A Comparison of Stepwise Cluster Analysis and Multiple Linear Regression for Hydrological Simulation

The soil and water assessment tool (SWAT) is a widely accepted semi-distributed agrohydrological model. In the present study, the SWAT has been calibrated for the agriculture-dominated Kantamal catchment of Mahanadi river basin, Odisha, India, to simulate streamflow at the Kantamal gauging station. The model was run for 19 years from 2000 to 2018 to simulate monthly streamflow. In addition, the model has been calibrated for the period 2004 to 2012, considering the initial 4 years (2000-2003) as a warm-up period and validated for 6 years from 2013 to 2018. Uncertainty analysis was carried out using the SUFI-2 algorithm in SWAT-CUP. The sensitivity of the parameters was determined using the t-stat and p-value. Fifteen distinguished parameters were selected for sensitivity analysis (SA). The performance of the model was evaluated satisfactorily on monthly time scale streamflow simulation using Nash- Sutcliffe Efficiency (NSE), coefficient of determination (R2), and percentage BIAS (PBIAS). The P- and R- factors were used to assess the degree of uncertainty. The values of NSE, R2, and PBIAS were found to be 0.91, 0.94, and -0.07 during the calibration period and 0.82, 0.87, and -0.16 during the validation period, respectively. The P- and R- factors values were 0.77 and 0.98 during calibration and 0.79 and 0.86 during the validation period, respectively. The simulated streamflow is well fitted within the 95% prediction uncertainty (95PPU) band of the SUFI-2 algorithm during the calibration and validation periods, indicating a satisfactory model performance under parameter uncertainty. Overall, it is depicted that the SWAT model can be successfully used for streamflow modeling and water resources assessment in agriculture-dominated catchments.

In this study, a stepwise cluster forecasting (SCF) framework is proposed for probabilistic prediction for monthly streamflow through integrating stepwise cluster analysis and quantile regression methods. The developed SCF method can capture discrete and nonlinear relationships between explanatory and response variables. A cluster tree was generated through the SCF method for reflecting complex relationships between independent (i.e. explanatory) and dependent (i.e. response) variables in the hydrologic system. Quantile regression approach was employed to construct probabilistic relationships between inputs and outputs in each leaf of the cluster tree. The developed SCF method was applied for monthly streamflow prediction in Xiangxi River based on the gauged records at Xingshan gauging station and related meteorological data. The performance of the SCF method was evaluated through indices of percent bias (PBIAS), RMSE-observations standard deviation ratio (RSR), and Nash-Sutcliffe efficiency coefficient (NSE). Two new indices, the relative distance to the bounds (RDB) and the degree of uncertainty (DOU) were proposed to reflect the uncertainty of the predictions from SCF model. The results showed that the uncertainty of the predictions was acceptable and would not change significantly in calibration and validation periods. Quantile regression was integrated into prediction process of the SCF approach to provide probabilistic forecasts. The 90 % confidence intervals could well bracket the observations in both calibration and validation periods. Comparison among different forecasting techniques showed the effectiveness of the proposed method.

Estimation of water balance and water yield in the Reedy Fork-Buffalo Creek Watershed in North Carolina using SWAT

An entropy‐copula method is proposed for single‐site monthly streamflow simulation. In this method, the joint distribution of adjacent monthly streamflows is constructed using the copula method, whereas the marginal distribution of streamflow for each month is derived using the entropy method. Then, the conditional distribution is derived from which monthly streamflow is generated. Moment statistics of monthly streamflow (such as mean, standard deviation and skewness) can be modeled by the entropy‐based marginal distribution while the dependence structure between streamflows of adjacent months can be modeled by the copula‐based joint distribution. The proposed entropy‐copula method can be extended by incorporating an aggregate variable for modeling the interannual dependence. Application to the simulation of monthly streamflow from the Colorado River illustrates the effectiveness of the proposed method.

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.

