Yazarlar
Yayınlar
- MakaleAçık Erişim2025Supervised classification-based framework for rock mass discontinuity identification using point cloud data
Günen, Mehmet Akif; Öztürk, Kaşif Furkan; Aliyazıcıoğlu, Şener
Mapping and evaluating rock mass discontinuities using point clouds is a critical task in mining, civil, and geological engineering. Rock discontinuities can significantly impact the integrity, strength, and stability of rock masses. The orientation of these discontinuities is also a key characteristic of the rock mass. Accurate orientation estimation from point clouds enables more precise predictions of rock mass behavior, leading to improved safety, more efficient excavation processes, reduced operational costs, and significant time savings. In this context, a supervised classification-based framework is proposed for calculating orientation parameters from point cloud. Supervised classification plays a crucial role in tasks where a model learns complex patterns from labeled data to accurately predict previously unseen instances. The proposed method consists of eight-steps, including: data collection, pre-processing (data filtering), adaptive neighborhood size selection (omnivariance-based), feature extraction (geometric features), feature selection (Minimum Redundancy Maximum Relevance method), classification (Support Vector Machine), clustering (connected component labeling), and plane fitting to calculate orientation parameters (dip angle and dip direction). The framework was applied to two real-world datasets and one synthetic dataset, which was tested in two different subsampled forms (random and uniform subsampling). The results statistically demonstrated that the technique was effective in detecting and characterizing rock mass discontinuities with high Accuracy, Recall, Precision, and F-Score values ranging from 94.64% to 99.57%. The deviations of the method in the measurements of the dip angle and the dip direction, compared to the manual measurements, range from 1% to 4%, indicating strong agreement with the manual measurements and the existing studies.
- MakaleYayıncıda açık erişim2025Explainable artificial intelligence for rock discontinuity detection from point cloud with ensemble methods
Günen, Mehmet Akif
This study presents a framework for the semi-automatic detection of rock discontinuities using a three-dimensional (3D) point cloud (PC). The process begins by selecting an appropriate neighborhood size, a critical step for feature extraction from the PC. The effects of different neighborhood sizes (k = 5, 10, 20, 50, and 100) have been evaluated to assess their impact on classification performance. After that, 17 geometric and spatial features were extracted from the PC. Next, ensemble methods, AdaBoost.M2, random forest, and decision tree, have been compared with Artificial Neural Networks to classify the main discontinuity sets. The McNemar test indicates that the classifiers are statistically significant. The random forest classifier consistently achieves the highest performance with an accuracy exceeding 95% when using a neighborhood size of k = 100, while recall, F-score, and Cohen's Kappa also demonstrate high success. SHapley Additive exPlanations (SHAP), an Explainable AI technique, has been used to evaluate feature importance and improve the explainability of black-box machine learning models in the context of rock discontinuity classification. The analysis reveals that features such as normal vectors, verticality, and Z-values have the greatest influence on identifying main discontinuity sets, while linearity, planarity, and eigenvalues contribute less, making the model more transparent and easier to understand. After classification, individual discontinuity sets were detected using a revised DBSCAN from the main discontinuity sets. Finally, the orientation parameters of the plane fitted to each discontinuity were derived from the plane parameters obtained using the Random Sample Consensus (RANSAC). Two real-world datasets (obtained from SfM and LiDAR) and one synthetic dataset were used to validate the proposed method, which successfully identified rock discontinuities and their orientation parameters (dip angle/direction).