This paper systematically reviews remote sensing technology and learning algorithms in exploring landslides. The work is categorized into four key components: (1) literature search characteristics, (2) geographical distribution and research publication trends, (3) progress of remote sensing and learning algorithms, and (4) application of remote sensing techniques and learning models for landslide susceptibility mapping, detections, prediction, inventory and deformation monitoring, assessment, and extraction and management. The literature selections were based on keyword searches using title/abstract and keywords from Web of Science and Scopus. A total of 186 research articles published between 2011 and 2024 were critically reviewed to provide answers to research questions related to the recent advances in the use of remote sensing technologies combined with artificial intelligence (AI), machine learning (ML), and deep learning (DL) algorithms. The review revealed that these methods have high efficiency in landslide detection, prediction, monitoring, and hazard mapping. A few current issues were also identified and discussed.

The strength, deformation and particle breakage behaviors of reinforced coral sand were analyzed by performing a series of large-scale consolidated drained triaxial tests on unreinforced and two-layer geogrid reinforced samples. Two grain size distributions, namely, the natural coral sand in the South China Sea (ISG) and the uniformly graded coral sand (UG), were used to investigate the effect of gradation on unreinforced and geogrid-reinforced specimens under dry and saturated conditions. The results indicated that the inclusion of geogrid offered a great improvement to the coral sand with respect to increasing its shear strength and reducing the shear dilation. The reinforcement effect of geogrid on dry sample was better than that on saturated one. Moreover, the UG sample exhibits high compressibility and distinct strain hardening behavior due to the significant particle breakage resulting from the lack of fine content compared with the ISG sample, which induced the better reinforcement effect of geogrid on ISG sample. The increase of particle breakage further led to the decrease of peak-state friction angle.

This paper presents an analysis of the soil arching effect associated with piled embankments under cyclic loading by developing a series of two-dimensional trapdoor discrete numerical models. After identification of the microparameters by a biaxial compression test, the numerical models were validated by comparing the numerical model and plane laboratory test results. The contact force characteristics, deformation behaviors, and porosity distributions under various embankment heights were analyzed. The numerical results showed that cyclic loading leads to the degradation of soil arching as characterized by the collapse of load transmission paths and their vertical distribution. The variability observed in the contact fabric further confirmed that degradation in the higher embankment mainly occurred in the upper layers. Increasing embankment height decelerated the increasing contact force of the portion above the trapdoor and thus retarded the process of degradation. The load-induced time-dependent surface settlement accumulated with increasing cycle numbers and varied with embankment height. With an increasing number of cycles, the deformation area in the lower embankment cases above the trapdoor shifted from a triangular pattern to a rectangular pattern, while the higher embankment still maintained a triangular pattern. Furthermore, the effects of the localized loading area, stationary support width, and trapdoor displacement on soil arching concerning the loading efficiency and surface settlement were evaluated.