Application of an inappropriate Digital Elevation Model (DEM) might lead to uncertainty in modelling of the hydrological cycle. The novelty of this work is the development of a comprehensive framework to evaluate the effect of DEM resolution (12 to 500 m), source (TanDEM-X, SRTM, AW3D30 and ASTER GDEM2), resampling technique (nearest neighbour, bilinear interpolation, cubic convolution and majority) and area threshold (1000 to 50,000 ha) on Soil and Water Assessment Tool (SWAT) outputs based on five criteria: (1) river network extraction, (2) streamflow simulation, (3) topography, slope and basin characteristics, (4) hydrological and (5) water quality simulations. Kelantan River Basin, a tropical basin in Peninsular Malaysia was selected as study area. The major findings are summarized as follows: (1) TanDEM-X had better river network extraction capability than ASTER GDEM2, (2) better monthly streamflow simulations were obtained between 20 m and 60 m DEM resolutions, with the smallest area threshold (1000 ha), (3) TanDEM-X and SRTM DEMs outperformed ASTER GDEM2 on monthly streamflow simulation, (4) DEM resolution, source and resampling technique were insensitive to most of the hydrological components, except the lateral flow, (5) area threshold was sensitive to SWAT-simulated surface runoff, soil water content and evapotranspiration, (6) DEM scenarios had a larger impact on sediment yield simulations compared to the total nitrogen and total phosphorus simulations. We recommend a preliminary assessment of DEM uncertainties on SWAT outputs to obtain more reliable modelling outputs.

평창유역의 적설량을 모의하기 위하여 HSPF 모형을 적용하였다. 미래 적설량을 평가하기 위해 CIMIP3에서 제공하는 A1, A1B, B1의 온실가스 배출시나리오에 기반한 GCMs를 이용하였으며, HSPF 모형과 GCMs의 통계학적 오류를 최소화 하기 위해 편의보정(Bias-correction)과 시간적 분해모형(Temporal disaggregation)을 적용하였다. 모형의 검 보정 결과 모의된 유출량과 적설량의 경우 모형 효율이 높게 나타났으며, 특히 모형의 검정 후 상관계수를 분석한 결과 월별 유출량의 상관계수는 0.94로 나타났다. 월별 적설량, 또한, 상관계수가 0.91로 나타나 보정된 HSPF 모형이 평창지역에 대한 유출량과 적설량을 잘 모의하고 있는 것으로 판단된다. GCMs를 이용한 2018년 평창올림픽 경기장의 적설량을 분석한 결과 1월에는 17.62%, 2월에는 9.38%, 3월에는 7.25%의 적설량이 감소되는 것으로 나타났다. Hydrological simulation Program-Fortran (HSPF) model was used to simulate streamflow and snow depth at Pyengchang watershed. The selected Global Climate Models (GCMs) provided by the Coupled Model Intercomparision Project Phase 3 (CMIP3) were utilized to evaluate streamflow and snow depth driven by future climate scenarios, including A1, A1B, and B1. Bias-correlation and temporal downscaling processes have been performed to minimize systematic errors between GCMs and HSPF. Based on simulated monthly streamflow and snow depth after calibration, the results indicate that HSPF performs well. The correlation coefficient between the observed and simulated monthly streamflow is 0.94. Snow depth simulations also show high correlation coefficient, which is 0.91. The results indicate that snow depth in 2018 at Pyongchang winter olympic venues will decrease by 17.62%, 9.38%, and 7.25% in January, February, and March respectively, based on streamflow realizations induced by all GCMs ensembles.

The SWAT model was used to estimate the runoff and sediment yield of Lolab watershed. The model was calibrated, validated, and assessed for evaluation to model ambiguity using Nash–Sutcliffe coefficient (NSE) and coefficient of determination (R2). Ten highly sensitive parameters were recognized for stream flow simulation of which CN2 (Initial SCS CN II value) factor was the most sensitive one and four highly sensitive parameters were recognized for sediment yield simulation of which SPCON (Linear parameters for sediment re-entrainment) was most sensitive one. The model was calibrated for a time period between 1993 to 2000 and validated from 2001 to 2004 for flow and sediment yield. The predicted and observed stream flow and sediment yields generally matched well. The results of the model calibration and validation showed reliable estimates of monthly stream flow (R2=0.74 and ENS=0.68) and yearly stream flow (R2=0.90 and ENS=0.68) during the calibration period and monthly stream-flow (R2=0.85 and ENS=0.83) and yearly stream-flow (R2=0.99 and ENS=0.91) during the validation period. For sediment yield, this study shows antremendous model efficiency of monthly sediment yield (R2=0.80 and ENS=0.79) and yearly sediment yield (R2=0.86 and ENS=0.78) during the calibration period and monthly sediment yield (R2=0.88 and ENS=0.86) and yearly sediment yield (R2=0.83 and ENS=0.58) during the validation period. This study showed that the SWAT model is competent of predicting sediment yields and hence can be used as a tool for water resources planning and management in the study watershed.

