that the integration of time series models and artificial intelligence techniques could be of use to improve the accuracy of single models in modeling purposes related to the hydrological studies.     

Mixed D-vine copula-based conditional quantile model for stochastic monthly streamflow simulation

Copula functions have been widely used in stochastic simulation and prediction of streamflow. However, existing models are usually limited to single two-dimensional or three-dimensional copulas with the same bivariate block for all months. To address this limitation, this study developed a mixed D-vine copula-based conditional quantile model that can capture temporal correlations. This model can generate streamflow by selecting different historical streamflow variables as the conditions for different months and by exploiting the conditional quantile functions of streamflows in different months with mixed D-vine copulas. The up-to-down sequential method, which couples the maximum weight approach with the Akaike information criteria and the maximum likelihood approach, was used to determine the structures of multivariate D-vine copulas. The developed model was used in a case study to synthesize the monthly streamflow at the Tangnaihai hydrological station, the inflow control station of the Longyangxia Reservoir in the Yellow River Basin. The results showed that the developed model outperformed the commonly used bivariate copula model in terms of the performance in simulating the seasonality and interannual variability of streamflow. This model provides useful information for water-related natural hazard risk assessment and integrated water resources management and utilization.

     

Development of a Hybrid Data Driven Model for Hydrological Estimation

High and low stremflow values forecasting is of great importance in field of water resources in order to mitigate the impacts of flood and drought. Most of water resources models deal with the problem of not being flexible for modeling maximum and minimum flows. To overcome that shortcoming, a combination of artificial neural network (ANN) models is developed in this study for monthly streamflow forecasting. A probabilistic neural network (PNN) is used to classify each of the input-output patterns and afterward, the classified data are forecasted using a modified multi-layer perceptron (MMLP). In addition, the performance of the MLP and generalized regression neural network (GRNN) in streamflow forecasting are investigated and compared to the proposed method. The findings indicate that the R² associated with the suggested model is 46 and 80% higher compared to MLP and GRNN models, respectively.     

Performance of a Monthly Streamflow Prediction Model for Ungauged Watersheds in Spain

Climate change, drought and the world??s growing population are increasing the demand for water which in turn requires improved water resources management. The sustainable management of a watershed requires a thorough knowledge of its water resources, including monthly streamflow. Spain is home to a large number of ungauged watersheds, the streamflows of which are often unknown. Chavez et al. (2007) reported a model for predicting monthly streamflow in ungauged watersheds that was validated for use in areas of tropical climate in Central America and a dry area in South America. This work reports an attempt to assess the performance of this model for eventual use with ungauged watersheds in Spain, using data for a number of watersheds for which gauging data were available. The proposed model took into account physical characteristics such us the soil infiltration rate, the slope of the terrain, plant fractional cover, the monthly moisture adequacy index, and the leaf area index. Comparisons of model-predicted monthly streamflows and those actually measured showed the Chavez et al. model unable to make reliable predictions for Spanish watersheds in its current form. A new approach has been developed considering only smaller watersheds in Spanish conditions, changing parameters in the original model. These parameters have been calibrated and validated, reaching adequate adjustment of results.     

PREDICTING THE LIKELIHOOD OF ALTERED STREAMFLOWS AT UNGAUGED RIVERS ACROSS THE CONTERMINOUS UNITED STATES

An approach is presented in this study to aid water‐resource managers in characterizing streamflow alteration at ungauged rivers. Such approaches can be used to take advantage of the substantial amounts of biological data collected at ungauged rivers to evaluate the potential ecological consequences of altered streamflows. National‐scale random forest statistical models are developed to predict the likelihood that ungauged rivers have altered streamflows (relative to expected natural condition) for five hydrologic metrics (HMs) representing different aspects of the streamflow regime. The models use human disturbance variables, such as number of dams and road density, to predict the likelihood of streamflow alteration. For each HM, separate models are derived to predict the likelihood that the observed metric is greater than (‘inflated’) or less than (‘diminished’) natural conditions. The utility of these models is demonstrated by applying them to all river segments in the South Platte River in Colorado, USA, and for all 10‐digit hydrologic units in the conterminous United States. In general, the models successfully predicted the likelihood of alteration to the five HMs at the national scale as well as in the South Platte River basin. However, the models predicting the likelihood of diminished HMs consistently outperformed models predicting inflated HMs, possibly because of fewer sites across the conterminous United States where HMs are inflated. The results of these analyses suggest that the primary predictors of altered streamflow regimes across the Nation are (i) the residence time of annual runoff held in storage in reservoirs, (ii) the degree of urbanization measured by road density and (iii) the extent of agricultural land cover in the river basin. Published 2012. This article is a U.S. Government work and is in the public domain in the USA.     

