1.Introduction The global transition to green energy has created an unprecedented demand for critical metals and energy resources such as cobalt,nickel,copper,manganese,rare earth elements,and gas hydrates.Against thi...1.Introduction The global transition to green energy has created an unprecedented demand for critical metals and energy resources such as cobalt,nickel,copper,manganese,rare earth elements,and gas hydrates.Against this strategic backdrop,deep-sea mineral and energy resources are increasingly viewed as essential supplements to terrestrial supply bottlenecks and as strategic safeguards for the future low-carbon economy.The international seabed forms a vast strategic resource of global significance,offering great potential to support energy transition and security.Therefore,under sound scientific evaluation and strict regulation,prudent development of this resource should serve both economic needs and the broader goals of sustainable energy transformation[1].展开更多
Deep Underground Science and Engineering(DUSE)is pleased to present this special issue on Groundwater and Stability in Deep Mining.As mining operations progress to greater depths to meet the growing global demand for ...Deep Underground Science and Engineering(DUSE)is pleased to present this special issue on Groundwater and Stability in Deep Mining.As mining operations progress to greater depths to meet the growing global demand for mineral resources and energy,the challenges associated with groundwater control and rock mass stability have grown increasingly critical.These challenges are exacerbated by complex geological conditions,structural heterogeneity,and intense mining-induced disturbances.This special issue seeks to address these challenges by showcasing cutting-edge research and technological advancements in the field.展开更多
Shear strain energy is a pivotal physical quantity in the occurrence of earthquakes and rockbursts during deep mining operations.This research is focused on understanding the changes in shear strain energy in the cont...Shear strain energy is a pivotal physical quantity in the occurrence of earthquakes and rockbursts during deep mining operations.This research is focused on understanding the changes in shear strain energy in the context of retreating longwall mining,which is essential for the optimized design and mitigation of rockbursts and seismic events.Through the application of innovative analytical models,this study expands its analytical range to include the variations in shear strain energy caused by fault coseismic slip.An integrated methodology is utilized,taking into account the changes in coseismic and fault friction parameters as well as enhancements in mining-induced stress and existing background stresses.Our numerical investigation highlights the significance of mining location and fault characteristics as key determinants of shear strain energy modifications.The analysis demonstrates significant spatial variability in shear strain energy,especially noting that fault slip near the mining face greatly increases the likelihood of rockburst.This finding emphasizes the need to integrate fault coseismic slip dynamics into the triggering factors of rock(coal)bursts,thus broadening the theoretical foundation for addressing geological hazards in deep mining operations.The results are further corroborated by observational data from the vicinity of the F16 fault zone,introducing the concept of mining-induced fault coseismic slip as an essential element in the theoretical framework for understanding rockburst triggers.展开更多
Mineral resources exploitation moving deeper into the earth is an inevitable trend with economic and social development.However,the deep high temperature poses a significant challenge to the safety and efficiency of h...Mineral resources exploitation moving deeper into the earth is an inevitable trend with economic and social development.However,the deep high temperature poses a significant challenge to the safety and efficiency of human and machine.The prevention of potential thermal risks in deep mining is critical.Here,the key and difficult issues of humanmachine-environment temperature monitoring are discussed according to the characteristics of deep hightemperature environment.Then,a monitoring and analysis method of human-machine-environment temperature field suitable for deep high-temperature mining areas is proposed.This method covers humanmachine-environment temperature monitoring,data storage and transmission,data processing,results visualization,and thermal risks warning.The monitoring sensor networks are constructed to collect real-time data of miners,machines,and environments.The data is transmitted to the central processing system for storage and analysis using both wired and wireless transmission technologies.Moreover,digital filtering and Kriging interpolation algorithms are applied to denoise and handle outliers in the monitored data,as well as to calculate the temperature field.The temperature prediction model is constructed using Long Short-Term Memory(LSTM)method.Finally,potential thermal risks are identified by combining real-time monitoring and prediction results,thereby guiding management personnels and miners to take appropriate measures.The proposed monitoring and analysis method can be applied to deep mines that affected by high temperature.It not only provides data and methodological support for assessing thermal risks in mines,but also offers scientific basis for optimizing mining operations and implementing safety measures.展开更多
