Fusion of Geochemical and Remote-Sensing Data for Lithological Mapping Using Random Forest Metric Learning
- PDF / 10,484,635 Bytes
- 21 Pages / 439.37 x 666.142 pts Page_size
- 22 Downloads / 197 Views
Fusion of Geochemical and Remote-Sensing Data for Lithological Mapping Using Random Forest Metric Learning Ziye Wang1 · Renguang Zuo1 · Linhai Jing2
Received: 28 March 2020 / Accepted: 22 September 2020 © International Association for Mathematical Geosciences 2020
Abstract Multisource geoscience data can provide significant information for mineral exploration in a variety of ways. For example, remote-sensing images record the spectral characteristics of objects, and geochemical data represent the enrichment or depletion of geochemical elements, which reflect the physical and chemical attributes of geological features. In this study, a hybrid model comprising data fusion and machine learning was applied for lithological mapping. This process is illustrated through a case study of mapping several lithological units in the Cuonadong Dome, in the northeastern part of the Himalayas, China. In this process, multisource data fusion technology is first used to provide more abundant information by integrating geochemical data and Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) remote-sensing images, retaining both the geochemical patterns and the textural structure of the remote-sensing images. Then, a random forest metric learning (RFML) approach is employed to achieve a high classification performance based on the fused data. RFML adopts metric learning in the classification process of each decision tree calculation, making full use of the advantages of random forest and metric learning. Seven target lithological units were discriminated with 93.0% overall accuracy. This excellent performance demonstrates the effectiveness of the hybrid method in the geological exploration of areas in poor environments that have undergone limited geological research.
B
Renguang Zuo [email protected]
1
State Key Laboratory of Geological Processes and Mineral Resources, China University of Geosciences, Wuhan 430074, China
2
Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
123
Math Geosci
Keywords Lithological mapping · Date fusion · Metric learning · Random forest · Mineral exploration
1 Introduction Formed from the collision of the Indian and Asian subcontinents, the Himalayan orogenic belt occupies an important part of the Tethys structural domain, where abundant mineral resources have been developed (Yin 2006). As a type of intrusive rock that is widely distributed in the Himalayan orogenic belt, Himalayan leucogranite has attracted growing attention owing to its excellent metallogenic potential for rare metals (e.g., Be, Nb, Ta, Sn, W, U, and Li) (Li et al. 2017; Liu et al. 2019; Wu et al. 2020). Such a finding implies the importance of mapping the distribution of Himalayan leucogranite for further exploration of rare polymetallic mineral resources in the Himalayan region. Multisource geoscience data (e.g., from geology, geochemistry, geophysics, and remote sensing) provide various types of information for mineral ex
Data Loading...
