Search

Accurate long-term runoff forecasting is crucial for managing and allocating water resources. Due to the complexity and variability of natural runoff, the most difficult problems currently faced by long-term runoff forecasting are the difficulty of model construction, poor prediction accuracy, and time intensive forecasting processes. Therefore, this study proposes a hybrid long-term runoff forecasting framework that uses the antecedent inflow and specific meteorological factors as the inputs, is modeled by ensemble empirical mode decomposition (EEMD) coupled with an artificial neural network (ANN), and computed by a parallel algorithm. First, the framework can transform monthly inflow and meteorological series into stationary signals via EEMD to more comprehensively explore the relationships of the input factors through the ANN. Second, the selected meteorological factors that are closely related to inflow formation can be filtered out by the single correlation coefficient method, which contributes to reducing coupling between input factors, and increases the accuracy of the prediction models. Finally, a multicore parallel algorithm that is easily accessed everywhere and that fully utilizes multiple calculation resources while flexibly contending with various optimization requirements will improve forecasting efficiency. The Xiaowan Hydropower Station (XW) is selected as the study area, and the final results of the study show that (1) the addition of targeted meteorological factors does indeed greatly enhance the performance of the prediction models; (2) the five criteria for evaluating the prediction accuracy show that the EEMD-ANN model is far superior to the prediction performance from the ordinary ANN model when run under the same input conditions; and (3) the optimization time of the 32-core model can be reduced by as much as 25 times, which significantly saves time during the forecast process. [ABSTRACT FROM AUTHOR]

With the expansion of wind power grid integration, the challenges of sharp fluctuations and high uncertainty in preparing the power grid day-ahead plan and short-term dispatching are magnified. These challenges can be overcome through accurate short-term wind power process prediction based on mining historical operation data and taking full advantage of meteorological forecast information. In this paper, adopting the ERA5 reanalysis dataset as input, a short-term wind power prediction framework is proposed, combining light gradient boosting machine (LightGBM), mutual information coefficient (MIC) and nonparametric regression. Primarily, the reanalysis data of ERA5 provide more meteorological information for the framework, which can help improve the model input features. Furthermore, MIC can identify effective feature subsets from massive feature sets that significantly affect the output, enabling concise understanding of the output. Moreover, LightGBM is a prediction method with a stronger ability of goodness-of-fit, which can fully mine the effective information of wind power historical operation data to improve the prediction accuracy. Eventually, nonparametric regression expands the process prediction to interval prediction, which significantly improves the utility of the prediction results. To quantitatively analyze the prediction results, five evaluation criteria are used, namely, the Pearson correlation coefficient (CORR), the root mean square error (RMSE), the mean absolute error (MAE), the index of agreement (IA) and Kling–Gupta efficiency (KGE). Compared with support vector regression (SVR), random forest (RF) and extreme gradient boosting (XGBoost) models, the present framework can make full use of meteorological information and effectively improve the prediction accuracy, and the generated output prediction interval can also be used to promote the safe operation of power systems. [ABSTRACT FROM AUTHOR]

Responding to the call for new verification methods in a recent editorial in Weather and Forecasting, this study proposed two new verification metrics to quantify the forecast challenges that a user faces in decision-making when using ensemble models. The measure of forecast challenge (MFC) combines forecast error and uncertainty information together into one single score. It consists of four elements: ensemble mean error, spread, nonlinearity, and outliers. The cross correlation among the four elements indicates that each element contains independent information. The relative contribution of each element to the MFC is analyzed by calculating the correlation between each element and MFC. The biggest contributor is the ensemble mean error, followed by the ensemble spread, nonlinearity, and outliers. By applying MFC to the predictability horizon diagram of a forecast ensemble, a predictability horizon diagram index (PHDX) is defined to quantify how the ensemble evolves at a specific location as an event approaches. The value of PHDX varies between 1.0 and −1.0. A positive PHDX indicates that the forecast challenge decreases as an event nears (type I), providing creditable forecast information to users. A negative PHDX value indicates that the forecast challenge increases as an event nears (type II), providing misleading information to users. A near-zero PHDX value indicates that the forecast challenge remains large as an event nears, providing largely uncertain information to users. Unlike current verification metrics that verify at a particular point in time, PHDX verifies a forecasting process through many forecasting cycles. Forecasting-process-oriented verification could be a new direction in model verification. The sample ensemble forecasts used in this study are produced from the NCEP global and regional ensembles. [ABSTRACT FROM AUTHOR]

The New England High-Resolution Temperature Program seeks to improve the accuracy of summertime 2-m temperature and dewpoint temperature forecasts in the New England region through a collaborative effort between the research and operational components of the National Oceanic and Atmospheric Administration (NOAA). The four main components of this program are 1) improved surface and boundary layer observations for model initialization, 2) special observations for the assessment and improvement of model physical process parameterization schemes, 3) using model forecast ensemble data to improve upon the operational forecasts for near-surface variables, and 4) transfering knowledge gained to commercial weather services and end users. Since 2002 this program has enhanced surface temperature observations by adding 70 new automated Cooperative Observer Program (COOP) sites, identified and collected data from over 1000 non-NOAA mesonet sites, and deployed boundary layer profilers and other special instrumentation throughout the New England region to better observe the surface energy budget. Comparisons of these special datasets with numerical model forecasts indicate that near-surface temperature errors are strongly correlated to errors in the model-predicted radiation fields. The attenuation of solar radiation by aerosols is one potential source of the model radiation bias. However, even with these model errors, results from bias-corrected ensemble forecasts are more accurate than the operational model output statistics (MOS) forecasts for 2-m temperature and dewpoint temperature, while also providing reliable forecast probabilities. Discussions with commerical weather vendors and end users have emphasized the potential economic value of these probabilistic ensemble-generated forecasts. [ABSTRACT FROM AUTHOR]

• A numerical model to predict flexural behavior of hybrid RC beams was proposed. • TCM was used to simplify the analysis of tension stiffening effect. • LSM was developed to simplify the description of softening behavior of concrete. • Simplified multilinear moment–curvature curve of hybrid RC beams was suggested. Hybrid fiber reinforced polymer (FRP)-steel reinforced concrete (RC) beams exhibit different flexural failure modes with different reinforcement ratios and the contributions from tensile region and compressive region of the beams to flexural behavior vary accordingly. Therefore, a general model to predict the global nonlinear behavior of hybrid FRP-steel RC beams featured by common flexural failure modes is critical to analysis and design. In this paper, flexural behavior of a hybrid FRP-steel RC beam is considered as the systematic combination of mechanical behavior of FRP and steel RC tension chords and concrete strut. The Tension Chord Model (TCM) for steel and its extended application for FRP, properly considering the bond performance between FRP/steel reinforcement and the surrounding concrete, are employed to represent the tension stiffening effect in tensile region; the Linear Softening Model (LSM), incorporating the compressive fracture energy and considering the confinement effect, is applied to predict the softening behavior of compressive concrete. Based on the primary principles of equilibrium and compatibility, the aforementioned two models are assembled to numerically evaluate the advanced moment–curvature relationship and flexural behavior. Due to the proper combination and application of mechanical models, the global evaluation process is significantly simplified and avoids the lengthy iterative calculations performed in conventional numerical methods. Finally, the proposed calculational model is validated by comparisons between the predictions and experimental results of hybrid FRP-steel RC beams with common flexural failure modes available in the literature. [ABSTRACT FROM AUTHOR]