Geotechnical characterisation of coal spoil piles using high-resolution optical and multispectral data: A machine learning approach

• DOI: 10.1016/j.enggeo.2024.107406
• Publication Date: 2024-01-06T16:23:38Z
• Authors: Sureka Thiruchitt...; Bikram Pratap Ban...; Nancy F. Glenn; Simit Raval
• Keywords: Relevance; Coal field; Feature (linguistics)

Geotechnical characterisation of spoil piles has traditionally relied on the expertise field specialists, which can be both hazardous and time-consuming. Although unmanned aerial vehicles (UAV) show promise as a remote sensing tool in various applications; accurately segmenting classifying very high-resolution images heterogeneous terrains, such mining with irregular morphologies, presents significant challenges. The proposed method adopts robust approach that combines morphology-based segmentation, well spectral, textural, structural, statistical feature extraction techniques to overcome difficulties associated pile characterisation. Additionally, it incorporates minimum redundancy maximum relevance (mRMR) based selection machine learning-based classification. This automated will serve proactive for dump stability assessment, providing crucial data improved models contributing greener more responsible industry .