Security attributes are the premise and foundation for implementing Attribute-Based Access Control(ABAC)mechanisms.However,when dealing with massive volumes of unstructured text big data resources,the current attribut...Security attributes are the premise and foundation for implementing Attribute-Based Access Control(ABAC)mechanisms.However,when dealing with massive volumes of unstructured text big data resources,the current attribute management methods based on manual extraction face several issues,such as high costs for attribute extraction,long processing times,unstable accuracy,and poor scalability.To address these problems,this paper proposes an attribute mining technology for access control institutions based on hybrid capsule networks.This technology leverages transfer learning ideas,utilizing Bidirectional Encoder Representations from Transformers(BERT)pre-trained language models to achieve vectorization of unstructured text data resources.Furthermore,we have designed a novel end-to-end parallel hybrid network structure,where the parallel networks handle global and local information features of the text that they excel at,respectively.By employing techniques such as attention mechanisms,capsule networks,and dynamic routing,effective mining of security attributes for access control resources has been achieved.Finally,we evaluated the performance level of the proposed attribute mining method for access control institutions through experiments on the medical referral text resource dataset.The experimental results show that,compared with baseline algorithms,our method adopts a parallel network structure that can better balance global and local feature information,resulting in improved overall performance.Specifically,it achieves a comprehensive performance enhancement of 2.06%to 8.18%in the F1 score metric.Therefore,this technology can effectively provide attribute support for access control of unstructured text big data resources.展开更多
Taking the Pusa Collapse in Nayong County,Guizhou Province,China as a case study,this paper investigates the impact of multi-layer coal mining on karst mountains characterized by deep fissures.Based on field investiga...Taking the Pusa Collapse in Nayong County,Guizhou Province,China as a case study,this paper investigates the impact of multi-layer coal mining on karst mountains characterized by deep fissures.Based on field investigations and employing discrete element numerical simulations,the deformation and failure mechanisms of karst mountain containing deep and large fissures under multi-seam mining conditions was investigated.The influence of the direction of coal seam extraction and the sequence of extraction between multiple coal seams on the failure modes of karst mountain with deep and large fissures was studied.The results indicate that underground mining primarily manifests in the development of mininginduced fissures in the mountain body,subsidence and deformation of slope masses,and triggering the expansion of existing fissures,further driving overall deformation and damage to the slopes.Deep and large fissures control the deformation and failure modes of the slopes,with closer and longer deep and large fissures near the slope surface exerting greater influence on the slope mass.The impact of mining in the same coal seam direction on the slopes is mainly reflected in the process of slope deformation and failure.Downslope mining directly leads to overall subsidence of the slope mass,squeezing the front and lower parts of the slope mass.Upslope mining initially causes the foot of the slope to sink and the entire slope mass to move outward,and continuous mining leads to overall settlement and downward compression deformation of the slope.The sequence of mining between multiple coal seams mainly affects the overall and local deformation values of the slope mass.Downward mining leads to increased overall subsidence of the slope mass and exacerbates the backward tilt of the slope top.展开更多
The increasing risk of ground pressure disasters resulting from deep well mining highlights the urgent need for advanced monitoring and early warning systems.Ground pressure monitoring,supported by microseismic techno...The increasing risk of ground pressure disasters resulting from deep well mining highlights the urgent need for advanced monitoring and early warning systems.Ground pressure monitoring,supported by microseismic technology,plays a pivotal role in ensuring mine safety by enabling real-time identifi cation and accurate classification of vibration signals such as microseismic signals,blasting signals,and noise.These classifications are critical for improving the efficacy of ground pressure monitoring systems,conducting stability analyses of deep rock masses,and implementing timely and precise roadway support measures.Such eff orts are essential for mitigating ground pressure disasters and ensuring safe mining operations.This study proposes an artificial intelligence-based automatic classification network model for mine vibration signals.Based on conventional convolutional neural networks,the proposed model further incorporates long short-term memory(LSTM)networks and attention mechanisms.The LSTM component eff ectively captures temporal correlations in time-series mining vibration data,while the attention mechanism enhances the models’ability to focus on critical features within the data.To validate the eff ectiveness of our proposed model,a dataset comprising 480,526 waveform records collected in 2022 by the microseismic monitoring system at Guangxi Shanhu Tungsten Mine was used for training,validation,and testing purposes.Results demonstrate that the proposed artifi cial intelligence-based classifi cation method achieves a higher recognition accuracy of 92.21%,significantly outperforming traditional manual classification methods.The proposed model represents a signifi cant advancement in ground pressure monitoring and disaster mitigation.展开更多
