Search

A comparison was made of the main transfer functions in the hidden layer of a nonlinear autoregressive neural network with an external input (NARX) to predict changes in the methane content in the surface layer of atmospheric air. Four transfer functions were used: S-type transfer function (LS), S-type hyperbolic tangent transfer function (TS), radial basis transfer function (RB), rectified linear units (LReLU). In general, all models were good at predicting changes in surface methane concentration. The most accurate results were obtained by the model, which using the RB type transfer function. [ABSTRACT FROM AUTHOR]

The results of the prediction of a model based on an artificial neural network were compared to predict the concentration of carbon dioxide (CO2) in the surface layer of the atmosphere for different time intervals. Measurements were taken on the Arctic island of Belyy, Russia. For comparison, three time intervals were used, which differed in the dependence of carbon dioxide concentration on the time of day. A non-linear autoregressive neural network with external input (NARX) was used. The model based on NARX successfully coped with the prediction. The smallest error was for the time intervals with a strong dependence of CO2 concentration on the time of day. [ABSTRACT FROM AUTHOR]

To studying variability of atmospheric particulate matter (PM), dust content measurements in location without industrial air pollution are very useful. The first time the air dust content and the size distribution were studied at 73.1° North latitude. This research presents data of the mass concentration and size-distribution of PM in the surface layer of atmospheric air on the Arctic island Belyy, Russia. The data was collected in Belyy Island, Yamal Peninsula, Siberia, Russia, in July of the same year. The mean air dust concentration was lower instrument limit of detection. The particle size distributions had two dominant Land Breeze and Sea Breeze patterns associated with the wind direction. [ABSTRACT FROM AUTHOR]

The mass concentration, size-distribution, height stratification and season variability of atmospheric particulate matter (PM) were researched in residential quarters of the industrial city in Ekaterinburg, Russia. The air dust samples were collected from March to May 2016. The particle size distribution in Ekaterinburg showed that most particles had diameters in the range of 0.5–2.5 µm. The particulate matter size distributions had dominant pattern with right tail and maximum was near 1 µm. [ABSTRACT FROM AUTHOR]

Psychophysics investigates the link between the objective stimuli and the sensations caused by them. Weber, Fechner, Stevens were solving this problem, in due time. Later the psychophysical model of the signal detection theory with four outcomes was proposed. This classical model quantitatively descriptions process of detection of a signal, but not its sign. This circumstance limits the use of the classical model. In this work we continue to develop the psychophysical model of the signal detection theory with nine outcomes (PMSDT9) for a sign alternating differential signals. On the example of the horizontal lines, the dependence of the parameters of probability density functions of the activity of neurons (arbitrary units) of the subject on the difference in line lengths is investigated. We found that increasing of the intensity of differential signal results increasing distance between probability density functions of neuronal activity (arbitrary units) faster than increasing their standard deviations. [ABSTRACT FROM AUTHOR]

In the study was proposed a new approach to the data preparation for the modelling the spatial distribution of the impurity in a heterogeneous environment. The data were obtained during soil screening of the urbanized territory in Tarko Sale, Yamalo-Nenets Autonomous Okrug, Russia. For the modelling, was used a model based on an artificial neural network (ANN) - a Multilayer Perceptron (MLP) with the Levenberg-Marquart training algorithm. The spatial distribution of the Copper (Cu) content in the surface layer of the soil was modelled. The data preparation algorithm based on the quantile division to the training and test subsamples was proposed. A comparison was made with the traditionally applied random separation of the original sample. [ABSTRACT FROM AUTHOR]

When studying the processes associated with global warming, forecasts of time series are very important. The present study used data of the concentration of greenhouse gas methane in the surface layer of atmospheric air on the Arctic island Belyi, Russia. For the work, a time interval of 170 hours was chosen. For the modelling, a model based on a nonlinear autoregressive neural network with an external input (NARX) was used. As a training algorithm three types were applied: Levenberg-Marquart (LM), LM with Bayesian regularization (BR), and a gradient descent with a speed parameter setting (GDA). Methane concentrations corresponding to the first 150 hours of the interval used to train the NARX network, then the concentrations were predicted for the next 20 hours. The model using the training algorithm LM was the most accurate. [ABSTRACT FROM AUTHOR]

Statistical analysis of the monitoring data of industrial enterprises influence zones is an important part of the researches related to natural environment changes. In present study, a cluster analysis of the elemental composition of the snow cover in the vicinity of a copper mine was carried out. The data were obtained as a result of the chemical analysis of the snow samples collected during annual environmental monitoring in the region of Rezh town (the Middle Ural of Russia), where Safyanovsky Copper Mine and Rezhevsky Nickel Plant are located. The elements identified by chemical analysis were grouped according to the strength of the correlation bond. The cluster analysis of these groups made it possible to identify and separate the influence zones of the Plant, Mine and other industrial objects located in the area. The obtained results became the basis for adjusting the snow cover monitoring scheme. [ABSTRACT FROM AUTHOR]

Creating models which are able to accurately predict the distribution of pollutants based on a limited set of input data is an important task in environmental studies. In the paper two neural approaches: (multilayer perceptron (MLP)) and generalized regression neural network (GRNN)), and two geostatistical approaches: (kriging and cokriging), are using for modeling and forecasting of dust concentrations in snow cover. The area of study is under the influence of dust emissions from a copper quarry and a several industrial companies. The comparison of two mentioned approaches is conducted. Three indices are used as the indicators of the models accuracy: the mean absolute error (MAE), root mean square error (RMSE) and relative root mean square error (RRMSE). Models based on artificial neural networks (ANN) have shown better accuracy. When considering all indices, the most precision model was the GRNN, which uses as input parameters for modeling the coordinates of sampling points and the distance to the probable emissions source. The results of work confirm that trained ANN may be more suitable tool for modeling of dust concentrations in snow cover. [ABSTRACT FROM AUTHOR]

We present the results of an analytical treatment and 3D numerical simulations of single attosecond pulse generation during ionization of atoms and molecules by an intense few-optical-cycle laser pulse. We study the possibilities to enhance the efficiency of high-order harmonic generation and to control spectral and temporal characteristics of attosecond pulses. We show that these enhancement and control can be achieved based on the concept of electron wave-packet engineering, which implies the control of the ionization process and electron propagation in the continuum by means of optimal preparation of the initial state of atom or molecule and laser pulse shaping. © 2006 American Institute of Physics [ABSTRACT FROM AUTHOR]

Coherent X-ray production via high-order harmonic generation in the stabilization regime is studied in detail in numerical experiments on two-dimensional model atoms and ions. The temporal behavior and the ellipticity dependence of harmonic intensities are shown to differ dramatically from those inherent to the well-studied low-frequency regime of harmonic generation. These peculiar properties can be used for X-ray short pulse generation and probing atomic stabilization. © 2002 American Institute of Physics. [ABSTRACT FROM AUTHOR]