| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Search the digital library catalog Help

Query: search in
search in
search in
search in
* old and bologna study programme

Options:
  Reset


1 - 2 / 2
First pagePrevious page1Next pageLast page
1.
Cross-Hole GPR for Soil Moisture Estimation Using Deep Learning
Blaž Pongrac, Dušan Gleich, Marko Malajner, Andrej Sarjaš, 2023, original scientific article

Abstract: This paper presents the design of a high-voltage pulse-based radar and a supervised data processing method for soil moisture estimation. The goal of this research was to design a pulse-based radar to detect changes in soil moisture using a cross-hole approach. The pulse-based radar with three transmitting antennas was placed into a 12 m deep hole, and a receiver with three receive antennas was placed into a different hole separated by 100 m from the transmitter. The pulse generator was based on a Marx generator with an LC filter, and for the receiver, the high-frequency data acquisition card was used, which can acquire signals using 3 Gigabytes per second. Used borehole antennas were designed to operate in the wide frequency band to ensure signal propagation through the soil. A deep regression convolutional network is proposed in this paper to estimate volumetric soil moisture using time-sampled signals. A regression convolutional network is extended to three dimensions to model changes in wave propagation between the transmitted and received signals. The training dataset was acquired during the period of 73 days of acquisition between two boreholes separated by 100 m. The soil moisture measurements were acquired at three points 25 m apart to provide ground truth data. Additionally, water was poured into several specially prepared boreholes between transmitter and receiver antennas to acquire additional dataset for training, validation, and testing of convolutional neural networks. Experimental results showed that the proposed system is able to detect changes in the volumetric soil moisture using Tx and Rx antennas.
Keywords: ground penetrating radar, cross-hole, L-band, deep learning, convolutional neural network, soil moisture estimation
Published in DKUM: 03.04.2024; Views: 448; Downloads: 26
.pdf Full text (3,22 MB)
This document has many files! More...

2.
Detecting karstic zones during highway construction using ground-penetrating radar
Matevž Uroš Pavlič, Blaž Praznik, 2011, original scientific article

Abstract: Ground-penetrating radar (GPR) has been applied to determine the subsurface karstic features during the construction of the national highway in the south-eastern part of Slovenia. The highway construction is situated mostly in the dinaric karstic region with a high density of karstic features visible on the surface. Ground-penetrating radar prospecting was done in all areas where a slope was cut into the limestone bedrock. The main purpose of the survey was to map potentially hazardous zones in the highway subsurface and to detect and characterize the karst. The ground-penetrating radar method was used because of the heterogeneous nature of the karst. With its high degree of karsticifaction and geological diversity all conventional methods failed. One of GPR’s main advantages is that, while the penetration depth is limited to several meters, the obtained resolution can be on the scale of centimeters and the measured profile is continuous. Because of the ground-penetrating radar’s limitations with respect to depth, the range surveying was done simultaneously with the road construction using 200-MHz bistatic antenna on the level of the highway plane. All the 2D radargrams were constructed in 3D models where the measurements were made in raster with 2 meters between a single GPR profile. This two-meters spacing was determined as the optimal value in which only a minimal resolution-price tradeoff was made. The gathered results were tested and compared to experimental drillings and excavations so that any anomalies and reflections were calibrated. The drilling was conducted twice, first to calibrate the radargram reflections and secondly to check and confirm the calibration success. Altogether, over 30 boreholes were drilled at various previously selected locations. The data obtained from the drilling proved to be very helpful with the calibration since anomalies found during the drilling were almost exclusively (over 95%) a result of the propagation of radar waves from the limestone to an air void or from the limestone to a clay pocket. Drilling test boreholes proved to be a very useful tool for the calibration of the GPR anomalies recorded in 2D radargrams. Such a process showed a near 100 % accuracy with respect to interpreting the subsurface features, with 77% correctly interpreted as caves or clay pockets and 23% wrongly interpreted, where the interpretation was a void but it was indeed partly a clay-filled and partly an air-filled void. The completed survey also showed simultaneous surveying with GPR and road construction is a very efficient and economical way to predict various karstic features and the density of the karstic forms.
Keywords: karst, ground-penetrating radar, geotechnics, cavities, detection
Published in DKUM: 13.06.2018; Views: 1314; Downloads: 106
.pdf Full text (756,55 KB)
This document has many files! More...

Search done in 0.07 sec.
Back to top
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica