Short-Term Streamflow Forecasting Using the Feature-Enhanced Regression Model

Reservoir inflow forecasting is extremely important for the management of a reservoir. In practice, accurate forecasting depends on the feature learning performance. To better address this issue, this paper proposed a feature-enhanced regression model (FER), which combined stack autoencoder (SAE) with long short-term memory (LSTM). This model had two constituents: (1) The SAE was constructed to learn a representation as close as possible to the original inputs. Through deep learning, the enhanced feature could be captured sufficiently. (2) The LSTM was established to simulate the mapping between the enhanced features and the outputs. Under recursive modeling, the patterns of correlation in the short term and dependence in the long term were considered comprehensively. To estimate the performance of the FER model, two historical daily discharge series were investigated, i.e., the Yangtze River in China and the Sava Dolinka River in Slovenia. The proposed model was compared with other machine-learning methods (i.e., the LSTM, SAE-based neural network, and traditional neural network). The results demonstrated that the proposed FER model yields the best forecasting performance in terms of six evaluation criteria. The proposed model integrates the deep learning and recursive modeling, and thus being beneficial to exploring complex features in the reservoir inflow forecasting. Moreover, for smaller catchments with significant torrential characteristics, more data are needed (e.g., at least 20 years) to effectively train the model and to obtain accurate flood-forecasting results.

     

Gene-Expression Programming for Short-Term Forecasting of Daily Reference Evapotranspiration Using Public Weather Forecast Information

This study aimed to forecast the daily reference evapotranspiration (ETo) using a gene-expression programming (GEP) algorithm with limited public weather forecast information over Gaoyou station, located in Jiangsu province, China. To calibrate and validate the gene-expression code, important meteorological data and weather forecast information were collected from the local meteorological station and public weather media, respectively. The GEP algebraic formulation was successfully constructed based only on daily minimum and maximum air temperature using the true FAO56 Penman-Monteith (PM) set as reference values. The performance of the models was then assessed using the correlation coefficient (R), root mean squared error (RMSE), root relative squared error (RRSE) and mean absolute error (MAE). The study demonstrated that GEP is able to calibrate ETo (all errors ≤0.990 mm/day, R = 0.832–0.866) and forecast the daily ETo with good accuracy (RMSE = 1.207 mm/day, MAE = 0.902 mm/day, RRSE = 0.629 mm/day, R = 0.777). The model accuracies slightly decreased over a 7-day forecast lead-time. These results suggest that the GEP algorithm can be considered as a deployable tool for ETo forecast to anticipate decision on short-term irrigation schedule in the study zone.     

石河子参考作物潜在腾发量的多元线性回归分析

利用FAO Penman-Monteith(1992)公式,根据新疆生产建设兵团农八师148团1998年～2008年(除2001年)4月～8月每日的气象资料,建立了参考作物潜在腾发量与其它气象要素的相关关系.利用这些相关关系进行参考作物潜在蒸发蒸腾量的估算,结果表明其精度较高,方法简单.可为今后灌溉管理和产量评估提供较为简便实用的模型.     

Application of Gaussian Process Regression Model to Predict Discharge Coefficient of Gated Piano Key Weir

Water Resources Management - The Piano Key (PK) weir is a new type of long crested weirs. This study was involved the addition of a gate to PK weir inlet keys. It was conducted by the Department of...     

Reference Evapotranspiration Prediction Using Neural Networks and Optimum Time Lags

The reference evapotranspiration (ET₀) plays a significant role especially in agricultural water management and water resources planning for irrigation. It can be calculated using different empirical equations and forecasted by applying various artificial intelligence techniques. The simulation result of a machine learning technique is a function of its structure and model inputs. The purpose of this study is to investigate the effect of using the optimum set of time lags for model inputs on the prediction accuracy of monthly ET₀ using an artificial neural network (ANN). For this, the weather data time-series i.e. minimum and maximum air temperatures, vapour pressure, sunshine hours, and wind speed were collected from six meteorological stations in Serbia for the period 1980–2010. Three ANN models were applied to monthly ET₀ time-series to study the impacts of using the optimum time lags for input time-series on the performance of ANN model. Achieved results of goodness–of–fit statistics approved the results obtained by scatterplots of testing sets - using more time lags that are selected based on their correlation to the dataset is more efficient for monthly ET₀ prediction. It was realized that all the developed models showed the best performances at Loznica and Vranje stations and the worst performances at Nis station. Simultaneous assessment of the impact of using a different number of time lags and the set of time lags that show a stronger correlation to the dataset for input time-series, on the performance of ANN model in monthly ET₀ prediction in Serbia is the novelty of this study.

