Performance of the WRF Model for the Forecasting of the V-Shaped Storm Recorded on 11–12 November 2019 in the Eastern Sicily

Castorina, Giuseppe; Semprebello, Agostino; Insinga, Vincenzo; Italiano, Francesco; Caccamo, Maria Teresa; Magazù, Salvatore; Morichetti, Mauro; Rizza, Umberto

doi:10.3390/atmos14020390

Cited by 4 publications

(4 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Its simulation results outperform those of existing methods when compared. Te ANN model forecasts hourly energy consumption, and its model is trained using Levenberg-Marquardt (LM) and BP techniques [54]. Diferent parameters, like temperature, hourly/ weekly energy usage, and dry bulb data, are taken as input.…”

Section: Hybrid Forecasting Modelmentioning

confidence: 99%

“…To compute the performance of the proposed hybrid model, two case studies are examined. Te frst study is for the Hellenic interconnected power system, where time series load data [53] covers the period from 1 January 2015 to 30 June 2019, and temperature prediction data is acquired from the SKIRON meteorological model [54]. Tis presented model was trained with recorded data for the frst four years and tested with recorded data during 2018.…”

Section: Case Studiesmentioning

confidence: 99%

See 1 more Smart Citation

Application of Fuzzy-RBF-CNN Ensemble Model for Short-Term Load Forecasting

Yadav

Jamil

Rizwan

et al. 2023

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

Accurate load forecasting (LF) plays an important role in the operation and decision-making process of the power grid. Although the stochastic and nonlinear behavior of loads is highly dependent on consumer energy requirements, that demands a high level of accuracy in LF. In spite of several research studies being performed in this field, accurate load forecasting remains an important consideration. In this article, the design of a hybrid short-term load forecasting model (STLF) is proposed. This work combines the features of an artificial neural network (ANN), ensemble forecasting, and a deep learning network. RBFNNs and CNNs are trained in two phases using the functional link artificial neural network (FLANN) optimization method with a deep learning structure. The predictions made from RBFNNs have been computed and produced as the forecast of each activated cluster. This framework is known as fuzzy-RBFNN. This proposed framework is outlined to anticipate one-week ahead load demand on an hourly basis, and its accuracy is determined using two case studies, i.e., Hellenic and Cretan power systems. Its results are validated while comparing with four benchmark models like multiple linear regression (MLR), support vector machine (SVM), ML-SVM, and fuzzy-RBFNN in terms of accuracy. To demonstrate the performance of RBF-CNN, SVMs replace the RBF-CNN regressor, and this model is identified as an ML-SVM having 3 layers.

show abstract

Section: Hybrid Forecasting Modelmentioning

confidence: 99%

Section: Case Studiesmentioning

confidence: 99%

Application of Fuzzy-RBF-CNN Ensemble Model for Short-Term Load Forecasting

Yadav

Jamil

Rizwan

et al. 2023

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

show abstract

“…As a new generation of mesoscale numerical weather forecasting system, the WRF model is mainly applied in atmospheric research and operational forecasting [34]. Studies have shown that the ability of the WRF model used to simulate and forecast weather conditions can be improved by optimizing appropriate parameters in the study's areas [35,36]. CMAQ (Community Multiscale Air Quality) is a chemical transport model released by the United States Environmental Protection Agency (EPA, https://www.epa.gov/cmaq, accessed on 5 March 2024).…”

Section: Introductionmentioning

confidence: 99%

Analyses and Simulations of PM2.5 Pollution Characteristics under the Influence of the New Year’s Day Effects in China

Shi,

Hou,

Wang

et al. 2024

Atmosphere

View full text Add to dashboard Cite

Regional haze often occurs after the New Year holiday. To explore the characteristics of PM2.5 pollutions under the influence of the New Year’s Day effect, this study analyzed the spatiotemporal changes relating to PM2.5 during and around the New Year’s Day holiday in China from 2015 to 2022, and used the Weather Research and Forecasting-Community Multiscale Air Quality (WRF-CMAQ) model to study the effects of human activities and meteorological factors on PM2.5 pollutions, as well as the differences in the contributions of different industries to PM2.5 pollutions. The results show that for the entire study period (i.e., before, during, and after the New Year’s Day holiday) from 2015 to 2022, the average concentrations of PM2.5 in China decreased by 41.9% overall. In 2019~2022, the New Year’s Day effect was significant, meaning that the average concentrations of PM2.5 increased by 18.9~46.8 μg/m3 from before to after the New Year’s Day holiday, with its peak occurring (64.3~74.9 μg/m3) after the holiday. In terms of spatial differences, the average concentrations of PM2.5 were higher in the Beijing–Tianjin–Hebei region, the Yangtze River Delta, and central China. Moreover, the Beijing–Tianjin–Hebei region and its surrounding areas, the Chengdu–Chongqing region, the Fenwei Plain, and the middle reaches of the Yangtze River region were greatly affected by the New Year’s Day effect. Human activities led to higher increases in PM2.5 in Henan, Hubei, Hebei, and Anhui on 3 and 4 January 2022. If the haze was accompanied by cloudy days or weak precipitation, the accumulation of surface water vapor and atmospheric aerosols further increased the possibility of heavy pollution. It was found that, for the entire study period, PM2.5 generated by residential sources contributed the vast majority (60~100 μg/m3) of PM2.5 concentrations, and that the main industry sources that caused changes in time distributions were industrial and transportation sources.

show abstract

“…In many studies related to the modeling of atmospheric conditions, including meteorological elements directly related to cloud cover (convective phenomena, precipitation, thunderstorms, tornadoes, lightning, etc.) have been used, with sequence of domains 9 km, 3 km, 1 km [34,35,[39][40][41][42][43][44], which we also implemented. This method is one of the most widely used domain nesting schemes.…”

Section: Introductionmentioning

confidence: 99%

Impact of Domain Nesting on High-Resolution Forecasts of Solar Conditions in Central and Eastern Europe

Mierzwiak

Kroszczyński

2023

Energies

View full text Add to dashboard Cite

The article presents a study on the impact of the domain nesting method on the results of simulated solar conditions using the mesoscale Weather Research and Forecasting model. The analysis included 8 consecutive days (July 2022), which were characterized by cloudless conditions, as well as complex situations related to the passing of a cold front. The study covered a region located in Central and Eastern Europe—the southern area of eastern Germany. The results of the model simulations using the adopted domain configurations (with spatial resolutions of 9, 3, and 1 km; 3 and 1 km; and 5 and 1 km) were compared to data from ground measurements from Deutscher Wetterdienst (DWD) stations. The effect of the duration of the triggered prediction on the quality of the output data was also investigated, and for this purpose, short-term predictions covering 24 and 48 h, respectively, were selected. Research revealed the advantages of one combination of domains—3 and 1 km—over the others and showed that the results of simulations with different duration lengths were characterized by consistent results. Research supports the demand for high-quality forecasts of solar conditions, which are extremely important in the process of managing energy systems.

show abstract

Performance of the WRF Model for the Forecasting of the V-Shaped Storm Recorded on 11–12 November 2019 in the Eastern Sicily

Cited by 4 publications

References 59 publications

Application of Fuzzy-RBF-CNN Ensemble Model for Short-Term Load Forecasting

Application of Fuzzy-RBF-CNN Ensemble Model for Short-Term Load Forecasting

Analyses and Simulations of PM2.5 Pollution Characteristics under the Influence of the New Year’s Day Effects in China

Impact of Domain Nesting on High-Resolution Forecasts of Solar Conditions in Central and Eastern Europe

Contact Info

Product

Resources

About