Search Documents

By J. Saunders, N. Pretorius, G. Krafft, T. P. Katakwa

Imagine being able to see all the future planned mining activities in real time. This is exactly what SIMS (Short Interval Management System) will enable you to do. SIMS is a real time short interval control system that continuously measures and sets optimised plans for mining production processes. The system utilises algorithm-based software that takes resources (people, equipment, tasks, and workplaces) and gives you the best achievable plan. The algorithm was developed using methods found in the field of metaheuristics. A metaheuristic is a strategy to designed to efficiently search for optimal or near optimal solutions to problems that are very complex computationally. (Glover, 1986) There are several algorithms that have been developed to solve optimisation problems which are difficult to solve using traditional techniques. This has given rise to a field called evolutionary computing. (Simon, 2013) Examples of these techniques are genetic algorithms, particle swarm optimisation, and ant colony optimisation. These methods are used to solve problems in a variety of fields. As an example, Kok and Lane (2012) used particle swarm optimisation for equipment allocation in a mechanised underground mining environment. The first SIMS deployment took place in a platinum underground tabular mechanised mine near Burgersfort (province?) from 2017-2019. This included the development from a paper-based system to a fully operational online system. SIMS then moved to a second site and is currently being tested in a second platinum underground tabular mechanised mine in South Africa. Full deployment of the system is currently being phased in. SIMS was built in response to issues that have been plaguing the mining industry for years. These issues are all aligned into one major problem statement: how can we optimise mining production processes without compromising safety? This product was developed by combining years of mining experience with software development. SIMS is based on a four-pillar concept. Safety, productivity, accountability, and business improvement. SIMS uses a set of pre-configured mining and production rules, and with the resources that are available, to determine valid short term production plans. A background algorithm then determines the optimum plan to be executed. The system continuously produces a set of job cards that are pushed to respective operators on their allocated tablets. The management portal component allows you to view and manage all current and planned work on any connected device available. This allows real time visibility of completed, current, and planned work to operators, service departments and management, i.e., seeing into the future.

Sep 1, 2021

By R. J. Hundermark, L. R. Nelson

The critical importance of tap-hole design and management to furnace performance and longevity is explored through examining some of the specific matte, metal and slag tapping requirements of non-ferrous copper blister and matte converting and smelting, ferroalloys smelting and ironmaking systems. Process conditions and productivity requirements and their influence on tapping are reviewed for these different pyrometallurgical systems. Some critical aspects of the evolution of tap-hole design to meet the diverging process and tapping duties are examined. Differences and similarities in tapping practices and tap-hole management are reviewed. Finally core aspects of tap-hole equipment and maintenance are identified that are considered important to securing improved tap-hole performance and life, so pivotal to superior furnace smelting performance.

Jan 1, 2014

By E. Lutz, M. Momayez, K. W. Brown Requist

As real-time air quality monitoring becomes more prevalent in US underground mines, it is important to provide the highest data reliability with the fewest possible sensors. Real-time sensors remain costly, and these costs are not exclusively financial; the time required to install, calibrate, and maintain real-time sensors poses a large barrier to widespread implementation. Current atmospheric monitoring systems typically rely on displaying point-specific values. This requires operators to infer real-time airborne contamination distributions. Monitoring and control software utilizing mine ventilation network (MVN) solvers has been implemented in limited cases because of their ability to simulate ventilation systems quickly, but these solvers use a one-dimensional representation of the mine, limiting spatial resolution of estimated distributions. Computational fluid dynamics (CFD) has likewise been considered as a means to improve spatial resolution, but processing times prevent its use as a basis for monitoring and control. For the real-time monitoring of airborne contamination distributions, we propose a spatial interpolation method that can estimate the distribution of airborne contaminants in near-real time. This method provides a middle ground between fast processing times and increased spatial resolution. With the use of a pathfinding algorithm and optimization through absolute percentage error minimization, this method outperforms spatial interpolation with a Euclidean distance. By providing contamination distribution information to operators, this method and its derivatives stand to outperform current atmospheric monitoring systems.