     

Improving the Summer Power Generation of a Hydropower Reservoir Using the Modified Multi-Step Ahead Time-Varying Hedging Rule

This paper aims to improve summer power generation of the Yeywa Hydropower Reservoir in Myanmar using the modified multi-step ahead time-varying hedging (TVH) rule as a case study. The results of the TVH rules were compared with the standard operation policy (SOP) rule, the binary standard operation policy (BSOP) rule, the discrete hedging (DH) rule, the standard hedging (SH) rule, the one-point hedging (OPH) rule, and the two-point hedging (TPH) rule. The Multi-Objective Genetic Algorithm (MOGA) was utilized to drive the optimal Pareto fronts for the hedging rules. The results demonstrated that the TVH rules had higher performance than the other rules and showed improvements in power generation not only during the summer period but also over the entire period.

     

Bivariate Simulation of Potential Evapotranspiration Using Copula-GARCH Model

Developing statistical period and simulating the required values in case of data shortage increases certainty and reliability of simulations and statistical analyses, which is very important in studies on hydrology and water resources. Therefore, in this study, for simulating values of potential evapotranspiration at Birjand Station located in eastern Iran, contemporaneous autoregressive moving average (CARMA), CARMA-generalized autoregressive conditional heteroskedasticity (GARCH), and Copula-GARCH models were used in statistical period of 1984–2019. The potential evapotranspiration and relative humidity time series were simulated using these three models. CARMA model has acceptable accuracy for simulating potential evapotranspiration values due to the effect of the second parameter on simulations. Nash–Sutcliffe efficiency (NSE) coefficient of CARMA model for simulating potential evapotranspiration values was estimated as 0.85. NSE coefficient of CARMA-GARCH model was obtained as 0.87 through extracting residuals of CARMA model and simulating variance of data using GARCH model. Comparing the CARMA and CARMA-GARCH models with each other, it was concluded that a combination of two linear and non-linear time series models increases simulation accuracy to some extent. Using Clayton copula (the selected copula from the studied copulas), the mentioned values were simulated by Copula-GARCH model. The results showed that among the three models used, Copula-GARCH model reduced root mean square error of bivariate simulation compared to CARMA and CARMA-GARCH models by 15 and 13%, respectively. The results also showed that the proposed model simulates the average, first, and third quarters and range of changes in the data by 5 and 95% better than the two CARMA and CARMA-GARCH models.

     

Evaluating and Calibrating Reference Evapotranspiration Models Using Water Balance under Hyper-Arid Environment

This research investigates five reference evapotranspiration models (one combined model, one temperature-based model, and three radiation-based models) under hyper-arid environmental conditions at the operational field level. These models were evaluated and calibrated using the weekly water balance of alfalfa by EnviroSCAN to calculate crop evapotranspiration (ET_c). Calibration models were evaluated and validated using wheat and potatoes, respectively, on the basis of weekly water balance. Based on the results and discussion, the FAO-56 Penman-Monteith model proved to be superior in estimating ET_c with a slight underestimation of 2 %. Meanwhile, the Hargreaves-Samani (HS) model (temperature-based) underestimated ET_c by 20 % and the Priestley-Taylor (PT) and Makkink (MK) models (radiation-based) had similar performances underestimating by up to 35 % of the measured ET_c. The Turc (TR) model had the lowest performance compared with other models, demonstrating values underestimated by up to 60 % of the measured ET_c. Local calibration based on alfalfa evapotranspiration measurements was used to rectify these underestimations. The surprisingly good performance of the calibrated simple HS model, with a new coefficient 0.0029, demonstrated its favorable potential to improve irrigation scheduling. The MK and PT models were in third and fourth rank, respectively, reflecting minor differences between one another. The new coefficients obtained for the MK and PT models were 1.99 and 0.963, respectively. One important observation was that the calibrated TR model performed poorly, with an increase in its coefficient from 0.013 to 0.034 to account for hyper-arid environmental conditions; moreover, it required additional seasonal calibration to adequately improve its performance.     

