SPARTACUS: Sampling Precision and Rate Transformation Algorithm for Continuous Uniform Sampling of an Underground Imaging Antenna

• Main Authors: Enriquez, Mike Louie, Ducut, Jullian Dominic, Baun, Jonah Jahara, De leon, Joseph Aristotle, Concepcion, Ronnie, Relano, R-Jay, Francisco, Kate, Vicerra, Ryan Rhay, Bandala, Argel, Dungca, Jonathan, Co, Homer, Dadios, Elmer
• Format: Conference Proceeding
• Language: English
• Subjects: electrical resistivity tomography; gaussian process regression; Gaussian processes; Measurement; Nyquist rate; Prediction algorithms; regression optimization; Regression tree analysis; Resistance; Roads; Support vector machines
• ISSN: 2770-0682
• DOI: 10.1109/HNICEM60674.2023.10589014

In locating subsurface utilities, one known method is a surveying system towed by trailers employing electrical resistivity tomography (ERT). However, the primary issue with subsurface surveying with a towing mechanism is the change in speed caused by unavoidable obstructions and sloping road surfaces since it affects the sampling logging of the system. With that, this study develops a novel technique for fast exploration of extensive transects using optimized receiver sampling rate as a function of velocity, current, power, slope angle, and voltage, Furthermore, regression models such as regression tree (RTree), gaussian process regression (GPR), support vector machine (SVM), and ensemble regression (ER) were used for model optimization. The prediction model demonstrating superior performance will be designated as the algorithm for continuous uniform sampling, known as the Sampling Precision and Rate Transformation Algorithm for Continuous Uniform Sampling (SPARTACUS). In modeling, the GPR outperforms the RTree, SVM, and ER based on the values of the RSME, SME, MAE, and R2 which were utilized as evaluation metrics in this study. Then, the MSE values of the different models of GPR such as the rational quadratic (RQ), square exponential (SE), Matern 5/2, exponential, and optimized Gaussian process regression, were identified with 1.938e-10, 1.735e-10, 1.663e-10, 3.785e-6, and 3.254e-10 respectively. With this, the Matern 5/2 regression model was considered as SPARTACUS. Additional evaluation metrics, including the Mean Absolute Error (MAE) and R2, were utilized, underscoring the distinct advantages offered by SPARTACUS. To verify the efficiency of SPARTACUS, Matplot in MATLAB was utilized and enabled the optimization of the sampling rate and normalization of the resistivity map.