Optimal Classification of Minerals by Microscopic Image Analysis Based on Seven-State “Deep Learning” Combined with Optimizers

The development of artificial intelligence (AI), particularly deep learning, has made it possible to accelerate and improve the processing of data collected in different fields (commerce, medicine, surveillance or security, agriculture, etc.). Most related works use open source consistent image databases. This is the case for ImageNet reference data such as coco data, IP102, CIFAR-10, STL-10 and many others with variability representatives. The consistency of its images contributes to the spectacular results observed in its fields with deep learning. The application of deep learning which is making its debut in geology does not, to our knowledge, include a database of microscopic images of thin sections of open source rock minerals. In this paper, we evaluate three optimizers under the AlexNet architecture to check whether our acquired mineral images have object features or patterns that are clear and distinct to be extracted by a neural network. These are thin sections of magmatic rocks (biotite and 2-mica granite, granodiorite, simple granite, dolerite, charnokite and gabbros, etc.) which served as support. We use two hyper-parameters: the number of epochs to perform complete rounds on the entire data set and the “learning rate” to indicate how quickly the weights in the network will be modified during optimization. Using Transfer Learning, the three (3) optimizers all based on the gradient descent methods of Stochastic Momentum Gradient Descent (sgdm), Root Mean Square Propagation (RMSprop) algorithm and Adaptive Estimation of moment (Adam) achieved better performance. The recorded results indicate that the Momentum optimizer achieved the best scores respectively of 96.2% with a learning step set to 10−3 for a fixed choice of 350 epochs during this variation and 96, 7% over 300 epochs for the same value of the learning step. This performance is expected to provide excellent insight into image quality for future studies. Then they participate in the development of an intelligent system for the identification and classification of minerals, seven (7) in total (quartz, biotite, amphibole, plagioclase, feldspar, muscovite, pyroxene) and rocks.

A Perspective of Laser Sampling for Inductively Coupled Plasma-Atomic Emission Spectro metry for Rock and Mineral Analysis

The development of laser sampling for optical emission spectrometry is reviewed . Advantages and limitations of pulsed laser sampling are compared with those of continuous laser sampling . A novel method of laser sampling of liquid samples for inductively coupled plasma -atomic emission spectrometry has been proposed , and its analytical performance investigated.Experimental results showed that,as a method of sample introduction , laser vaporization of liquid samples enjoyed certain advantages , e.g.,much higher sensitivity, much lower detection limit and reduced sample volume , over solution nebulization . A perspective of the application of laser sampling-inductively coupled plasma - actomic emission spectrometry for rock and mineral analysis is estimated as well.

Deformation mechanism of roadways in deep soft rock at Hegang Xing’an Coal Mine

Engineering geomechanics characteristics of roadways in deep soft rock at Hegang Xing'an Coal Mine were studied and the nature of clay minerals of roadway surrounding rock was analyzed. This paper is to solve the technical problems of high stress and the difficulty in supporting the coal mine, and provide a rule for the support design. Results show that mechanical deformation mechanisms of deep soft rock roadway at Xing'an Coal Mine is of ⅠABⅡABCⅢABCD type, consisting of molecular water absorption (the ⅠAB -type), the tectonic stress type + gravity deformation type + hydraulic type (the ⅡABC -type), and the ⅢABCD -type with fault, weak intercalation and bedding formation. According to the compound mechanical deformation mechanisms, the corresponding mechanical control measures and conversion technologies were proposed, and these technologies have been successfully applied in roadway supporting practice in deep soft rock at Xing'an Coal Mine with good effect. Xing'an Coal Mine has the deepest burial depth in China, with its overburden ranging from Mesozoic Jurassic coal-forming to now. The results of the research can be used as guidance in the design of roadway support in soft rock.

Advances in interaction mechanism of water(gas) on clay minerals in China

Dealing with large-scale deformations in soft-rock tunnels is a very important issue in soft-rock tunnel engineering. The mechanism of this large-scale deformation is closely related to the physical and chemical properties of soft rock, interaction between soft rock and water, and interaction between soft rock and gas contained in soft rock. In order to gain a better predictive understanding of the governing principles associated with this phenomenon, we used experimental and theoretical methods to study the effects of point defect on physical and chemical properties of soft rock and mechanism of interaction between water(gas) and soft rock. Firstly, we calculated the impurity formation energies and transition energy levels of defects by using the first-principle calculation, the results showed the microscopic mechanism of defects substitution in kaolinite and effects of defects on the structure of kaolinite. Moreover,comparing the experimental and theoretical results, we found the mechanism of interaction between water and soft rock. The results show that water is one of the most important factors which can induce various kinds of geological disasters. At last, the interaction between soft rock and surrounding gas as CO2, CH4 and CO is disused, the influence of surrounding gas on soft rock should not be ignored.

