ASTER VNIR‐SWIR Based Lithological Mapping of Granitoids in the Western Junggar Orogen (NW Xinjiang): Improved Inputs to Random Forest Method
Abstract Although advanced spaceborne thermal emission and reflection radiometer multispectral analysis for lithological mapping has been widely applied, traditional methods such as band ratios (BR) and principal component analysis (PCA) are still hampered by cumbersome data processing and poor clas...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
American Geophysical Union (AGU)
2023-08-01
|
| Series: | Earth and Space Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2023EA002877 |
| _version_ | 1797658101456830464 |
|---|---|
| author | Yarong Zhou Shuo Zheng Yanfei An Chunkit Lai |
| author_facet | Yarong Zhou Shuo Zheng Yanfei An Chunkit Lai |
| author_sort | Yarong Zhou |
| collection | DOAJ |
| description | Abstract Although advanced spaceborne thermal emission and reflection radiometer multispectral analysis for lithological mapping has been widely applied, traditional methods such as band ratios (BR) and principal component analysis (PCA) are still hampered by cumbersome data processing and poor classification performance. In this study, we utilize improved data inputs for random forest (RF) to extract lithological information of granitoids, which are the predominant rock type for intrusion‐related polymetallic ore deposits in the western Junggar Orogen (NW Xinjiang). Based on spectral absorption features of minerals (e.g., orthoclase, K‐feldspar, hornblende, biotite, plagioclase, and oligoclase), image statistical information and textural features, we tested different combinations of bands, BR, PCA, and texture using RF method, and found that the combination of B13678 + T1 (Mean texture) achieved the highest weighted‐F1 score for granitoids, with an accuracy of 87.32%. Compared to the support vector machine, RF effectively distinguishes lithological differences between different types of granitoid and wallrocks, especially the granite, granodiorite, and alkali granite in the Akebasito intrusion, as well as the alkali granite, plagiogranite and biotite granite in the Karamay intrusions. Moreover, the large number of rare metal deposits (including Cu, Au, Mo, etc.) distributed near the granitoid intrusions in the western Junggar, our result facilitates the analysis of regional tectonic evolution and mineralization controlling. |
| first_indexed | 2024-03-11T17:54:03Z |
| format | Article |
| id | doaj.art-58ec28674ae3486e849b52040d826929 |
| institution | Directory Open Access Journal |
| issn | 2333-5084 |
| language | English |
| last_indexed | 2024-03-11T17:54:03Z |
| publishDate | 2023-08-01 |
| publisher | American Geophysical Union (AGU) |
| record_format | Article |
| series | Earth and Space Science |
| spelling | doaj.art-58ec28674ae3486e849b52040d8269292023-10-17T21:16:18ZengAmerican Geophysical Union (AGU)Earth and Space Science2333-50842023-08-01108n/an/a10.1029/2023EA002877ASTER VNIR‐SWIR Based Lithological Mapping of Granitoids in the Western Junggar Orogen (NW Xinjiang): Improved Inputs to Random Forest MethodYarong Zhou0Shuo Zheng1Yanfei An2Chunkit Lai3School of Resources and Environmental Engineering Anhui University Hefei ChinaSchool of Resources and Environmental Engineering Anhui University Hefei ChinaSchool of Resources and Environmental Engineering Anhui University Hefei ChinaGlobal Project Generation and Targeting Fortescue Metals Group Ltd. Perth WA AustraliaAbstract Although advanced spaceborne thermal emission and reflection radiometer multispectral analysis for lithological mapping has been widely applied, traditional methods such as band ratios (BR) and principal component analysis (PCA) are still hampered by cumbersome data processing and poor classification performance. In this study, we utilize improved data inputs for random forest (RF) to extract lithological information of granitoids, which are the predominant rock type for intrusion‐related polymetallic ore deposits in the western Junggar Orogen (NW Xinjiang). Based on spectral absorption features of minerals (e.g., orthoclase, K‐feldspar, hornblende, biotite, plagioclase, and oligoclase), image statistical information and textural features, we tested different combinations of bands, BR, PCA, and texture using RF method, and found that the combination of B13678 + T1 (Mean texture) achieved the highest weighted‐F1 score for granitoids, with an accuracy of 87.32%. Compared to the support vector machine, RF effectively distinguishes lithological differences between different types of granitoid and wallrocks, especially the granite, granodiorite, and alkali granite in the Akebasito intrusion, as well as the alkali granite, plagiogranite and biotite granite in the Karamay intrusions. Moreover, the large number of rare metal deposits (including Cu, Au, Mo, etc.) distributed near the granitoid intrusions in the western Junggar, our result facilitates the analysis of regional tectonic evolution and mineralization controlling.https://doi.org/10.1029/2023EA002877lithological mappingband combinationmean texturerandom forestgranitoids |
| spellingShingle | Yarong Zhou Shuo Zheng Yanfei An Chunkit Lai ASTER VNIR‐SWIR Based Lithological Mapping of Granitoids in the Western Junggar Orogen (NW Xinjiang): Improved Inputs to Random Forest Method Earth and Space Science lithological mapping band combination mean texture random forest granitoids |
| title | ASTER VNIR‐SWIR Based Lithological Mapping of Granitoids in the Western Junggar Orogen (NW Xinjiang): Improved Inputs to Random Forest Method |
| title_full | ASTER VNIR‐SWIR Based Lithological Mapping of Granitoids in the Western Junggar Orogen (NW Xinjiang): Improved Inputs to Random Forest Method |
| title_fullStr | ASTER VNIR‐SWIR Based Lithological Mapping of Granitoids in the Western Junggar Orogen (NW Xinjiang): Improved Inputs to Random Forest Method |
| title_full_unstemmed | ASTER VNIR‐SWIR Based Lithological Mapping of Granitoids in the Western Junggar Orogen (NW Xinjiang): Improved Inputs to Random Forest Method |
| title_short | ASTER VNIR‐SWIR Based Lithological Mapping of Granitoids in the Western Junggar Orogen (NW Xinjiang): Improved Inputs to Random Forest Method |
| title_sort | aster vnir swir based lithological mapping of granitoids in the western junggar orogen nw xinjiang improved inputs to random forest method |
| topic | lithological mapping band combination mean texture random forest granitoids |
| url | https://doi.org/10.1029/2023EA002877 |
| work_keys_str_mv | AT yarongzhou astervnirswirbasedlithologicalmappingofgranitoidsinthewesternjunggarorogennwxinjiangimprovedinputstorandomforestmethod AT shuozheng astervnirswirbasedlithologicalmappingofgranitoidsinthewesternjunggarorogennwxinjiangimprovedinputstorandomforestmethod AT yanfeian astervnirswirbasedlithologicalmappingofgranitoidsinthewesternjunggarorogennwxinjiangimprovedinputstorandomforestmethod AT chunkitlai astervnirswirbasedlithologicalmappingofgranitoidsinthewesternjunggarorogennwxinjiangimprovedinputstorandomforestmethod |