Gold has been present throughout the history of mankind and used to make jewelry and coins, and recently, acquired several industrial uses. The price of gold in international market had a significant increasing, surpa...Gold has been present throughout the history of mankind and used to make jewelry and coins, and recently, acquired several industrial uses. The price of gold in international market had a significant increasing, surpassing 100% in the last five years. Thereby, deposits with low levels of gold content, gold with complex associations or in a very fine particle size became exploitable again, allowing new projects and expansion of existing ones. However, for maximum process efficiency is indispensable a deep knowledge of the characteristics of these minerals and their behavior in face of beneficiation processes. Consequently, an accurate routine for mineralogical and technological characterization is essential.展开更多
New attention has been given to the resources of rare earth minerals over the last years. The natural shortage of these elements in the Earth’s crust and trade restrictions recently imposed by China, motivated the Br...New attention has been given to the resources of rare earth minerals over the last years. The natural shortage of these elements in the Earth’s crust and trade restrictions recently imposed by China, motivated the Brazilian Government to encourage new projects by inserting the exploitation of rare earths in the National Mining Plan, which deals with industry strategic issues in the country, helping to reduce current importation. The incentives can be in the choice of future targets for mineral exploration and for the development of laboratory studies and pilot scale processing tests.展开更多
Understanding rock mineralogy is essential for formation evaluation,improving the calculation of porosity and hydrocarbon saturation.The primary method to obtain the mineralogy from a well is by applying a model to th...Understanding rock mineralogy is essential for formation evaluation,improving the calculation of porosity and hydrocarbon saturation.The primary method to obtain the mineralogy from a well is by applying a model to the geochemical tool’s chemical elements.However,creating a mineralogical model presents challenges such as the minerals’chemical composition and the decision to include a mineral in the model.The traditional application of machine learning can make mineral models less realistic since conventional training is developed based on a set of minerals with different occurrences,lowering some minerals’representativeness.The present research proposes the stepped machine learning(SML),a stepped way to use machine learning to create a mineralogical model from chemical and mineralogical data.A database was assembled with the elemental concentration obtained with XRF analyses and the mineral concentrations obtained with XRD analyses.The chemical elements were Al,Ca,Fe,K,Mg,Mn,Na,Si,and Ti.The minerals were calcite,dolomite,quartz,clays,K-feldspar,plagioclase,and pyroxene.Four algorithms were tested:MLP,GAN,Random Forest,and XGBoost,with XGBoost showing the best results.SML was applied,where a mineral model results are used to train a subsequent model.SML allowed for a significant improvement in some models,notably to clays with an increase in R 2 from 0.597 to 0.853,quartz an increase from 0.673 to 0.869,and calcite,from 0.758 to 0.862.A decrease in the mean squared error of these minerals’models was also observed.The model was applied to the geochemical logs from three wells drilled in the Brazilian pre-salt,and the results were compared with XRD analyzes.The SML model was able to honor the mineral concentrations for different rocks.It is demonstrated that the integration between machine learning tools and geological knowledge in SML was crucial for creating a representative mineralogical model.展开更多
文摘Gold has been present throughout the history of mankind and used to make jewelry and coins, and recently, acquired several industrial uses. The price of gold in international market had a significant increasing, surpassing 100% in the last five years. Thereby, deposits with low levels of gold content, gold with complex associations or in a very fine particle size became exploitable again, allowing new projects and expansion of existing ones. However, for maximum process efficiency is indispensable a deep knowledge of the characteristics of these minerals and their behavior in face of beneficiation processes. Consequently, an accurate routine for mineralogical and technological characterization is essential.
文摘New attention has been given to the resources of rare earth minerals over the last years. The natural shortage of these elements in the Earth’s crust and trade restrictions recently imposed by China, motivated the Brazilian Government to encourage new projects by inserting the exploitation of rare earths in the National Mining Plan, which deals with industry strategic issues in the country, helping to reduce current importation. The incentives can be in the choice of future targets for mineral exploration and for the development of laboratory studies and pilot scale processing tests.
文摘Understanding rock mineralogy is essential for formation evaluation,improving the calculation of porosity and hydrocarbon saturation.The primary method to obtain the mineralogy from a well is by applying a model to the geochemical tool’s chemical elements.However,creating a mineralogical model presents challenges such as the minerals’chemical composition and the decision to include a mineral in the model.The traditional application of machine learning can make mineral models less realistic since conventional training is developed based on a set of minerals with different occurrences,lowering some minerals’representativeness.The present research proposes the stepped machine learning(SML),a stepped way to use machine learning to create a mineralogical model from chemical and mineralogical data.A database was assembled with the elemental concentration obtained with XRF analyses and the mineral concentrations obtained with XRD analyses.The chemical elements were Al,Ca,Fe,K,Mg,Mn,Na,Si,and Ti.The minerals were calcite,dolomite,quartz,clays,K-feldspar,plagioclase,and pyroxene.Four algorithms were tested:MLP,GAN,Random Forest,and XGBoost,with XGBoost showing the best results.SML was applied,where a mineral model results are used to train a subsequent model.SML allowed for a significant improvement in some models,notably to clays with an increase in R 2 from 0.597 to 0.853,quartz an increase from 0.673 to 0.869,and calcite,from 0.758 to 0.862.A decrease in the mean squared error of these minerals’models was also observed.The model was applied to the geochemical logs from three wells drilled in the Brazilian pre-salt,and the results were compared with XRD analyzes.The SML model was able to honor the mineral concentrations for different rocks.It is demonstrated that the integration between machine learning tools and geological knowledge in SML was crucial for creating a representative mineralogical model.