Monthly Streamflow Forecasting Using Convolutional Neural Network

Monthly streamflow forecasting is vital for managing water resources. Recently, numerous studies have explored and evidenced the potential of artificial intelligence (AI) models in hydrological forecasting. In this study, the feasibility of the convolutional neural network (CNN), a deep learning method, is explored for monthly streamflow forecasting. CNN can automatically extract critical features from numerous inputs with its convolution–pooling mechanism, which is a distinct advantage compared with other AI models. Hydrological and large-scale atmospheric circulation variables, including rainfall, streamflow, and atmospheric circulation factors are used to establish models and forecast streamflow for Huanren Reservoir and Xiangjiaba Hydropower Station, China. The artificial neural network (ANN) and extreme learning machine (ELM) with inputs identified based on cross-correlation and mutual information analyses are established for comparative analyses. The performances of these models are assessed with several statistical metrics and graphical evaluation methods. The results show that CNN outperforms ANN and ELM in all statistical measures. Moreover, CNN shows better stability in forecasting accuracy.

     

Effect of Forest Thinning on Water Yield in a Sub-Humid Mediterranean Oak-Beech Mixed Forested Watershed

Forested watersheds provide fresh water with best quality and forestry practices play important role on the water production in the watersheds. Therefore, the objective of this study was to investigate the effect of 18 % thinning, which was under the 20 % threshold value reported in the literature on water yield in a forested watershed. Two experimental watersheds with similar ecological conditions in the Belgrad Forest of Istanbul were studied. Following a 6-year calibration period from December 2005 to October 2011, a simple linear regression equation was developed between the monthly streamflows of two watersheds with a significantly high correlation coefficient (r = 0.95). After 18 % of standing volume was removed from one watershed and the other was left untreated as a control, the streamflow was monitored for 2 years starting in January 2012 in both watersheds. The change in the monthly runoff was estimated as the difference between measured and values calculated with the linear regression equation. Average monthly streamflows were about 19, 15 and 10 mm in the control and 21, 20, and 11 mm in the treatment watersheds for calibration, first and second post-treatment periods, respectively. Paired watershed analysis showed that monthly streamflow did not significantly increase in either watershed for the first or the second year after the harvest. The results revealed that thinning intensity had to be greater to increase water yield significantly in this forest ecosystem and the threshold value for a streamflow increase was greater than 18 % for this region.     

Quantifying hydrologic alteration in an area lacking current reference conditions—The Mississippi alluvial plain of the south‐central United States

Quantifying hydrologic alteration in the Mississippi Alluvial Plain (MAP) of the south‐central United States is particularly difficult because of the lack of current reference, or even relatively undisturbed, streams and associated streamflow data. Impacts, such as water withdrawals for agriculture, weirs, dams, channelization, and other forms of regulation, within the MAP increased substantially beginning around 1960 suggesting that streamflow has since been altered. Using historical streamflow and climate data and explanatory variables, the U.S. Geological Survey developed random forest regression models to estimate expected reference monthly streamflows (pre‐1960) at 76 sites in the MAP and two adjacent Level III Ecoregions. To compensate for the lack of current reference stream sites in the study area, the pre‐1960 streamflow data were used as a surrogate to estimate current streamflow conditions without anthropogenic influence (inferring current reference conditions). Overall, nearly every site within the study area had less zero‐flow days than what historically has been observed and there were more low‐pulse spells. However, the frequency of floods remained relatively consistent.     

Stream Flow Forecasting of Poorly Gauged Mountainous Watershed by Least Square Support Vector Machine,Fuzzy Genetic Algorithm and M5 Model Tree Using Climatic Data from Nearby Station

Forecasting stream flow is a very importance issue in water resources planning and management. The ability of three soft computing methods, least square support vector machine (LSSVM), fuzzy genetic algorithm (FGA) and M5 model tree (M5T), in forecasting daily and monthly stream flows of poorly gauged mountainous watershed using nearby hydro-meteorological data is investigated in the current study. In the first application, monthly stream flows of Hunza river are forecasted using local stream flow data of Hunza and precipitation and temperature data of nearby station. LSSVM provides slightly better forecasts than the FGA and M5T models. Stream flow and temperature inputs generally give better forecasts compared to other inputs. In the second application, daily stream flows of Hunza river are forecasted using local stream flow data of Hunza and precipitation and temperature data of nearby station. Better results are obtained from the models comprising only stream flow inputs. In general, a better accuracy is obtained from LSSVM models in relative to the FGA and M5T. The results indicate that the monthly and daily stream flows of Hunza can be accurately forecasted by using only nearby climatic data. In the third application, daily stream flows of Hunza river are forecasted using local stream flow and climatic data and the models’ accuracy is slightly increased in relative to the previous applications. LSSVM generally performs superior to the FGA and M5T in forecasting daily stream flow of Hunza river using local stream flow and climatic inputs.     