回归模型在抚仙湖水量预报上的分析应用

基于回归分析能生成数学表达式,并能对数据进行预测的独到优越性,在对影响抚仙湖蓄水情况的降雨因素进行分析的基础上,运用多元回归和逐步回归分析方法,找出影响抚仙湖蓄水的主要因子,建立预报模型。通过分析比较,结果表明:多元回归模型预报效果最佳,可用于对抚仙湖蓄水量开展中长期预报,为湖泊调度管理提供可靠依据。     

基于气温预报的HS公式短期逐日参考作物腾发量预报评价与分析

为了开展基于气温预报Hargreaves-Samani(HS)公式短期逐日参考作物腾发量预报评价分析,收集南京站2002—2013年逐日观测气象数据和2012—2013年预见期7 d的逐日天气预报数据,采用FAO-56 Penman-Monteith(PM)公式及2002—2012年气象数据计算逐日ET₀(参考作物腾发量),并对Hargreaves-Samani(HS)公式参数进行率定。采用率定后的HS公式开展2012—2013年预见期7 d的ET₀预报,并对预报结果进行精度评价和敏感性分析,结果表明:最低温度预报准确率要高于最高温度;校正后的HS公式各相关统计指标较好,HS公式ET₀计算校正值与PM公式计算值总体上一致,校正后的HS公式精度得到提高;ET₀预报精度随预见期增加而下降,且基于最低温预报的ET₀预报精度要高于最高温度;ET₀预报误差对低温预报的敏感性要小于高温预报,ET₀预报误差对夏季温度预报误差敏感性最大,而对冬季温度预报误差敏感性最小。     

Real-Time Flow Forecasting in a Watershed Using Rainfall Forecasting Model and Updating Model

Water Resources Management - Watershed is the basic unit for studying different hydrologic processes. Flow forecasting in a watershed is dependent upon the rainfall. The effect of erroneous...     

Performance Evaluation of Reference Evapotranspiration Estimation Using Climate Based Methods and Artificial Neural Networks

This study is an attempt to find best alternative method to estimate reference evapotranspiration (ET_o) for the Mahanadi reservoir project (MRP) command area located at Raipur (Chhattisgarh) in India, when input climatic parameters are insufficient to apply standard Food and Agriculture Organization (FAO) of the United Nations Penman–Monteith (P–M) method. To identify the best alternative climatic based method that yield results closest to the P–M method, performances of four climate based methods namely Blaney–Criddle, Radiation, Modified Penman and Pan evaporation were compared with the FAO-56 Penman–Monteith method. Performances were evaluated using the statistical indices. The statistical indices used in the analysis were the standard error of estimate (SEE), raw standard error of estimate (RSEE) and the model efficiency. Study was extended to identify the ability of Artificial Neural Networks (ANNs) for estimation of ET_o in comparison to climatic based methods. The networks, using varied input combinations of climatic variables have been trained using the backpropagation with variable learning rate training algorithm. ANN models were performed better than the climatic based methods in all performance indices. The analyses of results of ANN model suggest that the ET_o can be estimated from maximum and minimum temperature using ANN approach in MPR area.     

Symbolic Regression Equations for Calculating Daily Reference Evapotranspiration with the Same Input to Hargreaves-Samani in Arid China

To present an alternative simple equation for reference evapotranspiration (ET _o) estimation, the symbolic regression (SR) method was applied to establish equations with the same inputs to simple Hargreaves-Samani (HS) equation in arid China. For most of the equations derived by SR method for each station, their performance increased with an increase in the equation complex index (CI). The most precise equation performed well although it was always complex and greatly varied in form. On the other hand, the simplest one was uniform in equation structure and performed slightly better than the HS equation for all the five stations, and sometimes better than the local calibrated HS equation. A trade-off equation was selected with almost the same equation form for all the five stations and low CI index. The site-specific trade-off equation performed better than the simplest one and the locally calibrated HS equation. Then parameters in the trade-off equation were unified for all the five stations, it did not perform as good as the site-specific one, but performed better than the HS equation and unified local calibrated HS equation. Thus, the SR method is suitable to determine both the site-specific and the unified equation among stations for daily ET _o calculation in arid regions.     

