A dataset of Earth Observation Data for Lithological Mapping using Machine Learning
- 1IIT/ NCSR Demokritos , Greece
- 2School of Rural, Surveying and Geo-Informatics Engineering/ NTUA, Greece
Machine Learning (ML) algorithms had successfully contributed in the creation of automated methods of recognizing patterns in high-dimensional data. Remote sensing data covers wide geographical areas and could be used to solve the problem of the demand of various in-situ data. Lithologicall mapping using remotely sensed data is one of the most challenging applications of ML algorithms. In the framework of the “AI for Geoapplications” project , ML and especially Deep Learning (DL) methodologies are investigated for the identification and characterization of the lithology based on remote sensing data in various pilot areas in Greece. In order to train and test the various ML algorithms, a dataset consisting of 30 ROIs selected mainly from low -vegetated areas, that cover 2% of the total area of Greece was created . For each ROI
- the corresponding shape file with the lithological units
- the corresponding Sentinel2 (10 bands) and/or Aster (14 bands) images
are provided
The dataset is being publicly available in the cloud along with the necessary code for visualization and processing.
How to cite: Vernikos, I., Giannopoulos, G., Christopoulou, A., Begaj, A., Stefouli, M., Bratsolis, E., and Charou, E.: A dataset of Earth Observation Data for Lithological Mapping using Machine Learning, EGU General Assembly 2023, Vienna, Austria, 24–28 Apr 2023, EGU23-17570, https://doi.org/10.5194/egusphere-egu23-17570, 2023.