Modeling Climate Change Effects on Streams and Reservoirs with HSPF

This study deals with the effects of the expected climate change on the hydrology of watersheds and on water resources. HSPF (Hydrological Simulation Program—Fortran) has been used to model streamflow and reservoir volume as realizations of watershed response. Climate change scenarios have been prepared based on trends expected in western Turkey in the first half of the twenty-first century and a hypothetical watershed with different land uses has been simulated. Changes in streamflow due to landuse, soil type and climate change have been examined using flood frequency and low flow analysis. The simulations have revealed quantitatively the difference among the responses of watersheds with no vegetative cover and with forests or pasture to trends in temperature and precipitation. It has also been found that monthly variations are very important in predicting the future response of watersheds. Significant differences have been observed in streamflows and reservoir volumes on a monthly basis between scenarios, soil types and land uses. Though the effects of temperature and precipitation act to counterbalance their effects on a long-term scale, on a monthly basis they can act to reinforce their effects and create drought periods and floods.     

Two-Dimension Monthly River Flow Simulation Using Hierarchical Network-Copula Conditional Models

River flow simulation is required on water resources planning and management. This paper proposes hierarchical network-copula conditional models to generate two-dimension monthly streamflow matrix aiming at simulating flow both on time and space. HNCCMs develop the simulation generator driven by both temporal and spatial covariates conditioned upon values of a set of parameters and hyper parameters which can be addressed from the three-layer hierarchical system. In the first layer, streamflow time series of the station at the most upstream is generated using bivariate Archimedean copulas and river flow space series in each month at stations down a river in sequence is simulated by nested copulas in the second layer. Last, the seasonal characters of the temporal parameters and covariates are detected as well as the spatial ones are detected using the neural network by fitting them into functions to contribute to the downscaling of space series. A case study for the model is carried on the Yellow River of China. This case (1) detects temporal and spatial relationships which illustrate the capacity of catching the seasonal characterize and spatial trend, (2) generates a river flow time series at Huayuankou station as well as (3) simulates a flow space sequence in January picking out best fitted building blocks for the cascade of bivariate copulas, and finally (4) synthesizes two-dimension simulation of monthly river flow. The result illustrates the essentially pragmatic nature of HNCCMs on simulation for this spatiotemporal monthly streamflow which is nonlinear and complex both on time and space.     

Using AR,MA, and ARMA Time Series Models to Improve the Performance of MARS and KNN Approaches in Monthly Precipitation Modeling under Limited Climatic Data

Precipitation is one of the most important components of the hydrologic cycle as it is required for multi-objective applications including flood estimation, drought monitoring, watersheds management, hydrology, agriculture, etc. Therefore, its estimation and modeling via a suitable method is a challenging task for hydrologists. The present study seeks to model monthly precipitation at two stations located in Iran. Two artificial intelligence (AI)-based models consisting of multivariate adaptive regression splines (MARS) and k-nearest neighbors (KNN) were used as the modeling techniques. In doing so, nine single-input scenarios under limited climatic data are implemented using minimum, maximum, and mean air temperatures, dew point temperature, station pressure, vapor pressure, relative humidity, wind speed, and antecedent precipitation data. The attained results illustrate that the performance of single MARS and KNN is relatively poor when modeling the monthly precipitation. Additionally, this study develops hybrid models to enhance the precipitation modeling through combining the MARS and KNN models with three diverse types of the time series (TS) models, namely autoregressive (AR), moving average (MA), and autoregressive moving average (ARMA). The most important justification for integrating the models applied is that the AI and TS-based models are respectively capable of modeling the non-linear and linear terms of the hydrological variables such as precipitation. It is therefore necessary to be considered both of the aforementioned terms in the modeling procedure. A performance comparison of the single and hybrid models denotes the higher accuracy of hybrid models than the single ones. However, the hybrid models generated by combining the KNN and the TS models used are the best-performing models.