Geomechanical and water vapor absorption characteristics of clay-bearing soft rocks at great depth

The geological and physico-mechanical properties characterization of deep soft rocks is one of the critical scientific issues for deep soft rock engineering. In the present study, X-ray diffraction(XRD) analysis,scanning electron microscope(SEM), and mercury intrusion porosimetry experiments were carried out to investigate the mineral compositions, microstructure and porosity characteristics of the 13 claybearing soft rock samples collected from a deep coal mine in China. Water vapor absorption and uniaxial compressive experiments were also performed to examine water absorption characteristics and waterinduced strength degradation effect of the investigated deep soft rock samples. The results show that the dominant mineral components in mudstone, coarse sandstone and fine sandstone samples were calcite, quartz and clay respectively. The contents of clay minerals in all samples were relatively high and ranged from 12.3%(N-4) to 56.5%(XS-1). Water vapor absorption processes of all the soft rock samples follow an exponential law which is very similar to the water vapor absorption behavior of conglomerate samples reported in our earlier study. Correlation analyses also suggested that there were good positive correlation relationships between water absorptivity and clay minerals for both mudstone and sandstone samples. Furthermore, it was found that vapor absorption was not correlated with the porosity for mudstone, however, positive correlation relationship was found between them for sandstone. Correlation analysis between UCS, modulus of elasticity and water content demonstrated that both of them tend to decrease with the increase of their water content due to water absorption.

Hydrophilic characteristics of soft rock in deep mines

A series of water absorption tests on dried soft rock have been conducted by the intelligent testing system for water absorption tests in deep soft rock, including tests of water absorption with and without pres- sure. The results show that the water absorbing capacity of rock with a certain pressure is larger than that of rock without pressure： however, the relationship between the water absorbing percentage and the time can be expressed by w（t） = a（l - e^-bt）. In hi-logarithmic coordinates, the hydrophilic relationship with time in tests with pressure could be characterized by linearity, while they present concave or convex in tests without pressure. Based on the hypothesis that each influential factor is irrelevant and they have a linear correlation with the water absorbing capacity, we calculated the weight coefficient of each factor according to experimental results under different conditions. The calculations demonstrate that the effec- tive porosity, content of smectite and kaolinite are all positively correlated with the water absorption capacity of rock; meanwhile, the fractal dimension of the effective pores presents a negative correlation with the water absorption capacity of rock. The water absorption capacity with pressure increases with increasing illite, chlorite and chlorite/smectite formation and a decrease in illite/smectite formation and the fractal dimension of the effective pores, while it is opposite in tests without pressure. The weight coefficient of smectite is smallest among positive factors, and the fractal dimension of the effective pores is the smallest amongst the negative factors.

多矿物岩石流变性的有限元计算

本文利用有限元计算方法从单矿物的流变关系式来确定其组合而成的岩石整体的流变规律。建立了三维不可压缩流体的粘弹性有限元模型,计算模型的骨架矿物橄榄石为立方体,填充矿物尖晶石分别取为立方体、单一球体和多个球体,模拟双矿物在三轴压缩实验条件下的蠕变变形过程。首先,本文验证了使用有限元方法数值模拟双矿物在三轴压缩实验下的蠕变变形的可行性。其次,计算研究了当填充矿物为弱矿物时几何外形对整体流变强度的影响,结果表明,填充矿物的几何外形为立方体时比球体时对整体的流变强度有更大的影响。当填充矿物体积不同时,随着填充矿物体积的增加,填充矿物对整体流变强度的影响也不断加大。最后利用三维模型得到的双矿物整体的流变强度结果,归纳出了填充矿物尖晶石占体积5％,10％,15％,20％时和骨架矿物橄榄石构成的双矿物岩石的蠕变关系式。与Tullis利用平面应变模型归纳出的双矿物经验流变关系式比较,发现Tullis的经验流变公式存在较大的误差,而本文得到的双矿物蠕变公式与理论结果更好地符合本文结果为研究地幔多矿物岩石流变规律提供了新的途径。

Some Challenges of Deep Mining

An increased global supply of minerals is essential to meet the needs and expectations of a rapidly rising world population. This implies extraction from greater depths. Autonomous mining systems, developed through sustained R＆D by equipment suppliers, reduce miner exposure to hostile work environments and increase safety. This places increased focus on ＂ground control＂ and on rock mechanics to define the depth to which minerals may be extracted economically. Although significant efforts have been made since the end of World War II to apply mechanics to mine design, there have been both technological and organizational obstacles. Rock in situ is a more complex engineering material than is typically encountered in most other engineering disciplines. Mining engineering has relied heavily on empirical procedures in design for thousands of years. These are no longer adequate to address the challenges of the 21st century, as mines venture to increasingly greater depths. The development of the synthetic rock mass （SRM） in 2008 provides researchers with the ability to analyze the deformational behavior of rock masses that are anisotropic and discontinuous-attributes that were described as the defining characteristics of in situ rock by Leopold Mfiller, the president and founder of the International Society for Rock Mechanics （ISRM）, in 1966. Recent developments in the numerical modeling of large-scale mining operations （e.g., caving） using the SRM reveal unanticipated deformational behavior of the rock. The application of massive parallelization and cloud computational techniques offers major opportunities： for example, to assess uncertainties in numerical predictions： to establish the mechanics basis for the empirical rules now used in rock engineering and their validity for the prediction of rock mass behavior beyond current experience： and to use the discrete element method （DEM） in the optimization of deep mine design. For the first time, mining-and rock engineering-will have its own mechanics-based Ulaboratory.＂ This promises to be a major tool in future planning for effective mining at depth. The paper concludes with a discussion of an opportunity to demonstrate the application of DEM and SRM procedures as a laboratory, by back-analysis of mining methods used over the 80-year history of the Mount Lvell Copper Mine in Tasmania.