A Comparative Study on Prediction of Monthly Streamflow Using Hybrid ANFIS-PSO Approaches

Streamflow forecasting is crucial for planning, designing, and managing water resources. Accurate streamflow forecasting is essential in developing water resource systems that are both technically and economically efficient. This study tested several machine learning techniques to estimate monthly streamflow data in the Hunza River Basin, Pakistan, using streamflow, precipitation, and air temperature data between 1985 and 2013. The techniques tested included adaptive boosting (AB), gradient boosting (GB), random forest (RF), and K-nearest neighbors (KNN). The models were developed using river discharge as the target variable, while air temperature and precipitation as the input variables. The model's performance was assessed via four statistical performance indicators namely root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE), and coefficient of determination (R2). The results obtained for RMSE, MSE, MAE, and R2 using AB, GB, RF, and KNN techniques are (16.8, 281, 6.53, and 0.998), (95.1, 9,047, 61.5, and 0.921), (126.8, 16,078, 74.6, and 0.859), and (219.9, 48,356, 146.3, and 0.775), respectively. The results indicate that AB outperforms GB, RF, and KNN in predicting monthly streamflow for the Hunza River Basin. Machine learning, particularly AB, offers a reliable approach for streamflow forecasting, aiding hazard and water management in the area.

Energy-saving design is becoming a trending topic and top-priority over the past decades due to high energy costs, limited available resources and growing urban development. Buildings are alluded to as the major contributors of energy consumption and environmental emissions across the globe. This calls for the development of precise forecasting models of energy consumption and carbon emissions. Hence, this research paper harnesses the implementation of several contemporary metaheuristics to accurately project heating and cooling energy (HEN and CEN) in residential buildings. In this respect, black widow optimization, dandelion optimization, dingo optimization, sparrow search, and red-tailed hawk optimization are among the studied metaheuristics in this research study. The prediction accuracies of the developed models are assessed stepping on the measures of i) relative absolute error (RAE), ii) mean absolute error (MAE), iii) mean absolute percentage error (MAPE), iv) root mean squared error (RMSE) and v) Nash-Sutcliffe efficiency (NSE). It is shown that the developed red-tailed hawk optimization-based model succeeded in accomplishing the most precise results of HEN and CEN. In this context, it predicted HEN with RAE (0.201), MAE (1.838), MAPE (7.626%), RMSE (2.826), and NSE (0.921). Besides, it anticipated CEN with RAE (0.234), MAE (2.009), MAPE (7.519%), RMSE (3.246), and NSE (0.883). It can be argued that this research study could benefit architects and designers in creating more energy-efficient buildings at an early stage.

Artificial neural network (ANN) models combined with time series decomposition are widely employed to calculate the river flows; however, the influence of the application of diverse decomposing approaches on assessing correctness is inadequately compared and examined. This study investigates the certainty of monthly streamflow by applying ANNs including feed forward back propagation neural network and radial basis function neural network (RBFNN) models integrated with discrete wavelet transform (DWT), at Jinsha River basin in the upper reaches of Yangtze River of China. The effect of the noise factor of the decomposed time series on the prediction correctness has also been argued in this paper. Data have been analyzed by comparing the simulation outputs of the models with the correlation coefficient (R) root mean square errors, mean absolute errors, mean absolute percentage error and Nash–Sutcliffe Efficiency. Results show that time series decomposition technique DWT contributes in improving the accuracy of streamflow prediction, as compared to single ANN’s. The detailed comparative analysis showed that the RBFNN integrated with DWT has better forecasting capabilities as compared to other developed models. Moreover, for high-precision streamflow prediction, the high-frequency section of the original time series is very crucial, which is understandable in flood season.

