Lithological Mapping Based on Fully Convolutional Network and Multi-Source Geological Data
Deep learning algorithms have found numerous applications in the field of geological mapping to assist in mineral exploration and benefit from capabilities such as high-dimensional feature learning and processing through multi-layer networks. However, there are two challenges associated with identif...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/23/4860 |
| _version_ | 1797507307084447744 |
|---|---|
| author | Ziye Wang Renguang Zuo Hao Liu |
| author_facet | Ziye Wang Renguang Zuo Hao Liu |
| author_sort | Ziye Wang |
| collection | DOAJ |
| description | Deep learning algorithms have found numerous applications in the field of geological mapping to assist in mineral exploration and benefit from capabilities such as high-dimensional feature learning and processing through multi-layer networks. However, there are two challenges associated with identifying geological features using deep learning methods. On the one hand, a single type of data resource cannot diagnose the characteristics of all geological units; on the other hand, deep learning models are commonly designed to output a certain class for the whole input rather than segmenting it into several parts, which is necessary for geological mapping tasks. To address such concerns, a framework that comprises a multi-source data fusion technology and a fully convolutional network (FCN) model is proposed in this study, aiming to improve the classification accuracy for geological mapping. Furthermore, multi-source data fusion technology is first applied to integrate geochemical, geophysical, and remote sensing data for comprehensive analysis. A semantic segmentation-based FCN model is then constructed to determine the lithological units per pixel by exploring the relationships among multi-source data. The FCN is trained end-to-end and performs dense pixel-wise prediction with an arbitrary input size, which is ideal for targeting geological features such as lithological units. The framework is finally proven by a comparative study in discriminating seven lithological units in the Cuonadong dome, Tibet, China. A total classification accuracy of 0.96 and a high mean intersection over union value of 0.9 were achieved, indicating that the proposed model would be an innovative alternative to traditional machine learning algorithms for geological feature mapping. |
| first_indexed | 2024-03-10T04:46:41Z |
| format | Article |
| id | doaj.art-ad67fe73aa6a4b7bbb04d9477349c929 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T04:46:41Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-ad67fe73aa6a4b7bbb04d9477349c9292023-11-23T02:57:28ZengMDPI AGRemote Sensing2072-42922021-11-011323486010.3390/rs13234860Lithological Mapping Based on Fully Convolutional Network and Multi-Source Geological DataZiye Wang0Renguang Zuo1Hao Liu2State Key Laboratory of Geological Processes and Mineral Resources, China University of Geosciences, Wuhan 430074, ChinaState Key Laboratory of Geological Processes and Mineral Resources, China University of Geosciences, Wuhan 430074, ChinaState Key Laboratory of Geological Processes and Mineral Resources, China University of Geosciences, Wuhan 430074, ChinaDeep learning algorithms have found numerous applications in the field of geological mapping to assist in mineral exploration and benefit from capabilities such as high-dimensional feature learning and processing through multi-layer networks. However, there are two challenges associated with identifying geological features using deep learning methods. On the one hand, a single type of data resource cannot diagnose the characteristics of all geological units; on the other hand, deep learning models are commonly designed to output a certain class for the whole input rather than segmenting it into several parts, which is necessary for geological mapping tasks. To address such concerns, a framework that comprises a multi-source data fusion technology and a fully convolutional network (FCN) model is proposed in this study, aiming to improve the classification accuracy for geological mapping. Furthermore, multi-source data fusion technology is first applied to integrate geochemical, geophysical, and remote sensing data for comprehensive analysis. A semantic segmentation-based FCN model is then constructed to determine the lithological units per pixel by exploring the relationships among multi-source data. The FCN is trained end-to-end and performs dense pixel-wise prediction with an arbitrary input size, which is ideal for targeting geological features such as lithological units. The framework is finally proven by a comparative study in discriminating seven lithological units in the Cuonadong dome, Tibet, China. A total classification accuracy of 0.96 and a high mean intersection over union value of 0.9 were achieved, indicating that the proposed model would be an innovative alternative to traditional machine learning algorithms for geological feature mapping.https://www.mdpi.com/2072-4292/13/23/4860lithological mappingmulti-source data fusiondeep learningfully convolutional network |
| spellingShingle | Ziye Wang Renguang Zuo Hao Liu Lithological Mapping Based on Fully Convolutional Network and Multi-Source Geological Data Remote Sensing lithological mapping multi-source data fusion deep learning fully convolutional network |
| title | Lithological Mapping Based on Fully Convolutional Network and Multi-Source Geological Data |
| title_full | Lithological Mapping Based on Fully Convolutional Network and Multi-Source Geological Data |
| title_fullStr | Lithological Mapping Based on Fully Convolutional Network and Multi-Source Geological Data |
| title_full_unstemmed | Lithological Mapping Based on Fully Convolutional Network and Multi-Source Geological Data |
| title_short | Lithological Mapping Based on Fully Convolutional Network and Multi-Source Geological Data |
| title_sort | lithological mapping based on fully convolutional network and multi source geological data |
| topic | lithological mapping multi-source data fusion deep learning fully convolutional network |
| url | https://www.mdpi.com/2072-4292/13/23/4860 |
| work_keys_str_mv | AT ziyewang lithologicalmappingbasedonfullyconvolutionalnetworkandmultisourcegeologicaldata AT renguangzuo lithologicalmappingbasedonfullyconvolutionalnetworkandmultisourcegeologicaldata AT haoliu lithologicalmappingbasedonfullyconvolutionalnetworkandmultisourcegeologicaldata |