As mine open pits become increasingly aggressive and deep (beyond 400 m) due to exhaustion of near-surface resources or implausibility of underground excavation, significant challenges emerge using standard slope stability analysis techniques. Typically during overall failure analysis, factor of safety calculations are conducted. Although quite useful and despite recent advances in characterizing insitu stresses, the factor of safety approach has its inadequacies. For example, single factor of safety values cannot characterize an entire pit sector under varying geotechnical and environmental conditions. In this paper we draw on lessons learned from large dataset techniques in engineering geology to assess landslides. The proposed approach utilizes the emerging field of deep learning using artificial neural networks. Deep learning uses data-driven tools to continually update algorithms used to conduct computations resulting in high levels of accuracy and precision. Using our results and relevant examples from the literature, we discuss the benefits and shortcoming of the proposed approach, the appropriate conditions and types of environments for application and suggested modifications and improvements.
Introduction and Background
Rock mass slope stability analysis is one of the most important undertakings during the design of surface mine open pit slopes. Typically select cross section profiles from a three dimensional geological model are created and assigned material and geotechnical properties for analytical calculations of factors of safety. In two dimensional limit equilibrium analysis using one of the methods of slices, the factor of safety is expressed as a ratio of the sum of the resistive forces to that of the destabilizing forces. A factor of safety less than 1.0 is indicative of unstable conditions, while a value greater than 1.0 represents stable conditions. For surface mine slopes, both interramp and overall slope stability analyses are undertaken under both static and pseudostatic conditions. The interramp angles are defined by bench face angles, bench heights and bench widths (Figure 1). The overall slope angle is defined by interramp sections separated by wide step-outs for haulage roads or mine infrastructure. In general, except for slopes of high failure consequence, a design factor of safety of 1.2 is adopted (Read and Stacey, 2009). Slopes of high failure consequence are those slopes that are critical to mine operations, such as hosting major haul roads, those providing ingress or egress points to the pit, or those underlying essential infrastructure. Those slopes identified as having high failure consequences tend to have relatively higher factors of safety up to 1.5 (Read and Stacey, 2009). In addition, certain adverse geologic environments do not favor high interramp angles due to rock fall and bench overbreak, and hence design angles tend to be flattened to provide wide catch benches. The Mine Safety and Health Administration (MSHA), Title 30 of the Code of Federal Regulations, Section 56.3130 requirements for open pit slopes demand that adequate benches must be in place to retain rockfall above work or travel areas.