The real-time accurate description of all spatial features of railway and their spatiotemporal relationships is a crucial factor in realizing comprehensive management and related decision-making within the entire life cycle of railways. Nevertheless, available spatiotemporal data models mainly use static historical sequence data, which are insufficient to support multi-source heterogeneous real-time sensed data; they lack a systematic depiction of the interactive relationships among multiple feature entities, and are limited to low-level descriptive analysis. Therefore, this study proposes a data-model-knowledge integrated representation data model for a digital twin railway, which explicitly describes the spatiotemporal, and interaction relationships among railway features through a conceptual knowledge graph. This study first analyzes the characteristics of railway features from above ground to underground, and then constructs a conceptual model to clearly describe the complex relationships among railway features. Secondly, a logical model is developed to illustrate the basic data structure. Thirdly, an ontology model is constructed as a basic framework for further deepening the domain knowledge graph. Finally, considering the prevention of landslides as an example, it demonstrates the abundant spatiotemporal relationships among railway related features. The results of this study bring more clear understanding of the complex interactive relationships of railway entities.

Recent studies have introduced transformer modules into convolutional neural networks (CNNs) to solve the inherent limitations of CNNs in global modeling and have achieved impressive performance. However, some challenges have yet to be addressed: first, networks with simple connections between the CNN and transformer perform poorly in small change areas; second, networks that only use transformer structures are prone to attaining coarse detection results and excessively generalizing feature boundaries. In addition, the methods of fusing the CNN and transformer have the issue of a unilateral flow of feature information and inter-scale communication, leading to a loss of change information across different scales. To mitigate these problems, this study proposes a full-scale connected CNN–Transformer network, which incorporates the Siamese structure, Unet3+, and transformer structure, used for change detection in remote sensing images, namely SUT. A progressive attention module (PAM) is adopted in SUT to deeply integrate the features extracted from both the CNN and the transformer, resulting in improved global modeling, small target detection capacities, and clearer feature boundaries. Furthermore, SUT adopts a full-scale skip connection to realize multi-directional information flow from the encoder to decoder, enhancing the ability to extract multi-scale features. Experimental results demonstrate that the method we designed performs best on the CDD, LEVIR-CD, and WHU-CD datasets with its concise structure. In particular, based on the WHU-CD dataset, SUT upgrades the F1-score by more than 4% and the intersection over union (IOU) by more than 7% compared with the second-best method.

Reliable assessment of landslide susceptibility in broad areas of terrain remains challenging due to complex topography and poor representation of randomly selected negative samples. Assessment in broad areas is now primarily based on grid units, which do not have a clear physical meaning like slope units, and their accuracy is not ideal. Nevertheless, the large amount of manual editing, due to the incorrectly generated horizontal and vertical lines during slope unit partitioning, limits using slope units for rapid assessment over large areas. Hence, this paper proposes a reliable susceptibility assessment approach to solve this problem based on optimal slope units and negative samples involving prior knowledge. Precisely, an algorithm to automatically extract slope units is designed to eliminate fragmented and erroneous units. Second, a samples labeling index (SLI) is defined based on the certainty factors model to select negative samples reasonably. Sichuan Province, China is selected for experimental analysis, with the results demonstrate that the optimized slope unit and the negative samples selection strategy consider prior knowledge achieve better results in the random forest model, support vector machine model, and artificial neural network model. In particular, the composite performance index AUC of artificial neural network model improved from 0.81 to 0.90.

It is essential to establish a digital twin scene, which helps to depict the dynamically changing geographical environment accurately. Digital twins could improve the refined management level of intelligent tunnel construction; however, research on geographical twin models primarily focuses on modeling and visual description, which has low analysis efficiency. This paper proposes a knowledge-guided intelligent analysis method for the geometric deformation of tunnel excavation profile twins. Firstly, a dynamic data-driven knowledge graph of tunnel excavation twin scenes was constructed to describe tunnel excavation profile twin scenes accurately. Secondly, an intelligent diagnosis algorithm for geometric deformation of tunnel excavation contour twins was designed by knowledge guidance. Thirdly, multiple visual variables were jointly used to support scene fusion visualization of tunnel excavation profile twin scenes. Finally, a case was selected to implement the experimental analysis. The experimental results demonstrate that the method in this article can achieve an accurate description of objects and their relationships in tunnel excavation twin scenes, which supports rapid geometric deformation analysis of the tunnel excavation profile twin. The speed of geometric deformation diagnosis is increased by more than 90% and the cognitive efficiency is improved by 70%. The complexity and difficulty of the deformation analysis operation are reduced, and the diagnostic analysis ability and standardization of the geographic digital twin model are effectively improved.

The absence of detailed façade elements in photogrammetric building mesh models falls short for complex applications. These models often present irregular surfaces, significant geometric noise, and subpar texture quality, complicating façade parsing. To mitigate these challenges, we introduce StructuredMesh, an innovative approach to augment façade details while adhering to architectural regularity. Our method captures multiview color and depth images with a virtual camera and implements an object detection pipeline to semiautomatically delineate façade elements—such as windows, doors, and balconies—from color images. These elements are mapped into 3-D space using depth information, forming a preliminary façade layout. By harnessing architectural intelligence, we engage binary integer programming (BIP) for 3-D layout optimization, targeting component positions, orientations, and sizes. The resulting refined layout underpins the façade reconstruction of the mesh model through instance replacement. Our method’s efficacy was confirmed on three distinct datasets. Employing the 3-D layout evaluation metrics we proposed, StructuredMesh surpasses conventional methods in numerical precision and regularity enhancement.