The rapid growth of biomedical data,particularly multi-omics data including genomes,transcriptomics,proteomics,metabolomics,and epigenomics,medical research and clinical decision-making confront both new opportunities...The rapid growth of biomedical data,particularly multi-omics data including genomes,transcriptomics,proteomics,metabolomics,and epigenomics,medical research and clinical decision-making confront both new opportunities and obstacles.The huge and diversified nature of these datasets cannot always be managed using traditional data analysis methods.As a consequence,deep learning has emerged as a strong tool for analysing numerous omics data due to its ability to handle complex and non-linear relationships.This paper explores the fundamental concepts of deep learning and how they are used in multi-omics medical data mining.We demonstrate how autoencoders,variational autoencoders,multimodal models,attention mechanisms,transformers,and graph neural networks enable pattern analysis and recognition across all omics data.Deep learning has been found to be effective in illness classification,biomarker identification,gene network learning,and therapeutic efficacy prediction.We also consider critical problems like as data quality,model explainability,whether findings can be repeated,and computational power requirements.We now consider future elements of combining omics with clinical and imaging data,explainable AI,federated learning,and real-time diagnostics.Overall,this study emphasises the need of collaborating across disciplines to advance deep learning-based multi-omics research for precision medicine and comprehending complicated disorders.展开更多
Seafloor massive sulfide（SMS） deposits which consist of Au, Ag, Cu, and other metal elements, have been a target of commercial mining in recent decades. The demand for established and reliable commercial mining syst...Seafloor massive sulfide（SMS） deposits which consist of Au, Ag, Cu, and other metal elements, have been a target of commercial mining in recent decades. The demand for established and reliable commercial mining system for SMS deposits is increasing within the marine mining industry. The current status and progress of mining technology and equipment for SMS deposits are introduced. First, the mining technology and other recent developments of SMS deposits are comprehensively explained and analyzed. The seafloor production tools manufactured by Nautilus Minerals and similar mining tools from Japan for SMS deposits are compared and discussed in turn. Second, SMS deposit mining technology research being conducted in China is described, and a new SMS deposits mining tool is designed according to the environmental requirement. Finally, some new trends of mining technology of SMS deposits are summarized and analyzed. All of these conclusions and results have reference value and guiding significance for the research of SMS deposit mining in China.展开更多
基金financial support from the National Key R&D Program of China(No.2024YFC2815400)the Young Taishan Scholars Program(No.TSQN202507107)+1 种基金the Shandong Natural Science Foundation(No.ZR2025MS647)the European Commission(HORIZON MSCA-2024-PF-01,101200637).
文摘1.Introduction The global transition to green energy has created an unprecedented demand for critical metals and energy resources such as cobalt,nickel,copper,manganese,rare earth elements,and gas hydrates.Against this strategic backdrop,deep-sea mineral and energy resources are increasingly viewed as essential supplements to terrestrial supply bottlenecks and as strategic safeguards for the future low-carbon economy.The international seabed forms a vast strategic resource of global significance,offering great potential to support energy transition and security.Therefore,under sound scientific evaluation and strict regulation,prudent development of this resource should serve both economic needs and the broader goals of sustainable energy transformation[1].
文摘Deep Underground Science and Engineering(DUSE)is pleased to present this special issue on Groundwater and Stability in Deep Mining.As mining operations progress to greater depths to meet the growing global demand for mineral resources and energy,the challenges associated with groundwater control and rock mass stability have grown increasingly critical.These challenges are exacerbated by complex geological conditions,structural heterogeneity,and intense mining-induced disturbances.This special issue seeks to address these challenges by showcasing cutting-edge research and technological advancements in the field.
