Regional Lithological Mapping Using ASTER-TIR Data: Preliminary Case Study for the Tibetan Plateau and the Surrounding Area

This study presents the combined use of field mapping, remote sensing data analysis, mineralogy, spectroscopy and GIS techniques for the geological mapping of Antiparos Island. Antiparos is part of the Cyclades Blueschist Belt located in central Aegean, where gneisses, schists and Pliocene volcanic rocks occurred. During the extended field work, a number of volcanic rock samples were collected from the southern part of Antiparos. The sampling strategy was to collect samples from the primary as well as the altered rocks in specific areas in which they were previously located from the remote sensing data processing. In this study, high resolution satellite images have been carried out in order to detect, allocate and separate the different geological formations. Furthermore, the existing geological map was georeferenced and all the tectonic lines and boundaries were digitized. All these features were implemented in a Mobile Mapper CE GPS using Arcpad GIS and checked in situ. The collected samples were analyzed in the laboratory using various techniques including XRD, Petrographic Microscopy and SEM. The qualitative mineralogical analyses were conducted by using XRD. The study was supplemented by the petrographic observations providing a detailed characterization of rock textures. In addition, SEM study and SEM-EDS analyses of the samples were emphasized on the genetic relations of the minerals. The laboratory results revealed that specific corrections should be made in the previous geological map of Antiparos concerning the volcanic rocks, especially at the southern part of the island. A significant conclusion is that the rock described as volcanic in the previous map proved to be a fossiliferous limestone which includes micritic matrix of calcite with an insignificant amount of fossils. All the analogical and digital data and the results of the petrographic analysis were imported in a geodatabase specially designed for geological data. After the necessary topological control and corrections, the data were unified and processed in order to create the final layout at 1/25.000 scale.

show abstract

Machine Learning-Based Lithological Mapping from ASTER Remote-Sensing Imagery

Bahrami,

Esmaeili,

Homayouni

et al. 2024

Minerals

View full text Add to dashboard Cite

Accurately mapping lithological features is essential for geological surveys and the exploration of mineral resources. Remote-sensing images have been widely used to extract information about mineralized alteration zones due to their cost-effectiveness and potential for being widely applied. Automated methods, such as machine-learning algorithms, for lithological mapping using satellite imagery have also received attention. This study aims to map lithologies and minerals indirectly through machine-learning algorithms using advanced spaceborne thermal emission and reflection radiometer (ASTER) remote-sensing data. The capabilities of several machine-learning (ML) algorithms were evaluated for lithological mapping, including random forest (RF), support vector machine (SVM), gradient boosting (GB), extreme gradient boosting (XGB), and a deep-learning artificial neural network (ANN). These methods were applied to ASTER imagery of the Sar-Cheshmeh copper mining region of Kerman Province, in southern Iran. First, several spectral features that were extracted from ASTER bands were used as input data. Second, correlation coefficients between the original spectral bands and features were extracted. The importance of the random forest features (RF’s feature importance) was subsequently computed, and features with less importance were removed. Finally, the remained features were given to the models as input data in the second scenario. Accuracy assessments were performed for lithological classes in the study region, including Sar-Cheshmeh porphyry, quartz eye, late fine porphyry, hornblende dike, granodiorite, feldspar dike, biotite dike, andesite, and alluvium. The overall accuracy results of lithological mapping showed that ML-based algorithms without feature extraction have the highest accuracy. The overall accuracy percentages for ML-based algorithms without conducting feature extraction were 84%, 85%, 80%, 82%, and 80% for RF, SVM, GB, XGB, and ANN, respectively. The results of this study would be of great interest to geologists for lithological mapping and mineral exploration, particularly for selecting appropriate ML-based techniques to be implemented in similar regions.

show abstract

Regional Lithological Mapping Using ASTER-TIR Data: Preliminary Case Study for the Tibetan Plateau and the Surrounding Area

Cited by 13 publications

References 40 publications

Desertification monitoring using the ASTER global emissivity dataset

Desertification monitoring using the ASTER global emissivity dataset

Combined Use of Remote Sensing Data, Mineralogical Analyses, Microstructure Studies and Geographic Information System for Geological Mapping of Antiparos Island (Greece)

Machine Learning-Based Lithological Mapping from ASTER Remote-Sensing Imagery

Contact Info

Product

Resources

About