Electron density irregularity structures, often associated with ionospheric plasma bubbles, drive amplitude and phase fluctuations in radio signals that, in turn, create a phenomenon known as ionospheric scintillation. The phenomenon occurs frequently around the magnetic equator where plasma instability mechanisms generate postsunset plasma bubbles and density depletions. A previous correlation study suggested that scintillation at the magnetic equator may provide a forecast of subsequent scintillation at the equatorial ionization anomaly southern peak. In this work, it is proposed to predict the level of scintillation over São Luís (2.52°S, 44.3°W; dip latitude:~2.5°S) near the magnetic equator with lead time of hours but without specifying the moment at which the scintillation starts or ends. A collection of extended databases relating scintillation to ionospheric variables for São Luís is employed to perform the training of an artificial neural network with a new architecture. Two classes are considered, not strong (null/weak/moderate) and strong scintillation. An innovative scheme preprocesses the data taking into account similarities of the values of the variables for the same class. A formerly proposed resampling heuristic is employed to provide a balanced number of tuples of each class in the training set. Tests were performed showing that the proposed neural network is able to predict the level of scintillation over the station on the evening ahead of the data sample considered between 17:30 and 19:00 LT.
Ionospheric scintillation refers to amplitude and phase fluctuations in radio signals due to electron density irregularities associated to structures named ionospheric plasma bubbles. The phenomenon is more pronounced around the magnetic equator where, after sunset, plasma bubbles of varying sizes and density depletions are generated by plasma instability mechanisms. The bubble depletions are aligned along Earth's magnetic field lines, and they develop vertically upward over the magnetic equator so that their extremities extend in latitude to north and south of the dip equator. Over Brazil, developing bubbles can extend to the southern peak of the Equatorial Ionization Anomaly, where high levels of ionospheric scintillation are common. Scintillation may seriously affect satellite navigation systems, such as the Global Navigation Satellite Systems. However, its effects may be mitigated by using a predictive model derived from a collection of extended databases on scintillation and its associated variables. This work proposes the use of a classification and regression decision tree to perform a study on the correlation between the occurrence of scintillation at the magnetic equator and that at the southern peak of the equatorial anomaly. Due to limited size of the original database, a novel resampling heuristic was applied to generate new training instances from the original ones in order to improve the accuracy of the decision tree. The correlation analysis presented in this work may serve as a starting point for the eventual development of a predictive model suitable for operational use.
RESUMOO objetivo do trabalho proposto é detectar antecipadamente possíveis ocorrências de eventos convectivos severos, por meio do monitoramento das saídas do modelo de previsão numérica de tempo Eta, para cada intervalo de previsão e para um conjunto de variáveis selecionadas. O período de estudo estende-se de janeiro a fevereiro de 2007. Classificadores foram desenvolvidos pela abordagem de similaridade de vetores e de conjuntos aproximativos, de forma a identificar saídas do modelo Eta que possam ser associados a esses eventos. Assumiu-se como premissa que os eventos convectivos severos possam ser correlacionados com grande número de ocorrências de descargas elétricas atmosféricas. Os classificadores agruparam as saídas do modelo Eta, compostas por essas variáveis, com base na densidade de ocorrência de descargas elétricas atmosféricas nuvem-solo. Ambos os classificadores apresentaram bom desempenho para os testes realizados para um período de dois meses escolhido para três mini-regiões selecionadas do território brasileiro. Palavras-Chave: mineração de dados, previsão meteorológica, eventos convectivos. ABSTRACT: METEOROLOGICAL DATA MINING FOR THE PREDICTION OF SEVERE CONVECTIVE EVENTSThis work aims the early detection of possible occurrences of severe convective events in Central and Southeast Brazil by means of monitoring the output of the Eta numerical weather prediction model for each forecasted time interval and for a selected set of variables. The studied period ranges from January to February 2007. Classifiers were developed by two approaches, vector similarity and rough sets, in order to identify Eta outputs that can be associated to such events. It was assumed that severe convective events can be correlated to a large number of atmospheric electric discharges. The classifiers grouped the Eta meteorological model outputs for these selected variables based on the density of occurrences of cloud-to-ground atmospheric electrical discharges. Both classifiers show good performance for the chosen 2-month period at the three selected mini-regions of the Brazilian territory.
In the last decades, artificial neural network has been increasingly applied in hydrological modeling given its potential to process the complex nonlinear relationships of the associated physical-environmental variables and produce a suitable solution (for instance, a forecasting model) in a relatively short time. In this scope, this work reports the design methodology and the operational results obtained with an artificial neural network-based model developed to forecast, with 2 h in advance, the level of a river in the mountainous region of Rio de Janeiro state in Brazil. This is an area susceptible to natural disasters with recent records of floods and landslides that caused environmental and socio-economic damage of large proportions. The proposed neural network uses an innovative learning algorithm (the quasi-Newton optimization method is applied to the slopes of each hidden activation function) and, as input features, values of rainfall and river level data collected from 8 monitoring stations located on studied watershed between 2013 and 2014. The results of the neural model, with NASH index greater than 0.86, are promising making possible its operational use on an issuing flood alerts system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.