文摘Shear strain energy is a pivotal physical quantity in the occurrence of earthquakes and rockbursts during deep mining operations.This research is focused on understanding the changes in shear strain energy in the context of retreating longwall mining,which is essential for the optimized design and mitigation of rockbursts and seismic events.Through the application of innovative analytical models,this study expands its analytical range to include the variations in shear strain energy caused by fault coseismic slip.An integrated methodology is utilized,taking into account the changes in coseismic and fault friction parameters as well as enhancements in mining-induced stress and existing background stresses.Our numerical investigation highlights the significance of mining location and fault characteristics as key determinants of shear strain energy modifications.The analysis demonstrates significant spatial variability in shear strain energy,especially noting that fault slip near the mining face greatly increases the likelihood of rockburst.This finding emphasizes the need to integrate fault coseismic slip dynamics into the triggering factors of rock(coal)bursts,thus broadening the theoretical foundation for addressing geological hazards in deep mining operations.The results are further corroborated by observational data from the vicinity of the F16 fault zone,introducing the concept of mining-induced fault coseismic slip as an essential element in the theoretical framework for understanding rockburst triggers.
基金supported by the National Science Foundation for Distinguished Young Scholars of China(Grant No.52425403)。
文摘Mineral resources exploitation moving deeper into the earth is an inevitable trend with economic and social development.However,the deep high temperature poses a significant challenge to the safety and efficiency of human and machine.The prevention of potential thermal risks in deep mining is critical.Here,the key and difficult issues of humanmachine-environment temperature monitoring are discussed according to the characteristics of deep hightemperature environment.Then,a monitoring and analysis method of human-machine-environment temperature field suitable for deep high-temperature mining areas is proposed.This method covers humanmachine-environment temperature monitoring,data storage and transmission,data processing,results visualization,and thermal risks warning.The monitoring sensor networks are constructed to collect real-time data of miners,machines,and environments.The data is transmitted to the central processing system for storage and analysis using both wired and wireless transmission technologies.Moreover,digital filtering and Kriging interpolation algorithms are applied to denoise and handle outliers in the monitored data,as well as to calculate the temperature field.The temperature prediction model is constructed using Long Short-Term Memory(LSTM)method.Finally,potential thermal risks are identified by combining real-time monitoring and prediction results,thereby guiding management personnels and miners to take appropriate measures.The proposed monitoring and analysis method can be applied to deep mines that affected by high temperature.It not only provides data and methodological support for assessing thermal risks in mines,but also offers scientific basis for optimizing mining operations and implementing safety measures.
基金supported by National Natural Science Foundation of China(No.62102449).
文摘Security attributes are the premise and foundation for implementing Attribute-Based Access Control(ABAC)mechanisms.However,when dealing with massive volumes of unstructured text big data resources,the current attribute management methods based on manual extraction face several issues,such as high costs for attribute extraction,long processing times,unstable accuracy,and poor scalability.To address these problems,this paper proposes an attribute mining technology for access control institutions based on hybrid capsule networks.This technology leverages transfer learning ideas,utilizing Bidirectional Encoder Representations from Transformers(BERT)pre-trained language models to achieve vectorization of unstructured text data resources.Furthermore,we have designed a novel end-to-end parallel hybrid network structure,where the parallel networks handle global and local information features of the text that they excel at,respectively.By employing techniques such as attention mechanisms,capsule networks,and dynamic routing,effective mining of security attributes for access control resources has been achieved.Finally,we evaluated the performance level of the proposed attribute mining method for access control institutions through experiments on the medical referral text resource dataset.The experimental results show that,compared with baseline algorithms,our method adopts a parallel network structure that can better balance global and local feature information,resulting in improved overall performance.Specifically,it achieves a comprehensive performance enhancement of 2.06%to 8.18%in the F1 score metric.Therefore,this technology can effectively provide attribute support for access control of unstructured text big data resources.
基金supported by the National Key R&D Program of China(Grant No.2018YFC1504802)the National Natural Science Foundation of China(Grant No.52074042)。
文摘Taking the Pusa Collapse in Nayong County,Guizhou Province,China as a case study,this paper investigates the impact of multi-layer coal mining on karst mountains characterized by deep fissures.Based on field investigations and employing discrete element numerical simulations,the deformation and failure mechanisms of karst mountain containing deep and large fissures under multi-seam mining conditions was investigated.The influence of the direction of coal seam extraction and the sequence of extraction between multiple coal seams on the failure modes of karst mountain with deep and large fissures was studied.The results indicate that underground mining primarily manifests in the development of mininginduced fissures in the mountain body,subsidence and deformation of slope masses,and triggering the expansion of existing fissures,further driving overall deformation and damage to the slopes.Deep and large fissures control the deformation and failure modes of the slopes,with closer and longer deep and large fissures near the slope surface exerting greater influence on the slope mass.The impact of mining in the same coal seam direction on the slopes is mainly reflected in the process of slope deformation and failure.Downslope mining directly leads to overall subsidence of the slope mass,squeezing the front and lower parts of the slope mass.Upslope mining initially causes the foot of the slope to sink and the entire slope mass to move outward,and continuous mining leads to overall settlement and downward compression deformation of the slope.The sequence of mining between multiple coal seams mainly affects the overall and local deformation values of the slope mass.Downward mining leads to increased overall subsidence of the slope mass and exacerbates the backward tilt of the slope top.