Apr 16, 2024

By R. J. Hundermark, L. R. Nelson

"The critical importance of tap-hole design and management for furnace performance and longevity is explored through examining some of the specific matte, metal, and slag tapping requirements of non-ferrous copper blister and matte converting and smelting, ferroalloy smelting, and ironmaking systems. Process conditions and productivity requirements and their influence on tapping are reviewed for these different pyrometallurgical systems. Some critical aspects of the evolution of tap-hole design to meet the diverging process and tapping duties are examined. Differences and similarities in tapping practices and tap-hole management are reviewed. Finally, core aspects of tap-hole equipment and maintenance are identified – aspects that are considered important for securing improved tap-hole performance and life, so pivotal to superior furnace smelting performance. IntroductionThe sheer diversity of tapping configurations used on industrial pyrometallurgical operations is at first bewildering. They range from historical tilting furnaces without tapholes to modern eccentric bottom tapping (EBT) tilting and/or bottom slide-gate electric arc furnaces; to classical single tap-hole multiphase tapping (e.g. metal/matte and slag); to dedicated phase tap-holes (e.g. dedicated metal/matte-only and slag-only); to dedicated phase multiple tap-hole configurations (up to eight metal/matte-only tap-holes and six slag-only tap-holes); to more esoteric metal/matte-only siphons and slag overflow skimming, e.g. Mitsubishi Continuous Process (Matsutani, n.d.). This can be further complicated by periodic batch tapping; consecutive tapping on a given taphole; alternating tap-hole tapping practice; near-continuous slag-only tapping, with discrete batch matte/metal tapping on higher productivity, but low metal/matte fall (<20% by mass feed) Co and Ni ferroalloy and platinum group metal (PGM) matte furnaces; near-continuous tapping through batch tapping of individual tap-holes that are opened consecutively (Tanzil et al., 2001; Post et al., 2003); to fully continuous tapping on coupled multi-furnace cascades (Matsutani, n.d.)."

Jan 1, 2016

By R. Nyirenda, B. Besa, N. Dzimunya

The accurate estimation of peak particle velocity (PPV) is crucial during the design of bench blasting operations in open pit mines, since the vibrations caused by blasting can significantly affect the integrity of nearby buildings and other structures. Conventional models used to predict blast-induced vibrations are not capable of capturing nonlinear relationships between the different blasting-related parameters. Soft computing techniques, i.e., techniques that are founded on the principles of artificial intelligence, effectively model these complexities. In this paper, we use the random forest (RF) algorithm to develop a model to predict blast-induced ground vibrations from bench blasting using 48 data records. The model was trained and tested using WEKA datamining software. To build this model, a feature selection process using several combinations of Attribute Evaluators and Search Methods under the WEKA Select Attributes tab was performed. The correlation coefficient of the actual data and RF model-predicted data was 0.95, and the weighted average of the relative absolute error (RAE) was 10.9%. The RF model performance was also compared to the equivalent-path-based (EPB) equation on the testing data-set, and it was seen that the RF model can effectively be used to predict PPV. The study also demonstrates that the EPB equation is a suitable empirical method for predicting PPV.

