Cross-Hole GPR for Soil Moisture Estimation Using Deep Learning

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.

3D Reverse-Time Migration Imaging for Multiple Cross-Hole Research and Multiple Sensor Settings of Cross-Hole Seismic Exploration

“…Surface seismic methods are suitable for near-surface conditions; however, they face challenges in transmitting sufficient energy through the weathered zone to desired depths due to the strong attenuation of seismic waves in unsaturated, unconsolidated sediments [1][2][3]. The cross-hole seismic imaging method has gained wide utilization in geotechnical engineering parameter calculation [4], tunnel and cavity detection [5][6][7], hydrogeology surveys [8][9][10], rock and aquifer distribution detection [11][12][13], reservoir descriptions [14][15][16], rock fragmentation descriptions [17], civil engineering [18], detection of hydrocarbon reservoirs [19][20][21] and so on. Despite this, this method also has deficiencies; for example, when cross-hole seismic receivers are arranged near the target body, the wavefield in profile between two wells is greatly influenced due to the medium inhomogeneity (especially the high-velocity target) in 3D space, leading to image distortion [22].…”

Transient Electromagnetic Monitoring of Permafrost: Mathematical Modeling Based on Sumudu Integral Transform and Artificial Neural Networks

“…Currently, the most ubiquitous approach towards permafrost monitoring is borehole temperature time-lapse surveys [35][36][37]. Next in abundance are geoelectric prospecting techniques, including their cross-borehole modifications and 3D data inversion: electrical resistivity tomography [38][39][40][41] and ground penetrating radar [42][43][44]. There exist experimental works that simulate resistivity monitoring of the active permafrost layer in laboratory conditions [45].…”

An Application of 3D Cross-Well Elastic Reverse Time Migration Imaging Based on the Multi-Wave and Multi-Component Technique in Coastal Engineering Exploration

“…Cross-well seismic can be applied to various aspects of oil and gas exploration, including detailed imaging of structures and precise characterization of reservoirs [10][11][12]. Furthermore, cross-well seismic has also been rapidly developed in the field of engineering [13,14] and has been applied in diverse areas, such as geological engineering [15][16][17], hydrogeological surveys [18][19][20], and quality inspections in civil engineering projects [21][22][23]. Currently, most cross-well seismic studies focus on two-dimensional (2D) tomographic imaging between adjacent wells [24,25].…”