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 sec...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.展开更多
This paper points out that the mineral rights should be transferred at the mineral resource’s own value after the analysis that the resource owner can not recover the resource’s value only by collecting the mineral ...This paper points out that the mineral rights should be transferred at the mineral resource’s own value after the analysis that the resource owner can not recover the resource’s value only by collecting the mineral resource tax and the mineral resource compensating fee.Then the paper expounds the theory on mineral resource evaluation and gives out tbe income evaluating model. The paper finally concludes that the mineral rights should be transferred by the manner of auction after the analysis on the requirements asked by the economics on the mineral rights-transferring.展开更多
The Kaerqueka polymetallic deposit, Qinghai, China, is one of the typical skarn-type polymetallic ore deposits in the Qimantage metallogenic belt. The dynamic mechanism on the formation of the Kaerqueka polymetallic d...The Kaerqueka polymetallic deposit, Qinghai, China, is one of the typical skarn-type polymetallic ore deposits in the Qimantage metallogenic belt. The dynamic mechanism on the formation of the Kaerqueka polymetallic deposit is always an interesting topic of research. We used the finite difference method to model the mineralizing process of the chalcopyrite in this region with considering the field geological features, mineralogy and geochemistry. In particular, the modern mineralization theory was used to quantitatively estimate the related chemical reactions associated with the chalcopyrite formation in the Kaerqueka polymetallic deposit. The numerical results indicate that the hydrothermal fluid flow is a key controlling factor of mineralization in this area and the temperature gradient is the driving force of pore-fluid flow. The metallogenic temperature of chalcopyrite in the Kaerqueka polymetallic deposit is between 250 and 350 ℃. The corresponding computational results have been verified by the field observations. It has been further demonstrated that the simulation results of coupled models in the field of emerging computational geosciences can enhance our understanding of the ore-forming processes in this area.展开更多
To achieve a synergistic solution for both sustainable waste management and permanent CO_(2) sequestration,CO_(2) mineralization via fly ash particles is an option.Based on computational fluid dynamics,two specialized...To achieve a synergistic solution for both sustainable waste management and permanent CO_(2) sequestration,CO_(2) mineralization via fly ash particles is an option.Based on computational fluid dynamics,two specialized reactors for fly ash mineralization were designed.The reactor designs were strategically tailored to optimize the interactions between fly ash particles and flue gas within the reactor chamber while concurrently facilitating efficient post-reaction-phase separation.The impinging-type inlet configuration dramatically enhanced the interfacial interaction between the fly ash particles and the gaseous mixture,predominantly composed of CO_(2) and steam.This design modality lengthens the particle residency and reaction times,substantially augmenting the mineralization efficiency.A rigorous investigation of three operational parameters,that is,flue gas velocity,carrier gas velocity,and particle velocity,revealed their influential roles in gas-particle contact kinetics.Through a computational investigation,it can be ascertained that the optimal velocity regime for the flue gas was between 20 and 25 m⋅s1.Concurrently,the carrier gas velocity should be confined to the range of 9-15 m⋅s1.Operating within these finely tuned parameters engenders a marked enhancement in reactor performance,thereby providing a robust theoretical basis for operational efficacy.Overall,a judicious reactor design was integrated with data-driven parameter optimization.展开更多
文摘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.
文摘This paper points out that the mineral rights should be transferred at the mineral resource’s own value after the analysis that the resource owner can not recover the resource’s value only by collecting the mineral resource tax and the mineral resource compensating fee.Then the paper expounds the theory on mineral resource evaluation and gives out tbe income evaluating model. The paper finally concludes that the mineral rights should be transferred by the manner of auction after the analysis on the requirements asked by the economics on the mineral rights-transferring.
基金Project(2017YFC0601503)supported by the National Key R&D Program of ChinaProjects(41872249,41472302,41772348)supported by the National Natural Science Foundation of China
文摘The Kaerqueka polymetallic deposit, Qinghai, China, is one of the typical skarn-type polymetallic ore deposits in the Qimantage metallogenic belt. The dynamic mechanism on the formation of the Kaerqueka polymetallic deposit is always an interesting topic of research. We used the finite difference method to model the mineralizing process of the chalcopyrite in this region with considering the field geological features, mineralogy and geochemistry. In particular, the modern mineralization theory was used to quantitatively estimate the related chemical reactions associated with the chalcopyrite formation in the Kaerqueka polymetallic deposit. The numerical results indicate that the hydrothermal fluid flow is a key controlling factor of mineralization in this area and the temperature gradient is the driving force of pore-fluid flow. The metallogenic temperature of chalcopyrite in the Kaerqueka polymetallic deposit is between 250 and 350 ℃. The corresponding computational results have been verified by the field observations. It has been further demonstrated that the simulation results of coupled models in the field of emerging computational geosciences can enhance our understanding of the ore-forming processes in this area.
文摘To achieve a synergistic solution for both sustainable waste management and permanent CO_(2) sequestration,CO_(2) mineralization via fly ash particles is an option.Based on computational fluid dynamics,two specialized reactors for fly ash mineralization were designed.The reactor designs were strategically tailored to optimize the interactions between fly ash particles and flue gas within the reactor chamber while concurrently facilitating efficient post-reaction-phase separation.The impinging-type inlet configuration dramatically enhanced the interfacial interaction between the fly ash particles and the gaseous mixture,predominantly composed of CO_(2) and steam.This design modality lengthens the particle residency and reaction times,substantially augmenting the mineralization efficiency.A rigorous investigation of three operational parameters,that is,flue gas velocity,carrier gas velocity,and particle velocity,revealed their influential roles in gas-particle contact kinetics.Through a computational investigation,it can be ascertained that the optimal velocity regime for the flue gas was between 20 and 25 m⋅s1.Concurrently,the carrier gas velocity should be confined to the range of 9-15 m⋅s1.Operating within these finely tuned parameters engenders a marked enhancement in reactor performance,thereby providing a robust theoretical basis for operational efficacy.Overall,a judicious reactor design was integrated with data-driven parameter optimization.