Mar 30, 2023

By A. K. Raji, E. F. Orumwense, M. O. Ojumu

The Fourth Industrial Revolution has driven significant advancements in autonomous robotic systems, particularly in subsea exploration and offshore mineral dredging. This review examines the latest developments in electrically powered quadrotor-track subsea robotic crawlers, highlighting their potential to enhance efficiency, mobility, and adaptability in challenging underwater environments. The integration of advanced automation, artificial intelligence, and real-time control systems has paved the way for more effective robotic solutions in offshore mining. This study explores the dynamic performance of hydraulic crawlers to quadrotortrack robotic dredgers, focusing on their propulsion, navigation, and stability under high hydrodynamic conditions. By leveraging state-of-the-art technologies such as lithium-ion battery power systems, intelligent microprocessors, and sensor-based control mechanisms, these robotic crawlers offer a promising alternative to conventional subsea excavation methods. Furthermore, the review analyses recent experimental and simulation-based studies that assess the feasibility and performance of these systems in real-world applications. The findings of this review provide valuable insights into the role of 4IR in transforming subsea robotics for offshore mineral dredging. By addressing existing limitations and identifying key technological advancements, this study contributes to the ongoing development of nextgeneration robotic systems capable of operating efficiently in extreme underwater conditions

Jan 30, 2026

By T. Chauke, J. M. Maponya, I. P. Dikgwatlhe

Accurate mineral resource estimation is crucial for optimising mining operations, reducing financial risks, and ensuring efficient resource utilisation. Various spatial modelling techniques have been developed to estimate ore grades and geological continuity, among which radial basis function interpolation and sequential Gaussian simulation are widely used. This review paper provides a comparative analysis of these two methods, examining their theoretical foundations, applications, strengths, and limitations in mineral resource estimation. Radial basis function is a deterministic interpolation method that models spatial relationships based on radial distance functions, making it effective for capturing smooth geological trends. Although kriging techniques have historically dominated the mining sector, new developments have brought to light their shortcomings, especially when handling sparse datasets and grade uncertainty. The paper examined case examples that demonstrate the usefulness of radial basis function and sequential Gaussian simulation in estimating mineral resources, with an emphasis on how they can model grade distributions, measure uncertainty, and maximise financial results. There is a substantial study gap dealing with the comparison of both methods; despite their respective advantages, a head-to-head comparison of radial basis function and sequential Gaussian simulation is still not well-studied. Their relative advantages, computational effectiveness, and compatibility with other geostatistical methods should all be assessed in future research. Guidelines for selecting estimating techniques based on geological conditions and project objectives are given to practitioners. The review emphasises how geostatistical techniques must be continuously improved to improve resource estimation precision and facilitate well-informed mining sector decision-making.

Jul 3, 2026

By M. Ataei, F. Sereshki, R. N. Masir

Given the inherent risks and disruptions in underground coal mining operations, strengthening the resilience of critical infrastructure has become a vital priority. This paper aims to evaluate the resilience of the underground coal mining environment using historical data and expert judgment. The study serves as a framework for optimising the utilisation of critical infrastructure to minimise operational disturbances. To achieve this, a practical methodology has been developed, incorporating nearly two and a half years of collected operational data, a hierarchical structure, and a systematic approach. Furthermore, a case study is conducted to demonstrate the real-world applicability of the proposed method. Finally, the resilience index isintroduced as a straightforward summation of ranked impact factors, providing a clear metric for resilience assessment.

Dec 15, 2025

By S. Botes, H. van der Merwe

While the refractory lining contains the process on a steady-state basis, the tap-hole must provide a channel for transport of molten materials at discreet intervals, with thermal cycling as routine. The tap-hole introduces a discontinuity in any lining, and this fact can lead to failure in the region around the tap-hole before general lining failure occurs. Hence there is a need for a rapid and reliable tap-hole repair technique that can be readily implemented in conjunction with all types of linings. The UCAR®V Repair supplied by GrafTech is a durable solution capable of repairing all types of lining designs and has been extensively utilized in the ferroalloy industry. More than 20 UCAR®V Repairs have been successfully performed in South Africa alone. This paper describes the system in general and reviews recent repairs and their unique challenges.

