Woodward, K, McFadyen, B & Tremblay, K 2024, 'Integrating a new approach at the Westwood mine site for predicting the stope mined geometry', in P Andrieux & D Cumming-Potvin (eds), Deep Mining 2024: Proceedings of the 10th International Conference on Deep and High Stress Mining, pp. 1335-1348, https://doi.org/10.36487/ACG_repo/2465_88
(https://papers.acg.uwa.edu.au/p/2465_88_McFadyen/)
Abstract: Open stoping has become a popular mining method in hard rock mines, not only due to the safety of the method as a non-entry approach, but also because of the high extraction rate and low costs. At mine sites, stope performance is evaluated by calculating stope overbreak using the Stability Chart. The limitations of the Stability Chart regarding the precision of the predictions, non-consideration of factors such as the influence of blasting, and the exclusion of underbreak have led to suboptimal designs. The modern capabilities of computers have resulted in large amounts of data being collected and despite subsequent statistical models being more capable, they have been underutilised in the stope design process. 
To increase the information and knowledge that is extracted from the data and to progress from the simple qualitative per stope face prediction that is provided by a traditional Stability Chart approach, the Australian Centre for Geomechanics has developed a design approach that can account for many of the variables that influence stope performance and uses multivariate modelling methods to forecast the expected stope geometry. This approach is implemented as a stope reconciliation and design application and is integrated in mXrap software that allow users to import their stope design as well as their blasting design and predict the expected mined geometry for stope planification and optimisation. 
This paper presents a case study of how the stope reconciliation and design application has been integrated at Westwood mine to understand and predict stope performance. An overview of the approach, the analysis of past stope performance and the generation of future predictions is presented along with the utility of this approach for optimising stope performance.

Keywords: open stope, octree, machine learning, performance optimisation, dilution, overbreak, underbreak