Spoil characterisation using UAV-based optical remote sensing in coal mine dumps

Abstract

The structural integrity of mine dumps is crucial for mining operations to avoid adverse impacts on the triple bottom-line. Routine temporal assessments of coal mine dumps are a compliant requirement to ensure design reconciliation as spoil offloading continues over time. Generally, the conventional in-situ coal spoil characterisation is inefficient, laborious, hazardous, and prone to experts' observation biases. To this end, this study explores a novel approach to develop automated coal spoil characterisation using unmanned aerial vehicle (UAV) based optical remote sensing. The textural and spectral properties of the high-resolution UAV images were utilised to derive lithology and geotechnical parameters (i.e., fabric structure and relative density/consistency) in the proposed workflow. The raw images were converted to an orthomosaic using structure from motion aided processing. Then, structural descriptors were computed per pixel to enhance feature modalities of the spoil materials. Finally, machine learning algorithms were employed with ground truth from experts as training and testing data to characterise spoil rapidly with minimal human intervention. The characterisation accuracies achieved from the proposed approach manifest a digital solution to address the limitations in the conventional characterisation approach.

Open-Pit Granite Mining Area Extraction Using UAV Aerial Images and the Novel GIPNet

“…They proposed a new complex environmental interpretation system for locating targets in noisy backgrounds and eliminating the influence of terrain undulations, used to search for useful minerals. Thiruchittampalam et al [21] used UAV remote sensing technology to characterize coal mine waste, extracting texture and spectral features from real-time on-site data, and employing machine learning algorithms combined with expert experience for waste classification. Kou et al [22] used high-resolution images obtained by UAVs to identify acidic mine drainage in coal mining areas, comparing three methods-SVM, Random Forest (RF), and UNet-and proposing an efficient and economical monitoring approach.…”

Multi-Stage and Multi-Parameter Influence Analysis of Deep Foundation Pit Excavation on Surrounding Environment

“…In deep foundation pit excavation, geotechnical parameters are usually obtained via on-site testing (such as standard penetration test and cone penetration test), indoor testing (such as direct shear test and triaxial compression test), geological exploration (including borehole sampling and core testing), and geophysical exploration (such as seismic wave and resistivity measurement). In addition, remote sensing technology offers an alternative, enabling the real-time extraction and inference of surface-level rock and soil properties [35,36]. This approach facilitates the gathering of crucial geotechnical data even in challenging or inaccessible environments.…”

Forecasting residual mechanical properties of hybrid fibre-reinforced self-compacting concrete (HFR-SCC) exposed to elevated temperatures

“…are already common in the field of civil engineering. These techniques and several other algorithms are frequently being utilized to estimate different properties of concrete composites, soil compaction parameters, slope failure susceptibility etc [ [28] , [29] , [30] , [31] , [32] , [33] , [34] , [35] , [36] , [37] , [38] , [39] , [40] ]. This research is attributed to utilization of a special ML algorithm called GEP to predict residual cs and fs of SCC containing a mix of steel, polypropylene and PVA fibres.…”