Jan 1, 2014

By K. Dagdelen , S. K. A. Owusu

Uncertainty with regard to estimated grades and tonnages of a mineral deposit demands risk assessment in order to build investor confidence and attract the interest of other stakeholders in the success of a project. Uncertainties associated with Mineral Resource estimates can lead to unreliable production schedules and unpredictable cash flows. However, the techniques used in the mining industry to determine these uncertainties are inconsistent, because the important decisions taken in the process are solely dependent on the responsible Competent Person (CP), without limitations. This leads to disparities between different CPs’ results, using data-sets from the same drill-holes. The various standard codes for public disclosure provide guidelines and recommendations for the classification of Mineral Resources and Reserves but do not provide details on, for example, the amount of geological and geostatistical information needed to qualify for each category of Resources and Reserves. The parameters used to generate the classification categories are subjectively assumed by the responsible CP. In this paper we investigate the impacts of different CPs’ judgements on resource classification, using the same data-sets. The results underpin the need for the mining industry to develop a uniform Mineral Resources and Reserves classification framework that can minimize or avoid significant discrepancies that lead to potential misleading public disclosures.

Aug 8, 2024

By M. Åstrand, M. Johansson

"Advanced planning and automation are increasingly important in modern mines. Sophisticated methods for long-term mine planning are often used, and the advent of autonomous machines makes the actual operation more predictable. However, the interface between these two timescales, i.e. the scheduling of the mobile production fleet, often limits the ability to operate mines at maximum profitability. We show how scheduling the production fleet in an underground mine can be modelled as a flow shop. A flow shop is a general abstract process formulation that captures the key properties of a scheduling problem without going into specific details. Thus, the flow shop enables mine scheduling to reap the benefits of scheduling research from other industries. We review recent results from the mining community and the flow shop community, and introduce scheduling methods used in these two fields. This work aims at providing value to researchers from the mining community who want to leverage their skill set, as well as to theoretical researchers by presenting the mining process as a potential application area. Lastly, we discuss the results, and outline some future challenges and opportunities facing the industry. IntroductionThe margins in underground mining are constantly under pressure since costs increase as the mine becomes deeper. One major component influencing the operational performance, and thus the profitability of an underground mine, is how the mobile machinery and staff are coordinated. Today, the coordination of the underground fleet, i.e. scheduling of the machines, is mostly done manually, with methods that are stretched to their limit and with no guarantees on performance. According to a survey of more than 200 high-level executives in mining companies around the world (Mincom, 2011), the top challenge for modern mines is to maximize production effectiveness, rather than improving the reliability of individual items of equipment. This highlights the importance of coordination on a system level.The effectiveness of mine production can be increased by introducing supportive algorithms in the scheduling process. These algorithms enable mines to construct optimized schedules with respect to custom metrics. Additionally, manual scheduling is a tedious and error-prone task where the performance is heavily dependent on the scheduler. To reduce the staff dependency, supportive algorithms can help to achieve more uniform outcomes, resulting in a more predictable process. In turn, this increases the transparency of the mining process through the entire production chain. It is worth noting that automatic scheduling has proved beneficial in many other industries, such as chemicals and metals (Floudas and Lin, 2004; Tang et al., 2001)."

Dec 1, 2018

By R. C. A. Minnitt, A. Akpabio

This study presents a rigorous comparison between ordinary kriging and commonly used machine learning algorithms, those being, linear regression, support vector regression, decision trees, random forests (RF), and k-nearest neighbours for spatial interpolation of platinum grade estimates in a complex ore body within the Bushveld Igneous Complex. Using only X and Y coordinates as predictors, both ordinary kriging and machine learning models were evaluated at point and block supports under traditional and spatial block cross validation frameworks. While naive validation results suggested superior performance for k-nearest neighbour and random forest (R² = 0.92 and 0.86, respectively), these were revealed to be overly optimistic under spatial dependence. Spatial block cross validation results demonstrated substantial declines in model performance, with R² often falling below zero, particularly for decision trees and k-nearest neighbour, indicating strong overfitting and limited generalisability. Ordinary kriging exhibited more stable, albeit modest, performance under spatial validation, reflecting its strength in geostatistical interpolation when contextual geological variables are unavailable. The study underscores the critical importance of spatially aware validation in resource estimation and highlights that machine learning models constrained to spatial coordinates behave as interpolators rather than true learners of geological variability. Recommendations are provided for future work incorporating geological information to enhance predictive robustness.