RockSL:an integrated rock spectral library for better global shared services

Spectral data of different rocks and minerals usually show different waveforms and absorption characteristics in visible and infrared wavelengths,which allow identification of mineral species and composition.However,massive spectra of rock/mineral on earth surface were scattered across a variety of spectral libraries world-wide,exhibiting inconsistent data structures and measurement conditions.To advance the data interoperability and the data usability,we collected data and information from six shared libraries with different format and measured field specimen in laboratory to establish an integrated rock spectral library(RockSL).Both the data quality of spectral curves and the integrity of descrip-tive metadata are considered in the integrated RockSL to be pub-lished in GitHub open-source repository.RockSL contains not only the big spectral dataset of rocks and minerals for data service(i.e.data sharing and retrieval)and geological discrimination,but also the characteristics dataset of key parameters/metadata(e.g.particle size,mineral composition and full-band signature,etc.)for explora-tion of data mining and knowledge discovery.We hope that more researchers will join to improve the availability and practical value of RockSL for remote sensing community.This article introduces the database structure and data processing workflow,and demon-strates a matching service and several examples of characteristic datasets of RockSL.

Petromagnetic Properties of Granulite-Facies Rocks from the Northern North China Craton: Implications for Magnetic and Evolution of the Continental Lower Crust

This paper studies magnetic properties and composition of granulite-facies rocks of both the Neogene and Archean continental lower crust in the Neogene xenolith-bearing Hannuoba （汉诺坝） alkaline basalt and the exposed lower crustal section in the Archean Huai＇an （淮安） terrain （Wayaokou （瓦窑口）-Manjinggou （蔓菁沟） profile）, the northern North China Craton. It provides a unique oppor-tunity for a comparative study of magnetic properties and composition of both the Archean and Neogene continental lower crust. We measure magnetic parameters （susceptibility x and magnetic hysteresis parameters, such as saturation magnetization Js, saturation isothermal remanent magnetization Jrs, and intrinsic coercivity He） of eleven Hannuoba lower crustal xenoliths and nine terrain granulites from the Archean Huai＇an terrain. Results indicate that the average values of K,Js and Jrs of Archean granu- lites are 4 122×10^-6 SI, 523.1 A/m and 74.9 A/m, respectively, which are generally higher than those of granulite-facies xenoliths （1 657×10^-6 SI, 163.9 A/m and 41.9 A/m, respectively）. These two types of granulites contain ilmenite, （titano） magnetite, minor hematite and some ＂magnetic silicates＂ （clinopyroxene, plagioclase and biotite）. The Mg-rich ilmenite in granulite-facies xenolith is relatively higher than that in terrain granulites. We observe a more evolved character as higher magnetic as well as lower Sr/Nd, Cr/Nd, Ni/Nd, Co/Nd and V/Nd ratios in terrain granulites. These differences in magnetic characteristics reflect their different origins and evolutions. The high magnetization of granulites in the Huai＇an terrain represents magnetic properties of the Archean continental lower crust, and low magnetization of granufite-facies xenoliths represents mag- netic properties of the Cenozoic lower crusts in the northern North China Craton.

Potassium sources, microorganisms and plant nutrition: Challenges and future research directions

Until recently,potassium(K)has not received considerable attention because of the general belief that soils contain ample amounts of this element.In addition,low rates of K fertilizer application in agriculture have led to rapid depletion of K in the rhizosphere soil in many underdeveloped countries.This results in various negative impacts,including preventing optimum utilization of applied nitrogen and phosphorus fertilizers.To compensate for these losses,massive use of K fertilizers in agriculture has been suggested.Potassium fertilizers are manufactured from rock minerals,particularly sylvite(KCl)and carnallite(KCl·MgCl2·6H2O).Unfortunately,to date,there is no cost-effective technology available for converting rock minerals into potassic fertilizers.Potassium-solubilizing microorganisms(KSMs)can release K from soil/minerals into plant-available forms,which could be a sustainable option.The possibility of using KSMs as efficient biofertilizers to improve crop production has been increasingly highlighted by researchers.In this review,the existing forms of K in soils and their availability and dynamic equilibrium are discussed.In addition,different K fertilizers and their advantages and disadvantages for crops are described.Furthermore,the microorganisms usually reported as K solubilizers,the research progress on KSMs,and future insights on the use of these KSMs in agriculture are reviewed.Screening and analyses of the published literature show that organic acid production is the common mechanism of K solubilization by bacteria and fungi.This review may serve as a proposal for the future research avenues identified here.