A Machine Learning-Based Method for Lithology Identification of Outcrops Using TLS-Derived Spectral and Geometric Features

Lithological identification of outcrops in complex geological settings plays a crucial role in hydrocarbon exploration and geological modeling. To address the limitations of traditional field surveys, such as low efficiency and high risk, we proposed an intelligent lithology recognition method, SG-R...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanlin Shao, Peijin Li, Ran Jing, Yaxiong Shao, Lang Liu, Kunpeng Zhao, Binqing Gan, Xiaolei Duan, Longfan Li
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/14/2434
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850071566671413248
author Yanlin Shao
Peijin Li
Ran Jing
Yaxiong Shao
Lang Liu
Kunpeng Zhao
Binqing Gan
Xiaolei Duan
Longfan Li
author_facet Yanlin Shao
Peijin Li
Ran Jing
Yaxiong Shao
Lang Liu
Kunpeng Zhao
Binqing Gan
Xiaolei Duan
Longfan Li
author_sort Yanlin Shao
collection DOAJ
description Lithological identification of outcrops in complex geological settings plays a crucial role in hydrocarbon exploration and geological modeling. To address the limitations of traditional field surveys, such as low efficiency and high risk, we proposed an intelligent lithology recognition method, SG-RFGeo, for terrestrial laser scanning (TLS) outcrop point clouds, which integrates spectral and geometric features. The workflow involves several key steps. First, lithological recognition units are created through regular grid segmentation. From these units, spectral reflectance statistics (e.g., mean, standard deviation, kurtosis, and other related metrics), and geometric morphological features (e.g., surface variation rate, curvature, planarity, among others) are extracted. Next, a double-layer random forest model is employed for lithology identification. In the shallow layer, the Gini index is used to select relevant features for a coarse classification of vegetation, conglomerate, and mud–sandstone. The deep-layer module applies an optimized feature set to further classify thinly interbedded sandstone and mudstone. Geological prior knowledge, such as stratigraphic attitudes, is incorporated to spatially constrain and post-process the classification results, enhancing their geological plausibility. The method was tested on a TLS dataset from the Yueyawan outcrop of the Qingshuihe Formation, located on the southern margin of the Junggar Basin in China. Results demonstrate that the integration of spectral and geometric features significantly improves classification performance, with the Macro F1-score increasing from 0.65 (with single-feature input) to 0.82. Further, post-processing with stratigraphic constraints boosts the overall classification accuracy to 93%, outperforming SVM (59.2%), XGBoost (67.8%), and PointNet (75.3%). These findings demonstrate that integrating multi-source features and geological prior constraints effectively addresses the challenges of lithological identification in complex outcrops, providing a novel approach for high-precision geological modeling and exploration.
format Article
id doaj-art-36b367488ddc4f6eb8b12cc1e02ea998
institution DOAJ
issn 2072-4292
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-36b367488ddc4f6eb8b12cc1e02ea9982025-08-20T02:47:17ZengMDPI AGRemote Sensing2072-42922025-07-011714243410.3390/rs17142434A Machine Learning-Based Method for Lithology Identification of Outcrops Using TLS-Derived Spectral and Geometric FeaturesYanlin Shao0Peijin Li1Ran Jing2Yaxiong Shao3Lang Liu4Kunpeng Zhao5Binqing Gan6Xiaolei Duan7Longfan Li8School of Geosciences, Yangtze University, Wuhan 430100, ChinaSchool of Geosciences, Yangtze University, Wuhan 430100, ChinaSchool of Geosciences, Yangtze University, Wuhan 430100, ChinaCenter for Governmental Studies, Northern Illinois University, DeKalb, IL 60115, USASchool of Geosciences, Yangtze University, Wuhan 430100, ChinaSchool of Geosciences, Yangtze University, Wuhan 430100, ChinaSchool of Geosciences, Yangtze University, Wuhan 430100, ChinaSchool of Geosciences, Yangtze University, Wuhan 430100, ChinaSchool of Geosciences, Yangtze University, Wuhan 430100, ChinaLithological identification of outcrops in complex geological settings plays a crucial role in hydrocarbon exploration and geological modeling. To address the limitations of traditional field surveys, such as low efficiency and high risk, we proposed an intelligent lithology recognition method, SG-RFGeo, for terrestrial laser scanning (TLS) outcrop point clouds, which integrates spectral and geometric features. The workflow involves several key steps. First, lithological recognition units are created through regular grid segmentation. From these units, spectral reflectance statistics (e.g., mean, standard deviation, kurtosis, and other related metrics), and geometric morphological features (e.g., surface variation rate, curvature, planarity, among others) are extracted. Next, a double-layer random forest model is employed for lithology