ground penetrating radar

In modern conditions, the problem of mine detection remains one of the most urgent due to the serious threat to the life and health of people in contaminated areas. This paper presents an approach to mine detection using a hybrid neural network CNN+BiLSTM+Attention, which analyzes B-scan signals received from ground-penetrating radar systems. To improve the quality of training with a limited amount of data, image augmentation was used, which includes shifting, reflecting, scaling, and adding noise.

The purpose of the research was to verify the extraordinary big theoretical penetration depth of new developed georadar in the real conditions of karsts areas. The new kind of the Ground Penetrating Radar (GPR) – Roteg – was developed in 2013 (RTG-Tengler 2013). Its technical parameters (pulse peak on the transmitting antenna 20 kV or more, and the sensitivity of the receiving antenna at least 2 uV, i.e. the real signal detection level around 20 uV) express that the real signal detection sensitivity is 9 orders, i.e. 180 dB.

The aim of the research was to determine the territory of the mass graves near Ralivka village (Lviv region) using  archival data and to display them on modern maps. To define the place of mass executions and burials from the World War II period applying ground geophysical methods on the locations pre-defined from the archival aerial images obtained by the Germans in 1944. Methods.

Georadars - a modern geophysical instrument, the use of which for non-destructive research allows monitoring environment at shallow depths with high detail, making it unique among other geophysical equipment.
The method is the reflection of electromagnetic waves radiated from the interface layers with different dielectric constants.
These limits can be both geological features and local heterogeneity of various origins (voids).