First posted September 7, 2021 For additional information, contact: Director, Wyoming-Montana Water Science Center U.S. Geological Survey3162 Bozeman Avenue Helena, MT 59601 Scant availability of streamflow data can impede the utility of streamflow as a variable in ecological models of aquatic and terrestrial species, especially when studying small streams in watersheds that lack streamgages. Streamflow data at fine resolution and broad extent were needed by collaborators for ecological research on small streams in several ungaged watersheds of southwestern Wyoming, where streamflow data are sparse.To improve the utility of sparse streamflow data to ecological research in ungaged watersheds, we developed a machine learning approach in R for modeling spatially and temporally continuous monthly streamflow from 2012 through 2017 in three semiarid montane-steppe watersheds (with drainage areas of 26–55 square miles and mean elevations of 8,031–8,455 feet) on the Wyoming Range in the upper Green River Basin. A machine learning streamflow (MLFLOW) model was calibrated and validated with 971 discrete streamflow observations and 24 static and dynamic predictor variables derived from geospatial and time series data on climatic, physiographic, and anthropogenic characteristics affecting streamflow. The predictor variables were temporally and spatially conditioned to amplify the relation of predictor variables to monthly streamflow.The MLFLOW model had satisfactory agreement between observed and predicted streamflow (coefficient of determination [R2]=0.80, Nash-Sutcliffe efficiency [NSE]=0.79, NSE with log-transformed data [logNSE]=0.82, and percent bias [PBIAS]=0.7 percent). NSE and logNSE indicated the MLFLOW model performed equally well for high and low flows, and PBIAS indicated the MLFLOW model did not overpredict or underpredict monthly streamflow. Streamflow predictions seemed to well represent the annual hydrograph within the study area during the study period.The most important variables (statistically important in the MLFLOW model) for explaining monthly streamflow were temporally and spatially conditioned dynamic climatic variables, mostly precipitation and snow water equivalent. Importance of the static and dynamic variables did not differ substantially among the three watersheds but differed considerably among the 6 years. Monthly streamflow increased with increasing precipitation, snow water equivalent, and drainage area but decreased with increasing forest cover, elevation, evapotranspiration, and temperature.The MLFLOW model was most sensitive to selection of dynamic climatic variables. Unconditioned dynamic climatic variables alone explained 54 percent of the variance (R2=0.54) in monthly streamflow, whereas adding static physiographic and anthropogenic variables only explained 12 percent more of the variance (R2=0.66). Also, spatial conditioning of all variables together with temporal conditioning of dynamic variables increased the variance explained in the MLFLOW model by another 14 percent (R2=0.80). The MLFLOW model also had greater sensitivity to temporal than to spatial differences in the data. For the MLFLOW model trained with observations from all watersheds and years or for models trained with observations from all except one watershed or 1 year left out sequentially, performance was better in testing on observations from each watershed than from each year separately. Also, performance was better for models fitted to fewer sites than to fewer months of observations.The greatest utility of the modeling approach is the ease of use and the speed of processing input data, running the model, and interpreting the model output, whereas the greatest limitation is the need for spatially and temporally representative streamflow observations to drive the model. Although familiarity with R is necessary, only a working knowledge of hydrology (for selecting appropriate predictor variables and evaluating the quality of streamflow observations) and a rudimentary understanding of machine learning models are needed. Therefore, this modeling approach is practicable for other scientists who work with water but who are not hydrologists.

A study was conducted to predict the stream flow from a catchment area of Hidkal dam situated in Krishna basin of India. The SimHYD model was selected to setup the stream flow model under limited data conditions. Daily rainfall, potential evapotranspiration (PET) and observed discharges were used as input data to setup the model. Sensitivity analysis was carried out to identify the more sensitive parameter and fixed final parameter values. A genetic algorithm was used for calibration and validation of the model with object function of Nash -Sutcliffe Equation (NSE). The performance of model during calibration and validation with monthly stream flow (m3/s) was found to be very good in terms of NSE, R2. The NSE and correlation coefficient were found to be 0.77 and 0.93 during calibration period and 0.90 and 0.95 during validation period respectively. The was a very good agreement between monthly observed and simulated stream flows of catchment area of Hidkal Dam. The NSE value of model during calibration period with daily runoff was found to be satisfactory at 0.51. It was observed that good agreement between observed and simulated daily runoff (in mm) with a correlation coefficient is 0.74. NSE and correlation coefficient during validation period using daily data are found to be 0.80 and 0.9 respectively. This study concluded that the SimHYD model can be used for assessment of stream flow with limited data.

In this paper kernel estimates of the joint and conditional probability density functions are used to generate synthetic streamflow sequences. Streamflow is assumed to be a Markov process with time dependence characterized by a multivariate probability density function. Kernel methods are used to estimate this multivariate density function. Simulation proceeds by sequentially resampling from the conditional density function derived from the kernel estimate of the underlying multivariate probability density function. This is a nonparametric method for the synthesis of streamflow that is data‐driven and avoids prior assumptions as to the form of dependence (e.g., linear or nonlinear) and the form of the probability density functions (e.g., Gaussian). We show, using synthetic examples with known underlying models, that the nonparametric method presented is more flexible than the conventional models used in stochastic hydrology and is capable of reproducing both linear and nonlinear dependence. The effectiveness of this model is illustrated through its application to simulation of monthly streamflow from the Beaver River in Utah.