Interpretable Dual-Channel Convolutional Neural Networks for Lithology Identification Based on Multisource Remote Sensing Data

Lithology identification provides a crucial foundation for various geological tasks, such as mineral exploration and geological mapping. Traditionally, lithology identification requires geologists to interpret geological data collected from the field. However, the acquisition of geological data requ...

Full description

Saved in:
Bibliographic Details
Main Authors: Sijian Wu, Yue Liu
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/7/1314
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850212924594847744
author Sijian Wu
Yue Liu
author_facet Sijian Wu
Yue Liu
author_sort Sijian Wu
collection DOAJ
description Lithology identification provides a crucial foundation for various geological tasks, such as mineral exploration and geological mapping. Traditionally, lithology identification requires geologists to interpret geological data collected from the field. However, the acquisition of geological data requires a substantial amount of time and becomes more challenging under harsh natural conditions. The development of remote sensing technology has effectively mitigated the limitations of traditional lithology identification. In this study, an interpretable dual-channel convolutional neural network (DC-CNN) with the Shapley additive explanations (SHAP) interpretability method is proposed for lithology identification; this approach combines the spectral and spatial features of the remote sensing data. The model adopts a parallel dual-channel structure to extract spectral and spatial features simultaneously, thus implementing lithology identification in remote sensing images. A case study from the Tuolugou mining area of East Kunlun (China) demonstrates the performance of the DC-CNN model in lithology identification on the basis of GF5B hyperspectral data and Landsat-8 multispectral data. The results show that the overall accuracy (OA) of the DC-CNN model is 93.51%, with an average accuracy (AA) of 89.77% and a kappa coefficient of 0.8988; these metrics exceed those of the traditional machine learning models (i.e., Random Forest and CNN), demonstrating its efficacy and potential utility in geological surveys. SHAP, as an interpretable method, was subsequently used to visualize the value and tendency of feature contribution. By utilizing SHAP feature-importance bar charts and SHAP force plots, the significance and direction of each feature’s contribution can be understood, which highlights the necessity and advantage of the new features introduced in the dataset.
format Article
id doaj-art-51c6d8fef63043e9acbdcc78e4abda81
institution OA Journals
issn 2072-4292
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-51c6d8fef63043e9acbdcc78e4abda812025-08-20T02:09:14ZengMDPI AGRemote Sensing2072-42922025-04-01177131410.3390/rs17071314Interpretable Dual-Channel Convolutional Neural Networks for Lithology Identification Based on Multisource Remote Sensing DataSijian Wu0Yue Liu1State Key Laboratory of Geological Process and Mineral Resources, Faculty of Earth Resources, China University of Geosciences, Wuhan 430074, ChinaState Key Laboratory of Geological Process and Mineral Resources, Faculty of Earth Resources, China University of Geosciences, Wuhan 430074, ChinaLithology identification provides a crucial foundation for various geological tasks, such as mineral exploration and geological mapping. Traditionally, lithology identification requires geologists to interpret geological data collected from the field. However, the acquisition of geological data requires a substantial amount of time and becomes more challenging under harsh natural conditions. The development of remote sensing technology has effectively mitigated the limitations of traditional lithology identification. In this study, an interpretable dual-channel convolutional neural network (DC-CNN) with the Shapley additive explanations (SHAP) interpretability method is proposed for lithology identification; this approach combines the spectral and spatial features of the remote sensing data. The model adopts a parallel dual-channel structure to extract spectral and spatial features simultaneously, thus implementing lithology identification in remote sensing images. A case study from the Tuolugou mining area of East Kunlun (China) demonstrates the performance of the DC-CNN model in lithology identification on the basis of GF5B hyperspectral data and Landsat-8 multispectral data. The results show that the overall accuracy (OA) of the DC-CNN model is 93.51%, with an average accuracy (AA) of 89.77% and a kappa coefficient of 0.8988; these metrics exceed those of the traditional machine learning models (i.e., Random Forest and CNN), demonstrating its efficacy and potential utility in geological surveys. SHAP, as an interpretable method, was subsequently used to visualize the value and tendency of feature contribution. By utilizing SHAP feature-importance bar charts and SHAP force plots, the significance and direction of each feature’s contribution can be understood, which highlights the necessity and advantage of the new features introduced in the dataset.https://www.mdpi.com/2072-4292/17/7/1314lithology identificationremote sensingconvolutional neural networksSHAP explanationinterpretable deep learning
spellingShingle Sijian Wu
Yue Liu
Interpretable Dual-Channel Convolutional Neural Networks for Lithology Identification Based on Multisource Remote Sensing Data
Remote Sensing
lithology identification
remote sensing
convolutional neural networks
SHAP explanation
interpretable deep learning
title Interpretable Dual-Channel Convolutional Neural Networks for Lithology Identification Based on Multisource Remote Sensing Data
title_full Interpretable Dual-Channel Convolutional Neural Networks for Lithology Identification Based on Multisource Remote Sensing Data
title_fullStr Interpretable Dual-Channel Convolutional Neural Networks for Lithology Identification Based on Multisource Remote Sensing Data
title_full_unstemmed Interpretable Dual-Channel Convolutional Neural Networks for Lithology Identification Based on Multisource Remote Sensing Data
title_short Interpretable Dual-Channel Convolutional Neural Networks for Lithology Identification Based on Multisource Remote Sensing Data
title_sort interpretable dual channel convolutional neural networks for lithology identification based on multisource remote sensing data
topic lithology identification
remote sensing
convolutional neural networks
SHAP explanation
interpretable deep learning
url https://www.mdpi.com/2072-4292/17/7/1314
work_keys_str_mv AT sijianwu interpretabledualchannelconvolutionalneuralnetworksforlithologyidentificationbasedonmultisourceremotesensingdata
AT yueliu interpretabledualchannelconvolutionalneuralnetworksforlithologyidentificationbasedonmultisourceremotesensingdata