Mar 30, 2026

By S. Swanepoel, A. V. Cherkaev, Q. G. Reynolds, M. Erwee

Ferrochrome (FeCr) is a vital ingredient in stainless steel production and is commonly produced by smelting chromite ores in submerged arc furnaces. Silicon (Si) is a componrnt of the FeCr alloy from the smelting process. Being both a contaminant and an indicator of the state of the process, its content needs to be kept within a narrow range. The complex chemistry of the smelting process and interactions between various factors make Si prediction by fundamental models infeasible. A data-driven approach offers an alternative by formulating the model based on historical data. This paper presents a systematic development of a data-driven model for predicting Si content. The model includes dimensionality reduction, regularized linear regression, and a boosting method to reduce the variability of the linear model residuals. It shows a good performance on testing data (R2 = 0.63). The most significant predictors, as determined by linear model analysis and permutation testing, are previous Si content, carbon and titanium in the alloy, calcium oxide in the slag, resistance between electrodes, and electrode slips. Further analysis using thermodynamic data and models, links these predictors to electrode control and slag chemistry. This analysis lays the foundation for implementing Si content control on a ferrochrome smelter.

Mar 14, 2024

By C. Musingwini, G. Njowa, M. Burnett, C. C. Birch

From 2022 to 2040, the global demand for mineral commodities is projected to increase by fourfold to six-fold, largely due to traditional drivers such as population growth and urbanisation compounded by the adoption of decarbonisation technologies that are more mineral intensive than fossil fuel technologies. To meet this projected demand, companies operating in the minerals industry should accelerate the development of mineral projects. Since most of the companies generally operate in multiple geographical, regulatory or legislative jurisdictions, it is critical that the information on Mineral Resources and Mineral Reserves they report on in the public domain should be comparable and consistent across different jurisdictions. The Committee for Mineral Reserves International Reporting Standards fosters alignment of national and regional mineral reporting codes through an internationally accepted template that creates common technical understanding of definitions, classification, estimation processes and the Public Reporting of Exploration Results, Mineral Resources, and Mineral Reserves. The Committee for Mineral Reserves International Reporting Standards Template-based codes guide reporting at respective national and regional levels. Since mine planning is critical in the conversion of mineral resources to mineral reserves, a shared technical understanding should aid comparability of mine planning results. However, differences persist in the way mine planning results are reported. Unlike most previous studies, which have primarily focused on comparing mineral reporting codes, this paper updates and extends such comparisons by exploring how similarities or differences in reporting should influence the mine planning process. It also recommends some principle and process changes to assist mine planning professionals to improve consistency and comparability in reporting mine planning results.

Mar 30, 2026

By A. Melkumyan, M. Balamurali, J. Zigman

Understanding the contribution of geophysical variables is vital for identifying ore indicator regions. Both magnetometry and gamma-rays are used to identify the geophysical signatures of the rocks. Density is another key variable for tonnage estimation in mining, and needs to be re-estimated in areas of change when a boundary update has been conducted. Modelling these geophysical variables in 3D will enable investigation of the properties of the rocks and improve our understanding of the ore. The Gaussian Process (GP) was previously used to generate 3D spatial models for grade estimation using geochemical assays. This study investigates the influence of the following two factors on the GP-based autonomously generated 3D geophysical models: the resolution of the input data, and the number of nearest samples used in the training process. A case study conducted on a typical Hammersley Ranges iron ore deposit using geophysical logs, including density, collected from the exploration holes, is examined in this paper.

