The study considers the impact of the environmental contamination by the electromagnetic radiation of electron beam generator and high-energy radioactive source on the memory components. Electron beam generator can be used for injecting particle energy into the plasma of the fusion system based on a Marx generator, while radioactive source as a simulator of high-energy ionizing radiation that can be caused by the neutron-induced activation of plasma surrounding structures or released from deuterium-tritium fusion reaction. The effects of gamma radiation of high-energy radioactive source and electric field of the electron beam generator on EPROM and EEPROM semiconductor computer memory, were investigated. An older memory types were deliberately chosen for the reason that their more robust construction will better protect them from the effects of ionizing and non-ionizing radiation. The results obtained under well-controlled conditions show a high degree of non-resistance of the semiconductor technology to the expected electromagnetic pollution of the electron beam generator and high-energy radioactive source. This conclusion raises doubts on the possibility of simultaneous application of electron beam generator, consequently fusion system and nanotechnologies with the increasing need for miniaturization of electronic components.

In nuclear physics experiments, it is very important to isolate the measured quantities from electromagnetic noise. Without this possibility, it is impossible to obtain usable experimental results since natural electromagnetic noise can be several orders of magnitude larger than the measured magnitude. In order to enable such measurements, it is necessary to eliminate electromagnetic noise from the experimental procedure. This is achieved by shielding against electromagnetic radiation. In this paper, experiments were performed to protect a room from electromagnetic noise. By applying all known methods of shielding against electromagnetic radiation, it was concluded that the room can be protected from the electrical component, but it is impossible to protect it from the magnetic component of electromagnetic radiation.

The miniaturization of computer facilities conditioned by the miniaturization of applied components makes them very sensitive to radioactive radiation. This is where neutron and electromagnetic radiation come to the fore. The reason for the particularly pronounced effects of this radiation is the fact that they do not interact with the Coulomb force, so they pass (leave) the reactor vessel unimpeded. This study examines the reliability of magnetic and semiconductor computer memories in the field of neutron and gamma radiation. This study experimental, and conducted under well-controlled conditions. The combined measurement uncertainty of the experimental procedure is less than 5 %. Sophisticated methods of mathematical statistics were used to process the stochastic results of measurements.

Mathematical methods are the basis of most models that describe the natural phenomena around us. However, the well-known conventional mathematical models for atmospheric modeling have some limitations. Machine learning with Big Data is also based on mathematics but offers a new approach for modeling. There are two methodologies to develop deep learning models for spatio-temporal image prediction. On these bases, two models were built—ConvLSTM and CNN-LSTM—with two types of predictions, i.e., sequence-to-sequence and sequence-to-one, in order to forecast Aerosol Optical Thickness sequences. The input dataset for training was NASA satellite imagery MODAL2_E_AER_OD from Terra/MODIS satellites, which presents global Aerosol Optical Thickness with an 8 day temporal resolution from 2000 to the present. The obtained results show that the ConvLSTM sequence-to-one model had the lowest RMSE error and the highest Cosine Similarity value. The advantages of the developed DL models are that they can be executed in milliseconds on a PC, can be used for global-scale Earth observations, and can serve as tracers to study how the Earth’s atmosphere moves. The developed models can be used as transfer learning for similar image time-series forecasting models.