SCIENCE@home

MC-H-Geo: A Multi-Scale Contextual Hierarchical Framework for Fine-Grained Lithology Classification

Lang Liu,Yanlin Shao,Yaxiong Shao,Peijin Li,Qingqing Yang,R. Zeng

Published 2025 in Italian National Conference on Sensors

ABSTRACT

Highlights This study develops MC-H-Geo, a multi-scale contextual hierarchical framework for fine-grained lithological classification of TLS outcrop point clouds. The framework integrates voxel-based anchor point construction, a multi-scale feature engine with cross-scale differentials, a gated expert classifier with task-adaptive feature subsets, and a two-step geological post-processing strategy. The method is validated on the Qianwangjiahe outcrop dataset, achieving state-of-the-art performance and highlighting the physical limits and pointing to multi-sensor solutions. What are the main findings? MC-H-Geo significantly improves fine-grained classification accuracy (OA = 94.3%, Macro F1 = 0.944), outperforming PointNet++, SG-RFGeo, and XGBoost. Error analysis demonstrates that misclassification of weathered sandstone as vegetation is caused by feature aliasing, marking a fundamental limitation of TLS-derived attributes. What is the implication of the main finding? The framework offers a transferable solution for high-resolution digital outcrop modeling in fine-grained successions. Overcoming TLS-only feature aliasing requires multi-sensor data fusion (RGB, hyperspectral) and advanced deep learning architectures, pointing to the next frontier in automated geological mapping. Abstract High-resolution lithological mapping of outcrops is fundamental for reservoir characterization and petroleum geology, yet distinguishing lithologies with subtle petrophysical contrasts remains a major challenge. This study proposes MC-H-Geo, a multi-scale contextual hierarchical framework for automated lithology classification from terrestrial laser scanning (TLS) point clouds. The framework integrates three modules: (i) a multi-scale contextual feature engine that extracts spectral, geometric, and textural descriptors across local and stratigraphic contexts, enhanced by cross-scale differentials to capture stratigraphic variability; (ii) a gated expert classifier with task-adaptive feature subsets for hierarchical vegetation–rock and intra-rock discrimination; and (iii) a two-step geological post-processing procedure that enforces stratigraphic continuity through Z-axis correction and neighborhood smoothing. Experiments on the Qianwangjiahe outcrop (Ordos Basin, China) demonstrate state-of-the-art performance (OA = 94.3%, Macro F1 = 0.944), outperforming PointNet++ (77.1%), SG-RFGeo (74.2%), and XGBoost (61.7%). Error analysis reveals that residual sandstone–vegetation confusion results from feature aliasing in weathered zones, highlighting the intrinsic limitations of TLS-only data. Overall, MC-H-Geo establishes an advanced framework for fine-grained lithological mapping and identifies multi-sensor data fusion as a promising pathway toward robust, geologically consistent outcrop interpretation.

PUBLICATION RECORD

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-32 of 32 references · Page 1 of 1

CITED BY