     

Forecasting Hourly Intermittent Rainfall by Deep Belief Networks with Simple Exponential Smoothing

Accurate rainfall forecasting is essential in planning and managing water resource systems efficiently. However, intermittent rainfall patterns increase the difficulty of accurately forecasting rainfall values. Deep learning techniques have recently been popular and powerful in forecasting. Thus, this study employed deep belief networks with a simple exponential smoothing procedure (DBNSES) to forecast hourly intermittent rainfall values in Taiwan. Weather factors were used as independent variables to forecast rainfall volume. The simple exponential smoothing data preprocessing procedure was used to deal with the intermittent data patterns. The other three forecasting models, namely the least squares support vector regression (LSSVR), the generalized regression neural network (GRNN), and the backpropagation neural network (BPNN), were employed to forecast rainfall using the same data sets. In addition, genetic algorithms were utilized to determine the parameters of four forecasting models. The empirical results indicate that the developed DBNSES models are superior to the other forecasting models in terms of forecasting accuracy. In addition, the DBNSES can obtain smaller values of RMSE than those in the previous studies. Therefore, the DBNSES model is a suitable and effective way of forecasting rainfall with intermittent data patterns.

     

Improving Forecasting Accuracy of Streamflow Time Series Using Least Squares Support Vector Machine Coupled with Data-Preprocessing Techniques

Highly reliable forecasting of streamflow is essential in many water resources planning and management activities. Recently, least squares support vector machine (LSSVM) method has gained much attention in streamflow forecasting due to its ability to model complex non-linear relationships. However, LSSVM method belongs to black-box models, that is, this method is primarily based on measured data. In this paper, we attempt to improve the performance of LSSVM method from the aspect of data preprocessing by singular spectrum analysis (SSA) and discrete wavelet analysis (DWA). Kharjeguil and Ponel stations from Northern Iran are investigated with monthly streamflow data. The root mean square error (RMSE), mean absolute error (MAE), correlation coefficient (R) and coefficient of efficiency (CE) statistics are used as comparing criteria. The results indicate that both SSA and DWA can significantly improve the performance of forecasting model. However, DWA seems to be superior to SSA and able to estimate peak streamflow values more accurately. Thus, it can be recommended that LSSVM method coupled with DWA is more promising.     

The hydroclimate niche: A tool for predicting and managing riparian plant community responses to streamflow seasonality

Habitat suitability is a consequence of interacting environmental factors. In riparian ecosystems, suitable plant habitat is influenced by interactions between stream hydrology and climate, hereafter referred to as “hydroclimate”. We tested the hypothesis that hydroclimate variables would improve the fit of ecological niche models for a suite of riparian species using occurrence data from the western United States. We focus on the climate conditions (temperature, precipitation and vapor pressure deficit) during the months of lowest and highest streamflow as integrative hydroclimate metrics of resource and stress levels. We found that the inclusion of hydroclimate variables improved model fit for all species in the western USA dataset. We then tested the utility of the improved habitat suitability models by projecting them onto a regulated segment of the Colorado River to assess potential impacts of streamflow seasonality on vegetation metrics of management concern. Species frequency derived from independent survey data in the Colorado River segment was significantly higher for species with predicted suitable habitat than for species without predicted suitable habitat. Under different simulated hydrographs for the Colorado River, overall species richness was predicted to be greatest with peak streamflows during summer, and native-to-non-native species ratios were predicted to be greatest with lowest streamflows in winter. Summer high flows were particularly associated with higher predicted habitat suitability for species that have increased in cover over recent decades (e.g., Pluchea sericea, Baccharis species). We conclude that hydroclimate covariates can be useful tools for predicting how riparian vegetation communities respond to changes in the seasonal timing of low and high streamflows.     

Middle- and Long-Term Streamflow Forecasting and Uncertainty Analysis Using Lasso-DBN-Bootstrap Model

Middle-term and long-term streamflow forecasting is of great significance for water resources planning and management, cascade reservoirs optimal operation, agriculture and hydro-power generation. In this work, a framework was proposed which integrates least absolute shrinkage and selection operator (lasso), DBN and bootstrap to improve the performance and the stability of streamflow forecasting with the lead-time of one month. Lasso helps to screen the appropriate predictors for the DBN model, and the DBN model simulates the complex relationship between the selection predictors and streamflow, and then bootstrap with the DBN model contributes to evaluate the uncertainty. The Three-River Headwaters Region (TRHR) was taken as a case study. The results indicated that lasso-DBN-bootstrap model produced significantly more accurate forecasting results than the other three models and provides reliable information on the forecasting uncertainty, which will be valuable for water resources management and planning.