Search

The small-strain and electromagnetic behaviors of soils significantly change due to compression. The objective of this study was to investigate the small-strain stiffness and electrical resistivity of diatomaceous sand by modifying the conventional setup of oedometer tests (1D-compression tests). The specimens used were pure sand and sand with 20% diatoms by weight. The vertical displacement was directly observed using a digital gauge at the top of the compression cap during compression. At the end of each loading step, shear waves (S-waves) are measured using a pair of bender elements installed on the top and bottom compression caps. In addition, electrical resistance was measured using a pair of electrodes installed horizontally in the middle of the compression cylinder. The test results show that the compression index increased but the swelling index decreased according with the increase in the amount of the small and crushable diatom particles. The presence of diatom particles weakened the interparticle contacts and softened the soil skeletons. In addition, the electrical resistivity increased with the increase in diatom contents, which increased the surface conduction. Our work suggests that the S-wave velocity and electrical resistivity of diatomaceous sand can be characterized by modifying the conventional oedometer tests.

This study aims to classify seafloor sediments using physics‐inspired and data‐driven soil models combined with machine learning algorithms and oversampling techniques. The field data used for the input variables include porosity, S‐ and P‐wave velocities and depth. The soil information reported in the original literature and the "six reference sediments" and effective stress‐versus‐depth models proposed by the previous study confirm the sediment type across all of the input variables. We use three machine learning algorithms and four oversampling methods to enhance the performance accuracy and overcome data imbalance in the minority class. The results show that the averaged accuracy of sediment classification with original data corresponds to 0.88 for porosity, 0.61 for S‐wave velocity, and 0.97 for P‐wave velocity. In particular, the enhanced accuracy with oversampled input variables becomes more pronounced when the depth data are considered in a dataset. The class‐oriented grouping method newly proposed in this study appears to be a robust approach to enhancing performance. Surprisingly, model‐based input variables lead to the best performance in all cases. The proposed analyses conducted using machine learning algorithms and oversampling techniques within the physics‐inspired models could be extended to obtain a first‐order assessment of marine sediment properties. [ABSTRACT FROM AUTHOR]