Coal Exploration Based on a Multilayer Extreme Learning Machine and Satellite Images

• Main Authors: Ba Tuan Le, Dong Xiao, Yachun Mao, Dakuo He, Shengyong Zhang, Xiaoyu Sun, Xiaobo Liu
• Format: Article
• Language: English
• Published: IEEE 2018-01-01
• Series: IEEE Access
• Subjects: Neural networks; remote sensing; satellites; sensors
• Online Access: https://ieeexplore.ieee.org/document/8421221/

The demand for coal has been on the rise in modern society. With the number of opencast coal mines decreasing, it has become increasingly difficult to find coal. Low efficiencies and high casualty rates have always been problems in the process of coal exploration due to complicated geological structures in coal mining areas. Therefore, we propose a new exploration technology for coal that uses satellite images to explore and monitor opencast coal mining areas. First, we collected bituminous coal and lignite from the Shenhua opencast coal mine in China in addition to non-coal objects, including sandstones, soils, shales, marls, vegetation, coal gangues, water, and buildings. Second, we measured the spectral data of these objects through a spectrometer. Third, we proposed a multilayer extreme learning machine algorithm and constructed a coal classification model based on that algorithm and the spectral data. The model can assist in the classification of bituminous coal, lignite, and non-coal objects. Fourth, we collected Landsat 8 satellite images for the coal mining areas. We divided the image of the coal mine using the constructed model and correctly described the distributions of bituminous coal and lignite. Compared with the traditional coal exploration method, our method manifested an unparalleled advantage and application value in terms of its economy, speed, and accuracy.