混合门限回归模型在河道水位预报中的应用

针对松花江干流汛期洪水的特点以及松花江流域防洪减灾的需求,采用多元门限回归模型建立了松花江干流肇源、三家子、涝洲、木兰、富锦5个水位站的水位预报模型;在多元门限回归模型的基础上进行改进,得到混合门限回归模型,并以此建立松花江干流5个站的水位预报模型。两种模型的预报因子均通过AIC准则和DW检验法筛选确定,并用最小二乘法估算模型的参数。选取各水位站2008—2012年汛期的水位资料分别率定相应的水位预报模型,选取2013年汛期的水位资料对各个率定的模型进行验证。率定和验证的结果表明:多元门限回归模型的预报精度偏低,而混合门限回归模型的预报精度高,且有一定的通用性,适用于水位预报。     

Crop Reference Evapotranspiration: A Discussion of the Concept,Analysis of the Process and Validation

The study at first recalls the concept of “potential evapotranspiration” (PET), originally considered equal to the evaporation climatic demand; then, it reminds the steps of its progressive evolution toward the concept of “reference crop evapotranspiration” (ET₀) determined on irrigated grass. A physical analysis conducted on the evaporation process is subsequently reported to help clarifying the links between ET₀ and evaporation climatic demand. This analysis clearly demonstrates that the equivalence of ET₀ to evaporation climatic demand is not correct, although still common assumption in recent scientific literature, particularly in hydrology. The study also identifies two processes acting in opposite directions in the dynamics of ET₀: (1) the climatic variables determining the evaporation demand, and (2) the canopy resistance which slows down the response of irrigated grass to such demand. The analysis of the respective impact of these two processes on ET₀ dynamics shows that the available energy is the dominant process. This variable takes into account the 60–70% of the variation of ET₀, both at hourly and daily scales, while canopy resistance only explains 10–20% of ET₀ variation of irrigated grass. The study regards different climatic situations. Possible effects on practical applications were also discussed in the conclusions, together with comments on the correct canopy resistance modelling.     

Forecasting High-Frequency River Level Series Using Double Switching Regression with ARMA Errors

River level forecasting is a difficult problem. Complex river dynamics lead to level series with strong time-varying serial correlation and nonlinear relations with influential factors. The current high-frequency level series present a new challenge: they are measured hourly or at finer time scales, but predictions of up to several days ahead are still needed. In this framework, prediction models must be able to provide h-step predictions for high h values. This work presents a new nonlinear model, double switching regression with ARMA errors, that addresses the features of level series. It distinguishes different regimes both in the regression and in the error terms of the model to capture time-varying correlations and nonlinear relations between response and predictors. The use of different regression and ARMA regimes will provide good h-step prediction for both low and high h values. We also propose a new estimation method that, in contrast to other switching models, does not need to define the regimes before estimating the model. This method is based on a two-step estimation and model-based recursive partitioning. The approach is applied to model the hourly levels of the Ebro River in Zaragoza (Spain), using as input an upstream location, Tudela. Using the fitted model, we obtain hourly predictions and confidence intervals up to three days ahead, with very good results. The model outperforms previous approaches, especially with high values and in cases of long-term predictions.

     

Optimizing the Runoff Estimation with HEC-HMS Model Using Spatial Evapotranspiration by the SEBS Model