identification. In the shallow layer, the Gini index is used to select relevant features for a coarse classification of vegetation, conglomerate, and mud–sandstone. The deep-layer module applies an optimized feature set to further classify thinly interbedded sandstone and mudstone. Geological prior knowledge, such as stratigraphic attitudes, is incorporated to spatially constrain and post-process the classification results, enhancing their geological plausibility. The method was tested on a TLS dataset from the Yueyawan outcrop of the Qingshuihe Formation, located on the southern margin of the Junggar Basin in China. Results demonstrate that the integration of spectral and geometric features significantly improves classification performance, with the Macro F1-score increasing from 0.65 (with single-feature input) to 0.82. Further, post-processing with stratigraphic constraints boosts the overall classification accuracy to 93%, outperforming SVM (59.2%), XGBoost (67.8%), and PointNet (75.3%). These findings demonstrate that integrating multi-source features and geological prior constraints effectively addresses the challenges of lithological identification in complex outcrops, providing a novel approach for high-precision geological modeling and exploration.https://www.mdpi.com/2072-4292/17/14/2434outcrop lithology identificationpoint cloud analysisspectral–geometric feature fusionrandom forest classificationstratigraphic constraints
spellingShingle Yanlin Shao
Peijin Li
Ran Jing
Yaxiong Shao
Lang Liu
Kunpeng Zhao
Binqing Gan
Xiaolei Duan
Longfan Li
A Machine Learning-Based Method for Lithology Identification of Outcrops Using TLS-Derived Spectral and Geometric Features
Remote Sensing
outcrop lithology identification
point cloud analysis
spectral–geometric feature fusion
random forest classification
stratigraphic constraints
title A Machine Learning-Based Method for Lithology Identification of Outcrops Using TLS-Derived Spectral and Geometric Features
title_full A Machine Learning-Based Method for Lithology Identification of Outcrops Using TLS-Derived Spectral and Geometric Features
title_fullStr A Machine Learning-Based Method for Lithology Identification of Outcrops Using TLS-Derived Spectral and Geometric Features
title_full_unstemmed A Machine Learning-Based Method for Lithology Identification of Outcrops Using TLS-Derived Spectral and Geometric Features
title_short A Machine Learning-Based Method for Lithology Identification of Outcrops Using TLS-Derived Spectral and Geometric Features
title_sort machine learning based method for lithology identification of outcrops using tls derived spectral and geometric features
topic outcrop lithology identification
point cloud analysis
spectral–geometric feature fusion
random forest classification
stratigraphic constraints
url https://www.mdpi.com/2072-4292/17/14/2434
work_keys_str_mv AT yanlinshao amachinelearningbasedmethodforlithologyidentificationofoutcropsusingtlsderivedspectralandgeometricfeatures
AT peijinli amachinelearningbasedmethodforlithologyidentificationofoutcropsusingtlsderivedspectralandgeometricfeatures
AT ranjing amachinelearningbasedmethodforlithologyidentificationofoutcropsusingtlsderivedspectralandgeometricfeatures
AT yaxiongshao amachinelearningbasedmethodforlithologyidentificationofoutcropsusingtlsderivedspectralandgeometricfeatures
AT langliu amachinelearningbasedmethodforlithologyidentificationofoutcropsusingtlsderivedspectralandgeometricfeatures
AT kunpengzhao amachinelearningbasedmethodforlithologyidentificationofoutcropsusingtlsderivedspectralandgeometricfeatures
AT binqinggan amachinelearningbasedmethodforlithologyidentificationofoutcropsusingtlsderivedspectralandgeometricfeatures
AT xiaoleiduan amachinelearningbasedmethodforlithologyidentificationofoutcropsusingtlsderivedspectralandgeometricfeatures
AT longfanli amachinelearningbasedmethodforlithologyidentificationofoutcropsusingtlsderivedspectralandgeometricfeatures
AT yanlinshao machinelearningbasedmethodforlithologyidentificationofoutcropsusingtlsderivedspectralandgeometricfeatures
AT peijinli machinelearningbasedmethodforlithologyidentificationofoutcropsusingtlsderivedspectralandgeometricfeatures
AT ranjing machinelearningbasedmethodforlithologyidentificationofoutcropsusingtlsderivedspectralandgeometricfeatures
AT yaxiongshao machinelearningbasedmethodforlithologyidentificationofoutcropsusingtlsderivedspectralandgeometricfeatures
AT langliu machinelearningbasedmethodforlithologyidentificationofoutcropsusingtlsderivedspectralandgeometricfeatures
AT kunpengzhao machinelearningbasedmethodforlithologyidentificationofoutcropsusingtlsderivedspectralandgeometricfeatures
AT binqinggan machinelearningbasedmethodforlithologyidentificationofoutcropsusingtlsderivedspectralandgeometricfeatures
AT xiaoleiduan machinelearningbasedmethodforlithologyidentificationofoutcropsusingtlsderivedspectralandgeometricfeatures
AT longfanli machinelearningbasedmethodforlithologyidentificationofoutcropsusingtlsderivedspectralandgeometricfeatures