Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems. In this entry, we introduce ANN using familiar econometric terminology and provide an overview of ANN modeling approach and its implementation methods. † Correspondence: Chung-Ming Kuan, Institute of Economics, Academia Sinica, 128 Academia Road, Sec. 2, Taipei 115, Taiwan; ckuan@econ.sinica.edu.tw. †† I would like to express my sincere gratitude to the editor, Professor Steven Durlauf, for his patience and constructive comments on early drafts of this entry. I also thank Shih-Hsun Hsu and Yu-Lieh Huang for very helpful suggestions. The remaining errors are all mine.

Artificial neural networks

A comparison of methods to avoid overfitting in neural networks training in the case of catchment runoff modelling

A statistical point-process model is derived to describe the standard activity of earthquake occurrences by assuming that general seismicity is given by the superposition of aftershock sequences. The parameters are estimated ty the maximum likelihood method. Using the estimated model, the “residual point process” of the data is defined and used to find the anomalies which are included in the data set but not captured in the considered model for the standard seismicity. For instance, seismic quiescences can be measured quantitatively by using the residual process. Some examples are provided to illustrate such analyses. Furthermore, a time series of the magnitudes on the residual point process is considered, to investigate its dependence either on the time or on the history of the seismicity. By assuming the exponential distribution at each time and modelling of the b- value , we can examine such dependences and estimate them. Two practical examples are shown.

Statistical model for standard seismicity and detection of anomalies by residual analysis

Optimizing neural networks for river flow forecasting – Evolutionary Computation methods versus the Levenberg–Marquardt approach

Lightning produces electromagnetic fields and waves in all frequency ranges. In the extremely low frequency (ELF) range below 100 Hz, the global Schumann Resonances (SR) are excited at frequencies of 8 Hz, 14 Hz, 20 Hz, etc. This review is aimed at the reader generally unfamiliar with the Schumann Resonances. First some historical context to SR research is given, followed by some theoretical background and examples of the extensive use of Schumann resonances in a variety of lightning-related studies in recent years, ranging from estimates of the spatial and temporal variations in global lighting activity, connections to global climate change, transient luminous events and extraterrestrial lightning. Both theoretical and experimental results of the global resonance phenomenon are presented. It is our hope that this review will increase the interest in SR among researchers previously unfamiliar with this phenomenon.

https://www.mdpi.com/2073-4433/7/9/116/pdf

ELF Electromagnetic Waves from Lightning: The Schumann Resonances

Wave equations in an anisotropic plasma imbedded in a moving dielectric medium have been derived through Maxwell-Minkowski relations. These are solved for longitudinal and transverse cases of propagation. The dispersion relation within the medium has been deduced through which the nature of splitting may be understood.

Field solution in an anisotropic plasma imbedded in a moving dielectric medium

Normal 0 MicrosoftInternetExplorer4 The unusual variations observed in the records of the integrated field intensity of the atmospherics (IFIA) at 6 kHz and 9 kHz at Agartala, Tripura, in the north-eastern state of India (latitude, 23˚ N; longitude, 91.4˚ E) during the large earthquake on October 8, 2005 at Muzaffarabad (latitude, 34.53˚ N; longitude, 73.58˚ E) in Kashmir in Pakistan are here analyzed. Spiky variations in the IFIA at 6 kHz and 9 kHz were observed several days previous to the day of the earthquake (from midnight, September 28, 2005). The effects persisted for some days, decayed gradually, and eventually ceased on October 31, 2005. The spikes are distinctly superimposed on the ambient level, with mutual separation of 2–5 mins. The number of spikes per day and the total duration of their occurrence were particularly high on the day of the earthquake. The spike heights are higher at 6 kHz than at 9 kHz. The results are discussed here. The generation of electromagnetic radiation associated with the fracture of rocks, the subsequent penetration of this radiation into the Earth atmosphere, and finally its propagation through the Earth–ionosphere waveguide may be responsible for these observed spikes. The present observations show that the very low frequency anomaly dominates between 6 kHz and 9 kHz. The nature of the spikes presented here is a characteristic feature of the IFIA during the period of the earthquake. This has been established on the basis of time-series analyses over a period of one year.

/pdf/effects-of-the-india-pakistan-border-earthquake-on-the-5otydiqhhc.pdf

Effects of the India-Pakistan border earthquake on the atmospherics at 6 kHz and 9 kHz recorded at Tripura

This study reports univariate modeling methodologies applied to the maximum tsunami wave height over Sibolga, Sumatra. The univariate time series models fitted are autoregressive model (AR), autoregressive integrated moving average (ARIMA) and autoregressive neural network (AR-NN). Goodness of fit of the models to the time series of maximum tsunami wave height has been assessed using percentage of prediction error, Pearson correlation coefficient, and Willmott's indices. After rigorous skill assessment using the above three models, the AR-NN model with seven previous values as predictor has been identified as the best predictive model for the time series under study.

Time series modelling of maximum tsunami wave heights recorded in Sibolga (Sumatra)

Asymmetries of Thomson scatter spectra occurring at different heights have been investigated through differential ion-flow technique using BGK form of Boltzmann equation. The result is useful to study the frequency broadening and bite-out centre of power spectra of incoherent scatter signals.

Asymmetries of Thomson scatter spectra from the terrestrial ionosphere

A brief review of Cerenkov radiation within the upper atmospheric plasma has been presented. Different attempts in this context are systematically discussed. The results of analysis about the nature and characteristics of VLF hisses in terms of incoherent Cerenkov radiation are given in a concise manner. The occurrence of resonance cone has also been reported.

Syam Sundar De

Papers

Field solution in an anisotropic plasma imbedded in a moving dielectric medium

Effects of the India-Pakistan border earthquake on the atmospherics at 6 kHz and 9 kHz recorded at Tripura

Time series modelling of maximum tsunami wave heights recorded in Sibolga (Sumatra)

Asymmetries of Thomson scatter spectra from the terrestrial ionosphere

Čerenkov radiation within the Earth's upper atmosphere