The current developments with unmanned aerial vehicles (‘UAVs’) are revolutionizing many fields in civil applications, such as agriculture, environmental and visual inspections. The mining industry can also benefit from UAVs in many aspects, and the reconciliation through topographic control is an example. In comparison with traditional topography and maybe modern techniques such as laser scanning, aerial photogrammetry is cheaper, provides faster data acquisition and processing, and generates several high-quality products and impressive level of details in the outputs. However, despite the quality of the software currently available, there is an uncertainty intrinsic to the surfaces acquired by photogrammetry and this discrepancy needs to be assessed in order to validate the techniques applied. To understand the uncertainty, different surfaces were generated by UAVs for a small open pit quarry in southern Brazil. Well-established topographic surveying methodologies were used for geolocation support and comparison, namely the RTK (real-time kinetic) global navigation satellite system (GNSS) (here called conventional method) and laser scanning. The results showed consistency between the UAV surfaces with a few outliers in when vegetation, water and mobile objects during the flight missions. In comparison with the laser-scanned surface, the UAV results were less erratic surrounding the RTK points, showing that surfaces generated by photogrammetry can be a simpler and quicker alternative for mining reconciliation, presenting low uncertainty when compared to conventional methods.

Mine planning is directly dependent on the lithological features and the definition of contacts between materials. Geological modelling is a continual duty that is performed using observation data, which includes open faces information. New data must be continuously acquired and more details are added to the model. This task can benefit from the automation of lithological detection. Unmanned aerial vehicles (UAVs) are widely used in open pit mining projects, with low risk to the operators, to the aircraft or third parties. Topographic modelling using UAV imagery is now common in the mining industry. The next step, presented here, is to automate the surface feature detection using machine learning (ML) algorithms to classify a complete detailed geological model. An inexpensive aircraft was used on a Brazilian phosphate mine with point spacing as small as 10 cm.

Geometallurgical models are commonly built by combining explanatory variables to obtain the response that requires prediction. This study presented a phosphate plant with three concentration steps: magnetic separation, desliming and flotation, where the yields and recoveries corresponding to each process unit were predicted. These output variables depended on the ore composition and the collector concentration utilized. This paper proposed a solution based on feature engineering to select the best set of explanatory variables and a subset of them able to keep the model as simple as possible but with enough precision and accuracy. After choosing the input variables, two neural network models were developed to simultaneously forecast the seven geometallurgical variables under study: the first, using the best set of variables; and the second, using the reduced set of inputs. The forecasts obtained in both scenarios were compared, and the results showed that the mean squared error and the root mean squared error increase in all output variables evaluated in the test set was smaller than 2.6% when the reduced set was used. The trade-off between simplicity and the quality of the model needs to be addressed when choosing the final neural network to be used in a 3D-block model.

Geostatistical seismic rock physics amplitude-versus-angle (AVA) inversion allows the joint prediction of rock and fluid properties from seismic reflection data. In these seismic inversion methods, the model perturbation and update occur iteratively in the petrophysical domain. A facies-dependent precalibrated rock physics model is applied to the simulated rock properties to calculate elastic properties. Synthetic seismic reflection data are computed from these elastic models. The rock physics models are calibrated at the well locations and act as the link between the rock and the elastic domains, remaining unchanged during the inversion procedure: the convergence of the inversion and the geological plausibility of the inverted rock property models depend on the quality of the calibration and available well-log data. To overcome this limitation, account for calibration errors and geological scenarios not sampled at the well locations, we introduce an iterative geostatistical seismic AVA inversion where the elastic predictions from a facies-dependent precalibrated rock physics model are updated iteratively, based on the mismatch between observed and synthetic data. We assume an initial $a$ priori uncertainty in the rock physics model and update it iteratively based on the data mismatch. The proposed method is applied in a 1-D synthetic example to illustrate the concept and validate the method. Then, we apply the inversion method to a 3-D real data set. In this application, we use a blind well to assess locally the performance of the technique. The results show that the parameters of space exploration is not compromised by the rock physics model’s uncertainty.

One of the first decisions to be made when building a mineral resource model is the definition of geological/geostatistical domains. Cluster analysis is a set of techniques in machine learning that can be especially suited for this matter. In order to compare different approaches, two clustering algorithms were investigated in this study: k-means and the dual-space clustering algorithm. Choosing the most appropriate method and the number of clusters can be challenging and some metrics are needed to support these decisions, including the validation of the spatial distribution of the clusters, which is not always appropriately discussed in the literature. We introduce the use of correlograms of the indicators for that matter. Although clustering techniques can be robust for an application in resource modelling, expert knowledge is still necessary when applying cluster analysis to resource modeling, since final decisions should not be based solely on statistical indexes, but also on experience. In this paper, the proposed methodology was tested in a three-dimensional dataset related to a phosphate/titanium deposit.