Three-dimensional morphological analysis of Chang'e-5 lunar soil using deep learning-automated segmentation on computed tomography scans

Zhou, S, Jiang, Y, Tao, X, Li, F, Zhang, C, Yang, W and Gao, Y ORCID: 0000-0001-7310-1476 (2026) Three-dimensional morphological analysis of Chang'e-5 lunar soil using deep learning-automated segmentation on computed tomography scans. Computer Aided Civil and Infrastructure Engineering, 40 (28). pp. 5076-5092. ISSN 1093-9687

Preview

Text Three dimensional morphological analysis of Chang e5 lunar soil using deep learning automated segmentation on computed tomography scans.pdf - Published Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (7MB) | Preview

Abstract

Grain morphology is a fundamental characteristic of lunar soil that influences its mechanical properties, sintering behavior, and in situ resource utilization. However, traditional two-dimensional imaging methods are time-consuming and lack full three-dimensional (3D) structural information. This study presents an automated deep learning-based segmentation and reconstruction algorithm for high-resolution X-ray computed tomography scans of Chang'e-5 lunar soil samples. By integrating a U-Net convolutional neural network with a watershed algorithm, this method enables efficient and accurate 3D reconstruction of 553,578 lunar soil particles, significantly reducing manual annotation time. The results reveal a median particle size of 63.73 µm, an average aspect ratio of 0.55, and an average sphericity of 0.87, providing key insights into lunar regolith morphology. A clustering analysis identified 30 representative particle types, whose STereoLithography models will be made publicly available for further research and numerical simulations. These findings offer crucial data for discrete element modeling, thermal analysis, and engineering applications, supporting future lunar exploration and the development of sustainable lunar infrastructure.

Item Type:	Article
Uncontrolled Keywords:	40 Engineering; 4019 Resources Engineering and Extractive Metallurgy; Bioengineering; Machine Learning and Artificial Intelligence; Biomedical Imaging; Networking and Information Technology R&D (NITRD); 9 Industry, Innovation and Infrastructure; 0905 Civil Engineering; Civil Engineering; 4005 Civil engineering
Subjects:	T Technology > TA Engineering (General). Civil engineering (General)
Divisions:	Engineering and Built Environment
Publisher:	Elsevier
Date of acceptance:	1 April 2025
Date of first compliant Open Access:	1 September 2026
Date Deposited:	01 Sep 2026 14:09
Last Modified:	01 Sep 2026 14:09
DOI or ID number:	10.1111/mice.13487
URI:	https://researchonline.ljmu.ac.uk/id/eprint/29263

View Item