Deep-time Earth research plays a pivotal role in deciphering the rates,patterns,and mechanisms of Earth's evolutionary processes throughout geological history,providing essential scientific foundations for climate...Deep-time Earth research plays a pivotal role in deciphering the rates,patterns,and mechanisms of Earth's evolutionary processes throughout geological history,providing essential scientific foundations for climate prediction,natural resource exploration,and sustainable planetary stewardship.To advance Deep-time Earth research in the era of big data and artificial intelligence,the International Union of Geological Sciences initiated the“Deeptime Digital Earth International Big Science Program”(DDE)in 2019.At the core of this ambitious program lies the development of geoscience knowledge graphs,serving as a transformative knowledge infrastructure that enables the integration,sharing,mining,and analysis of heterogeneous geoscience big data.The DDE knowledge graph initiative has made significant strides in three critical dimensions:(1)establishing a unified knowledge structure across geoscience disciplines that ensures consistent representation of geological entities and their interrelationships through standardized ontologies and semantic frameworks;(2)developing a robust and scalable software infrastructure capable of supporting both expert-driven and machine-assisted knowledge engineering for large-scale graph construction and management;(3)implementing a comprehensive three-tiered architecture encompassing basic,discipline-specific,and application-oriented knowledge graphs,spanning approximately 20 geoscience disciplines.Through its open knowledge framework and international collaborative network,this initiative has fostered multinational research collaborations,establishing a robust foundation for next-generation geoscience research while propelling the discipline toward FAIR(Findable,Accessible,Interoperable,Reusable)data practices in deep-time Earth systems research.展开更多
Continental crust is the long-term achievements of Earth's evolution across billions of years.The continental rocks could have been modified by various types of geological processes,such as metamorphism,weathering...Continental crust is the long-term achievements of Earth's evolution across billions of years.The continental rocks could have been modified by various types of geological processes,such as metamorphism,weathering,and reworking.Therefore,physical or chemical properties of rocks through time record the composite effects of geological,biological,hydrological,and climatological processes.Temporal variations in these time series datasets could provide important clues for understanding the co-evolution of different layers on Earth.However,deciphering Earth's evolution in deep time is challenged by incompleteness,singularity,and intermittence of geological records associated with extreme geological events,hindering a rigorous assessment of the underlying coupling mechanisms.Here,we applied the recently developed local singularity analysis and wavelet analysis method to deep-time U-Pb age spectra and sedimentary abundance record across the past 3.5 Gyrs.Standard cross-correlation analysis suggests that the singularity records of marine sediment accumulations and magmatism intensity at continental margin are correlated negatively(R^(2)=0.8),with a delay of~100 Myr.Specifically,wavelet coherence analysis suggests a~500-800 Myr cycle of correlation between two records,implying a coupling between the major downward processes(subduction and recycling sediments)and upward processes(magmatic events)related to the aggregation and segregation of supercontinents.The results clearly reveal the long-term cyclic feedback mechanism between sediment accumulation and magmatism intensity through aggregation of supercontinents.展开更多
1 Introduction Information technology has been playing an ever-increasing role in geoscience.Sphisicated database platforms are essential for geological data storage,analysis and exchange of Big Data(Feblowitz,2013;Zh...1 Introduction Information technology has been playing an ever-increasing role in geoscience.Sphisicated database platforms are essential for geological data storage,analysis and exchange of Big Data(Feblowitz,2013;Zhang et al.,2016;Teng et al.,2016;Tian and Li,2018).The United States has built an information-sharing platform for state-owned scientific data as a national strategy.展开更多
In the new era of earth system science in conjunction with the digital revolution,new platforms and programs are required for facilitating the utilization of geoscience data,especially to improve the integration of st...In the new era of earth system science in conjunction with the digital revolution,new platforms and programs are required for facilitating the utilization of geoscience data,especially to improve the integration of structured data with unstructured data for solving complex problems.Big data is not just matter of size but most importantly how easily and effectively it can be used.A major goal is to facilitate a move from traditional scientific approaches to a more modern approach that involves big data analytics.展开更多
1 Introduction Sedimentary rocks archive important information for understanding how the earth system operates and how life and environments have evolved through earth history.Properly identifying characteristics of s...1 Introduction Sedimentary rocks archive important information for understanding how the earth system operates and how life and environments have evolved through earth history.Properly identifying characteristics of sedimentary rocks,along with the subsequent interpretation of depositional processes and sedimentary environments in a basin or locality.展开更多
