The parameters of lightning discharges were estimated using long-term data of the automated system of lightning detection. It was shown that the dynamic monitoring of these parameters is an effective step towards solving the problem of lightning protection. Studies of electrical parameters of discharges in the atmosphere using the data of the geophysical monitoring system, including a network of automatic lightning sensors LS8000, comprise more than five million lightning discharges for the South of Russia territory during 2009-2017. The values of lightning discharges parameters obtained during the observation period make it possible to identify the main characteristics. The regularities of changes in the parameters characterizing the electrical activity of the atmosphere in different periods of time and in different climatic zones of the southern region of the Russian Federation were investigated. Modeling with use of the statistical dependences approximation built on the distribution data reveals the main factors affecting the distributions and makes it possible to carry out the territorial zoning according to the degree of emerging risks.
Interest in lightning research is primarily associated with the negative consequences of their direct impact, leading to fires, damage of power lines, failure of sensitive electronics and communication networks, etc. In order to prevent and protect against these consequences the detection of occurrence time and spatial position of thunderstorms, assessment of their danger degree and the direction of further development are very important. Data of lightning discharges distribution, their number and value of the current over the territory is required for lightning protection measures. Research of thunderstorm dynamics is required to understand the nature of thunderstorms. The monthly distributions of discharges were studied. This allowed to trace the trends of thunderstorms development and density of discharges per unit area. Technology of lightning sensing significantly decreases the risks of lightning damage and also takes into account the thunderstorm activity for the purpose of design and placement of buildings and structures. It is aimed at minimizing the serious violations in the power industry, mass accidents and damage to power lines, which, in turn, determines its high economic efficiency.
The mechanisms of dangerous effects of lightning discharges are investigated in the paper. Analysis of electrical parameters of thunderstorm discharges in the atmosphere using the data of geophysical monitoring center of the High- Mountain Geophysical Institute (Nalchik, Russia), which includes a network of automatic lightning sensors LS8000 were fulfilled. The results of the ground discharges registration and the time of their increase received during its operation are analyzed. The authors determined the statistical distribution of the amplitude of the lightning current. It is found that the parameters of the discharges in different areas are varies in a great range and can change over time. The effective operation of lightning protection systems and the implementation of life safety measures in case of thunderstorms requires monitoring of the lightning discharge situation in each region.
KEYWORDS: Neurons, Signal processing, Data processing, Sensors, Artificial intelligence, Neural networks, Chemical elements, Information technology, Electric field sensors, Image compression
Methods of artificial intelligence are a good solution for weather phenomena forecasting. They allow to process a large amount of diverse data. Recirculation Neural Networks is implemented in the paper for the system of thunderstorm events prediction. Large amounts of experimental data from lightning sensors and electric field mills networks are received and analyzed. The average recognition accuracy of sensor signals is calculated. It is shown that Recirculation Neural Networks is a promising solution in the forecasting of thunderstorms and weather phenomena, characterized by the high efficiency of the recognition elements of the sensor signals, allows to compress images and highlight their characteristic features for subsequent recognition.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.