基金supported in part by the National Science Fund for Distinguished Young Scholars under Grant (42025403)the National Key Research and Development Plan of China (2021YFA0716800)the National Key Research and Development Plan of China (2022YFC2903804)。
文摘The increasing risk of ground pressure disasters resulting from deep well mining highlights the urgent need for advanced monitoring and early warning systems.Ground pressure monitoring,supported by microseismic technology,plays a pivotal role in ensuring mine safety by enabling real-time identifi cation and accurate classification of vibration signals such as microseismic signals,blasting signals,and noise.These classifications are critical for improving the efficacy of ground pressure monitoring systems,conducting stability analyses of deep rock masses,and implementing timely and precise roadway support measures.Such eff orts are essential for mitigating ground pressure disasters and ensuring safe mining operations.This study proposes an artificial intelligence-based automatic classification network model for mine vibration signals.Based on conventional convolutional neural networks,the proposed model further incorporates long short-term memory(LSTM)networks and attention mechanisms.The LSTM component eff ectively captures temporal correlations in time-series mining vibration data,while the attention mechanism enhances the models’ability to focus on critical features within the data.To validate the eff ectiveness of our proposed model,a dataset comprising 480,526 waveform records collected in 2022 by the microseismic monitoring system at Guangxi Shanhu Tungsten Mine was used for training,validation,and testing purposes.Results demonstrate that the proposed artifi cial intelligence-based classifi cation method achieves a higher recognition accuracy of 92.21%,significantly outperforming traditional manual classification methods.The proposed model represents a signifi cant advancement in ground pressure monitoring and disaster mitigation.
文摘The rapid growth of biomedical data,particularly multi-omics data including genomes,transcriptomics,proteomics,metabolomics,and epigenomics,medical research and clinical decision-making confront both new opportunities and obstacles.The huge and diversified nature of these datasets cannot always be managed using traditional data analysis methods.As a consequence,deep learning has emerged as a strong tool for analysing numerous omics data due to its ability to handle complex and non-linear relationships.This paper explores the fundamental concepts of deep learning and how they are used in multi-omics medical data mining.We demonstrate how autoencoders,variational autoencoders,multimodal models,attention mechanisms,transformers,and graph neural networks enable pattern analysis and recognition across all omics data.Deep learning has been found to be effective in illness classification,biomarker identification,gene network learning,and therapeutic efficacy prediction.We also consider critical problems like as data quality,model explainability,whether findings can be repeated,and computational power requirements.We now consider future elements of combining omics with clinical and imaging data,explainable AI,federated learning,and real-time diagnostics.Overall,this study emphasises the need of collaborating across disciplines to advance deep learning-based multi-omics research for precision medicine and comprehending complicated disorders.
基金Supported by National Natural Science Foundation of China(Grant No.51074179)National Hi-tech Research and Development Program of China(863 Program,Grant No.2012AA091291)Basic Research Foundation of Shenzhen Science and Technology Innovation,China(Grant No.JCYJ20150929102555935)
文摘Seafloor massive sulfide（SMS） deposits which consist of Au, Ag, Cu, and other metal elements, have been a target of commercial mining in recent decades. The demand for established and reliable commercial mining system for SMS deposits is increasing within the marine mining industry. The current status and progress of mining technology and equipment for SMS deposits are introduced. First, the mining technology and other recent developments of SMS deposits are comprehensively explained and analyzed. The seafloor production tools manufactured by Nautilus Minerals and similar mining tools from Japan for SMS deposits are compared and discussed in turn. Second, SMS deposit mining technology research being conducted in China is described, and a new SMS deposits mining tool is designed according to the environmental requirement. Finally, some new trends of mining technology of SMS deposits are summarized and analyzed. All of these conclusions and results have reference value and guiding significance for the research of SMS deposit mining in China.