Most of the commonly used hydrological models do not account for the actual evapotranspiration (ETa) as a key contributor to water loss in semi-arid/arid regions. In this study, the HEC-HMS (Hydrologic Engineering Center Hydrologic Modeling System) model was calibrated, modified, and its performance in simulating runoff resulting from short-duration rainfall events was evaluated. The model modifications included integrating spatially distributed ETa, calculated using the surface energy balance system (SEBS), into the model. Evaluating the model’s performance in simulating runoff showed that the default HEC-HMS model underestimated the runoff with root mean squared error (RMSE) of 0.14 m³/s (R²?=?0.92) while incorporating SEBS ETa into the model reduced RMSE to 0.01 m³/s (R²?=?0.99). The integration of HECHMS and SEBS resulted in smaller and more realistic latent heat flux estimates translated into a lower water loss rate and a higher magnitude of runoff simulated by the HECHMS model. The difference between runoff simulations using the default and modified model translated into an average of 95,000 m³ runoff per rainfall event (equal to seasonal water requirement of ten-hectare winter wheat) that could be planned and triggered for agricultural purposes, flood harvesting, and groundwater recharge in the region. The effect of ETa on the simulated runoff volume is expected to be more pronounced during high evaporative demand periods, longer rainfall events, and larger catchments. The outcome of this study signifies the importance of implementing accurate estimates of evapotranspiration into a hydrological model.

     

Multiple Linear Correlation Analysis of Daily Reference Evapotranspiration

An accurate estimation of reference evapotranspiration (ET₀) is of paramount importance for many studies such as hydrologic water balance, irrigation system design and management, crop yield simulation, and water resources planning and management. Simple regression techniques, may sometimes, provide adequate estimation of ET₀. Implementation of regression methods considering all the predictor variables may, however, lead to overfit and consequent reduction in the predictive capability. The regression models for ET₀ have been developed in the present study for Tirupati, Nellore, Rajahmundry, Anakapalli and Rajendranagar regions of Andhra Pradesh, India by following step-wise procedure, eliminating superfluous predictor variables based on statistical criteria. The sunshine hours, wind velocity, temperature and relative humidity influenced ET₀ in the study area. The linear regression models developed in terms of predictor variables may conveniently be applied in the regions selected for the present study and, in the regions with similar climatic conditions for satisfactory ET₀ estimation.     

Evaluation of Reference Evapotranspiration Equations Under Humid Conditions

Five reference evapotranspiration (ET₀) equations are evaluated using data from seven humid locations. The equations evaluated include Hargreaves, Thornthwaite, Turc, Priestley–Taylor, and Jensen–Haise. The objective of this study is to evaluate ET₀ estimated by these equations against the corresponding values estimated using the standardized FAO-56 Penman–Monteith (PM) equation. For each location, ET₀ estimates by the all equations were statistically compared with FAO-56 PM ET₀ estimates. The Turc equation yielded the smallest root-mean-square-difference (RMSD) values at the all locations except Novi Sad, Serbia. The final ranking of equations was based on the weighted RMSD. The Turc equation has the lowest weighted RMSD and ranking first, and other equations ranked in decreasing order are: Priestley–Taylor, Jensen–Haise, Thornthwaite, and Hargreaves. The Turc equation gives the reliable calculation at all humid locations and it has proven to be the most adjustable to the local climatic conditions. The results obtained from this study, indicate very clearly that the Turc equation is most suitable for estimating reference evapotranspiration at humid locations when weather data are insufficient to apply the FAO-56 PM equation.     

Estimation of Monthly Mean Reference Evapotranspiration in Turkey

Monthly mean reference evapotranspiration (ET ₀ ) is estimated using adaptive network based fuzzy inference system (ANFIS) and artificial neural network (ANN) models. Various combinations of long-term average monthly climatic data of wind speed, air temperature, relative humidity, and solar radiation, recorded at stations in Turkey, are used as inputs to the ANFIS and ANN models so as to calculate ET ₀ given by the FAO-56 PM (Penman-Monteith) equation. First, a comparison is made among the estimates provided by the ANFIS and ANN models and those by the empirical methods of Hargreaves and Ritchie. Next, the empirical models are calibrated using the ET ₀ values given by FAO-56 PM, and the estimates by the ANFIS and ANN techniques are compared with those of the calibrated models. Mean square error, mean absolute error, and determination coefficient statistics are used as comparison criteria for evaluation of performances of all the models considered. Based on these evaluations, it is found that the ANFIS and ANN schemes can be employed successfully in modeling the monthly mean ET ₀ , because both approaches yield better estimates than the classical methods, and yet ANFIS being slightly more successful than ANN.