Catastrophic failure in engineering structures of island reefs would occur when the tertiary creep initiates in coral reef limestone with a transition from short-to long-term load. Due to the complexity of biological structures, the underlying micro-behaviors involving time-dependent deformation are poorly understood. For this, an abnormal phenomenon was observed where the axial and lateral creep deformations were mutually independent by a series of triaxial tests under constant stress and strain rate conditions. The significantly large lateral creep deformation implies that the creep process cannot be described in continuum mechanics regime. Herein, it is hypothesized that sliding mechanism of crystal cleavages dominates the lateral creep deformation in coral reef limestone. Then, approaches of polarizing microscope (PM) and scanning electronic microscope (SEM) are utilized to validate the hypothesis. It shows that the sliding behavior of crystal cleavages combats with conventional creep micro-mechanisms at certain condition. The former is sensitive to time and strain rate, and is merely activated in the creep regime. (c) 2025 Institute of Rock and Soil Mechanics, Chinese Academy of Sciences. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/ 4.0/).

Different sedimentary zones in coral reefs lead to significant anisotropy in the pore structure of coral reef limestone (CRL), making it difficult to study mechanical behaviors. With X-ray computed tomography (CT), 112 CRL samples were utilized for training the support vector machine (SVM)-, random forest (RF)-, and back propagation neural network (BPNN)-based models, respectively. Simultaneously, the machine learning model was embedded into genetic algorithm (GA) for parameter optimization to effectively predict uniaxial compressive strength (UCS) of CRL. Results indicate that the BPNN model with five hidden layers presents the best training effect in the data set of CRL. The SVM-based model shows a tendency to overfitting in the training set and poor generalization ability in the testing set.The RF-based model is suitable for training CRL samples with large data. Analysis of Pearson correlation coefficient matrix and the percentage increment method of performance metrics shows that the dry density, pore structure, and porosity of CRL are strongly correlated to UCS. However, the P-wave velocity is almost uncorrelated to the UCS, which is significantly distinct from the law for homogenous geomaterials. In addition, the pore tensor proposed in this paper can effectively reflect the pore structure of coral framework limestone (CFL) and coral boulder limestone (CBL), realizing the quantitative characterization of the heterogeneity and anisotropy of pore. The pore tensor provides a feasible idea to establish the relationship between pore structure and mechanical behavior of CRL. (c) 2024 Institute of Rock and Soil Mechanics, Chinese Academy of Sciences. Production and hosting by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/ licenses/by-nc-nd/4.0/).