In this paper, we provide a comprehensive survey of existing hybrid physics-based ML methods for TSE problem. This survey leads us to uncover inherent challenges and gaps in the current state of research. The results have profound implications for evaluating the applicability of hybrid physics-based ML TSE methods and identifying future research directions.In this paper, a critical review is conducted to understand the current research status of the quantification technology for obtaining three-dimensional (3D) point cloud information of rock mass and extracting structural key information, which is a major challenge and problem facing rock engineering. The timely and accurate acquisition of rock mass data and fine characterization of rock mass parameters can avoid unnecessary personnel injury and property damage. Firstly, the methods of point cloud information acquisition and structural information extraction are systematically summarized and classified. Then, various existing methods are analysed for their advantages and disadvantages. Based on this analysis, the future development direction of relevant technologies is proposed to improve the level of acquisition of 3D information of rock mass and the level of extraction of key information of rock mass. The results indicate that rock mass point cloud information acquisition technology can be classified into two types: laser point cloud acquisition and image reconstruction based on Structure from Motion (SfM) algorithm. Rock mass structural information can be classified into rock mass structural planes and their attitudes, rock mass traces and their geometric parameters, and other rock mass parameters, including structural plane roughness, spacing, and block characteristics, etc. Different acquisition technologies and feature extraction methods have their own advantages, disadvantages, and applicable ranges. Therefore, a comprehensive selection of various evaluation methods should be made based on specific engineering characteristics and existing data situations in practice.
- Rock mass characteristics