Sep 1, 2021

By D. Almond

Low-grade, complex mineral deposits have resulted in the need for complicated large-throughput processing plants delivering increased productivity, reliability, and utilization, together with reducing operational costs. Complex mineralogy has resulted in complicated process flow sheets designed to recover minerals as efficiently as possible. In addition, the remote location of many minerals-processing plants, continuously rising energy costs, and fierce competition pose significant challenges to the modern mine, compounded by a global scarcity of qualified and experienced operational personnel. Over the last decade the Internet and automation technologies have undergone major advancements. Automation technologies, solutions, and concepts that existed, but were considered risky or unreliable prior to the year 2000, have now gained acceptance and matured. Furthermore, new technologies and different collaboration schemes have appeared, offering innovative solutions to the mining industry to address many of the challenges described. These advancements in reliable remote systems that access technology through the Internet provide significant opportunity to support mining operations, enhance process performance, provide engineering services, and proactively anticipate and execute maintenance services. This paper references a global survey of automation trends in the mining industry and the potential for an intelligent collaborative environment using automation technologies to exploit opportunities in operating the plant of the future, increasing effectiveness, and reducing operational costs. A variety of possibilities are described, including asset management solutions, remote access capabilities, performance monitoring solutions, advanced process control technologies, and the formation of an intelligent collaborative environment. A real example where this technology is used to support the operation and maintenance at a cement plant in Egypt is given to underpin the concepts described in this paper.

Jan 1, 2012

By L. Schernikau, W. H. Smith

Oil, coal, and gas account for approximately 80% of global primary energy, but only a portion of total airborne CO2 eq (approx. 35% at GWP20 to 65% at GWP100), even though they account for 95% of total measured CO2 emissions. The benefits of these energy sources, as well as their related costs, are not all incorporated in current energy policy discussions. Global greenhouse gas policies must include documented changes in measured airborne CO2 eq to avoid spending large amounts of public funds on ineffective or sub-optimal policies. The authors examined airborne CO2, which is less than half of emitted CO2, as well as reported CH4 emissions and the global warming potential of CH4 as published by the IPCC for coal and natural gas. The surprising conclusion is that surfaced-mined coal appears ‘better for the climate’ than the average natural gas, and all coal appears beneficial over LNG. Therefore, current CO2-only reduction policies and CO2 taxes are leading to unintended consequences and the switch from coal to natural gas, especially LNG, will not have the desired impact of reducing predicted future global warming; in fact, quite the contrary. A large portion of anthropogenic global warming is attributed by the IPCC and IEA to CH4, but it must be noted that CH4 emissions from natural sources and from agriculture account for approximately 40% and 25% of annual global CH4 emissions respectively. Energy accounts for about 20% of documented CH4 emissions. CO2 contributes only approximately 35% of annual airborne anthropogenic GHG emissions after accounting for CH4, over a 20-year horizon. At a 100-year horizon, the contribution of CO2 increases to approximately 60%. Energy policies that do not consider all GHG emissions along the entire value chain will lead to undesired economic and environmental distortions. All carbon taxation and CO2 pricing schemes are incorrect and need to be revised. At IPCC’s GWP20 an approximately 2%1 higher loss of CH4 across the value chain prior to combustion of natural gas versus coal will lead to ‘climate parity’ of coal with natural gas. According to public data, natural gas value chains have high CH4 and undocumented CO2 losses. On a global average, using only IEA-documented CH4 data, natural gas emits approximately 15% more CO2 eq than surface-mined coal, over a 20-year horizon. This difference will increase as the use of shale gas and LNG expands. Investors should support all energy systems in a manner that avoids an energy crisis, including intermittent renewable energy systems where they make sense. If CO2 emissions need to be reduced, one of the most effective ways would be to install ultra-supercritical power plants with CCUS technology. However, the undisputed benefits of increased CO2 concentrations in the atmosphere because of its promotion of photosynthesis and plant growth effects (fertilization) need to be considered in energy policy decisions as well. The authors suggest that future research and development should concentrate on reducing net emissions from fossil fuel power plants and providing cost-effective and reliable new conventional power generation capacity, utilizing clean coal and clean natural gas technology.

