Datasets
Standard Dataset
gpr forward modeling dataset
- Citation Author(s):
- Submitted by:
- Tianjia Xu
- Last updated:
- Mon, 10/30/2023 - 11:42
- DOI:
- 10.21227/wsrh-cj62
- License:
52 Views- Categories:
- Keywords:
Abstract
Our dataset consists of a pretraining dataset and a fine-tuning dataset. The pretraining dataset is generated using the FDTD method. We simulated a scenario for underground pipeline detection, where the transmitter (tx) is located above the ground, and the receiver (rx) is approximately 30 cm away from the transmitter. The target pipeline buried underground has depths ranging from 1 to 3 meters and a length of approximately 10 meters. The simulation area is discretized into both time and space grids, with a time step of 0.1 nanoseconds and a spatial step of 0.1 meters to ensure accurate electromagnetic wave modeling. The transmission frequency is set at 400 MHz to simulate common underground pipeline detection applications. With this model, we can generate simulated data for researching pipeline detection and localization methods, and we can adjust simulation parameters as needed to meet different research scenarios. In total, 10,000 dielectric constant samples and 20,000 pairs of data were generated.
Our dataset consists of a pretraining dataset and a fine-tuning dataset. The pretraining dataset is generated using the FDTD method. We simulated a scenario for underground pipeline detection, where the transmitter (tx) is located above the ground, and the receiver (rx) is approximately 30 cm away from the transmitter. The target pipeline buried underground has depths ranging from 1 to 3 meters and a length of approximately 10 meters. The simulation area is discretized into both time and space grids, with a time step of 0.1 nanoseconds and a spatial step of 0.1 meters to ensure accurate electromagnetic wave modeling. The transmission frequency is set at 400 MHz to simulate common underground pipeline detection applications. With this model, we can generate simulated data for researching pipeline detection and localization methods, and we can adjust simulation parameters as needed to meet different research scenarios. In total, 10,000 dielectric constant samples and 20,000 pairs of data were generated.