Mar 2, 2022

By F. Navarro, F. Soto, G. Díaz, E. Jélvez, G. Morales, N. Morales

The increasing availability of tools on the web provides a great opportunity for the research community to boost investigation by accessing computational resources from all over the world. For example, data analytics libraries implemented in languages like Python can be accessed through many open and commercial platforms, therefore providing researchers with a common set of tools or shared datasets. Unfortunately, that is not the case with research in resource assessment and mine planning, where the most standardised tools are commercial applications designed to work on the desktop, but there are not many standard platforms for research. As a result, researchers from different groups often need to start from scratch in order to develop their work, and rarely share implementations details. Similarly, apart from a few publicly available examples, there is a lack of common datasets that are validated and can be used to compare results between different approaches. In this paper, we introduce a platform that provides tools for resource assessment and mine planning, which can be accessed remotely utilising Jupyter Notebooks. In its current version, the platform provides (i) definition and implementation of basic structures for managing samples and models (loading, saving, adding or removing columns, etc.), (ii) definition of experimental and modelled variograms for spatial continuity analysis, (iii) definition of standard interpolation methods in resource evaluation (inverse distance and kriging), (iv) definition of standard problems in mine planning (ultimate pit and precedence constrained production scheduling), (v) generation of 2D standard graphs like grade distribution, conditional means, tonnage-grade, and production plans (vi) a set of datasets, which can be used for case studies, and (vii) a set of notebooks with examples and documentation. In this paper, we introduce the platform and show some examples that illustrate some of the possibilities that it has for research and education in the area of resource assessment and mine planning.

Sep 1, 2021

By M. A. Mahboob, T. Celik, B. Genc

Mineral Resources estimation plays a crucial role in the profitability of the future of mining operations. The conventional geostatistical methods used for grade estimation require expertise, understanding and knowledge of the spatial statistics, resource modelling, geology, mining engineering as well as clean validated data to build accurate block models. However, the geostatistical models are sensitive to changes in data and would have to be rebuilt on newly acquired data with different characteristics, which has proved to be a time-consuming process. Machine learning methods have in recent years been proposed as an alternative to the geostatistical methods to alleviate the problems these might suffer from in Mineral Resource estimation. In this paper, a systematic literature review of machine learning methods used in Mineral Resource estimation is presented. This has been conducted on such studies published during the period 1990 to 2019. The types, performances, and capabilities, of several machine learning methods have been evaluated and compared against each other, and against the conventional geostatistical methods. The results, based on 31 research studies, show that the machine learningbased methods have outperformed the conventional grade estimation modelling methods. The review also shows there is active research on applying machine learning to grade estimation from exploration through to exploitation. Further improvements can be expected if advanced machine learning techniques are to be used.

Nov 30, 2022

By M. Z. Emad, A. Hassan, M. A. Raza, M. U. Khan, S. A. Saki

Digital modelling of a surface is crucial for Earth science and mining applications for many reasons. These days, high-tech digital representations are used to produce a high-fidelity topographic surface in the form of a digital terrain model (DTM). DTMs are created from 2D data-points collected by a variety of techniques such as traditional ground surveying, image processing, LiDAR, radar, and global positioning systems. At the points for which data is not available, the heights need to be interpolated or extrapolated from the points with measured elevations. There are several interpolation/extrapolation techniques available, which may be categorized based on criteria such as area size, accuracy or exactness of the surface, smoothness, continuity, and preciseness. In this paper we examine these DTM production methods and highlight their distinctive characteristics. Real data from a mine site is used, as a case study, to create DTMs using various interpolation techniques in Surfer® software. The significant variation in the resulting DTMs demonstrates that developing a DTM is not straightforward and it is important to choose the method carefully because the outcomes depend on the interpolation techniques used. In mining instances, where volume estimations are based on the produced DTM, this can have a significant impact. For our data-set, the natural neighbour interpolation method made the best predictions (R2 = 0.969, β = 0.98, P < 0.0001).

Feb 6, 2023