Groundwater is an important water resource.The total amount of active groundwater in a hydrological cycle is about 3.5 times that of the total amount of surface water.The information in the deep groundwater records th...Groundwater is an important water resource.The total amount of active groundwater in a hydrological cycle is about 3.5 times that of the total amount of surface water.The information in the deep groundwater records the material exchange and dynamics in the earth’s evolution,which is an important aspect of the Deep-Time Digital Earth(DDE)plan.In recent years,scientists have discussed the distribution of transboundary aquifers and the environmental significance of groundwater resources through groundwater databases established by international organizations,such as the Global Groundwater Information System and the chronicles consortium,and national institutes,such as national geological surveys.The application of the groundwater database in the DDE plan,however,has been limited by the management,interactivity,and monitoring method of the groundwater data.The ability to further integrate data that are private and scattered across research institutions and individuals,while establishing an open,unified,and shared groundwater data platform,is essential to enhance our understanding of groundwater,ranging from shallow to deep water,which is a goal of the DDE plan.In this study,we introduced the current situation of groundwater database operations in domestic and international research and provided frontier research with groundwater big data.Considering the related objectives of the DDE plan and the limitations of existing groundwater databases,we proposed an improvement plan and new prospects for applying groundwater databases in the research of the deep earth.展开更多
Paleogeography is a discipline that studies spatial distribution and evolutionary characteristics of geographic objects in earth history(Feng,2003;Feng et al.,2012).It focuses on the sediments,organisms and environmen...Paleogeography is a discipline that studies spatial distribution and evolutionary characteristics of geographic objects in earth history(Feng,2003;Feng et al.,2012).It focuses on the sediments,organisms and environmental proxies,most of which are preserved in the rocks.However,a large amount of this geological and biological information was no longer preserved after the geological process of burial.展开更多
短期预测在智能电网建设中扮演着重要角色,深刻影响电网发输变配用各个环节的智能化改造。短期预测一般基于系统实测数据,而传感器故障,数据传输错误等原因会导致数据质量下降,严重影响短期预测的精确性。为建立数据质量受损情况下的精...短期预测在智能电网建设中扮演着重要角色,深刻影响电网发输变配用各个环节的智能化改造。短期预测一般基于系统实测数据,而传感器故障,数据传输错误等原因会导致数据质量下降,严重影响短期预测的精确性。为建立数据质量受损情况下的精确短期预测模型,提出了结合数据预处理和双向长短期记忆(bi-directional long short-term memory,Bi-LSTM)的短期预测框架Bi-LSTM-DP(bi-directional long short-term memory data preprocessing)。在Bi-LSTM-DP中,采集的数据首先通过均值填补缺失值,进而基于Savitzky-Golay滤波器对数据降噪,最后采用Bi-LSTM提取时间序列的信息,实现短期预测。为了评估所提方法的性能,文中使用实测的公开数据集分别预测风电发电量和负荷需求,与其他参考方法对比表明了所述方法的有效性和鲁棒性。展开更多
传统时序预测模型通常仅关注捕捉复杂时序中的趋势和模式,而忽略了变量间的相互作用,限制了该模型在复杂时序预测中应用.提出一种Dualformer双模型并联方案,该模型并联iTransformer(inverted transformer)和PatchTST(patch time series ...传统时序预测模型通常仅关注捕捉复杂时序中的趋势和模式,而忽略了变量间的相互作用,限制了该模型在复杂时序预测中应用.提出一种Dualformer双模型并联方案,该模型并联iTransformer(inverted transformer)和PatchTST(patch time series transformer),通过激活函数替代前馈神经网络,并通过多层感知机计算输出结果.Dualformer利用注意力机制同时捕捉复杂时序中的时间维度和变量维度信息,关注时间趋势与多变量交互.实验结果显示,Dualformer在复杂时序预测效果上显著优于对比模型iTransformer、PatchTST和DLinear(decomposition linear),在实际应用中可显著提高复杂时序预测的准确度,具有广泛应用前景.展开更多
基金Strategic Priority Research Program of the Chinese Academy of Sciences,No.XDB0740000National Key Research and Development Program of China,No.2022YFB3904200,No.2022YFF0711601+1 种基金Key Project of Innovation LREIS,No.PI009National Natural Science Foundation of China,No.42471503。
文摘Deep-time Earth research plays a pivotal role in deciphering the rates,patterns,and mechanisms of Earth's evolutionary processes throughout geological history,providing essential scientific foundations for climate prediction,natural resource exploration,and sustainable planetary stewardship.To advance Deep-time Earth research in the era of big data and artificial intelligence,the International Union of Geological Sciences initiated the“Deeptime Digital Earth International Big Science Program”(DDE)in 2019.At the core of this ambitious program lies the development of geoscience knowledge graphs,serving as a transformative knowledge infrastructure that enables the integration,sharing,mining,and analysis of heterogeneous geoscience big data.The DDE knowledge graph initiative has made significant strides in three critical dimensions:(1)establishing a unified knowledge structure across geoscience disciplines that ensures consistent representation of geological entities and their interrelationships through standardized ontologies and semantic frameworks;(2)developing a robust and scalable software infrastructure capable of supporting both expert-driven and machine-assisted knowledge engineering for large-scale graph construction and management;(3)implementing a comprehensive three-tiered architecture encompassing basic,discipline-specific,and application-oriented knowledge graphs,spanning approximately 20 geoscience disciplines.Through its open knowledge framework and international collaborative network,this initiative has fostered multinational research collaborations,establishing a robust foundation for next-generation geoscience research while propelling the discipline toward FAIR(Findable,Accessible,Interoperable,Reusable)data practices in deep-time Earth systems research.
基金supported by the National Natural Science Foundation of China(No.42050103)。
文摘Continental crust is the long-term achievements of Earth's evolution across billions of years.The continental rocks could have been modified by various types of geological processes,such as metamorphism,weathering,and reworking.Therefore,physical or chemical properties of rocks through time record the composite effects of geological,biological,hydrological,and climatological processes.Temporal variations in these time series datasets could provide important clues for understanding the co-evolution of different layers on Earth.However,deciphering Earth's evolution in deep time is challenged by incompleteness,singularity,and intermittence of geological records associated with extreme geological events,hindering a rigorous assessment of the underlying coupling mechanisms.Here,we applied the recently developed local singularity analysis and wavelet analysis method to deep-time U-Pb age spectra and sedimentary abundance record across the past 3.5 Gyrs.Standard cross-correlation analysis suggests that the singularity records of marine sediment accumulations and magmatism intensity at continental margin are correlated negatively(R^(2)=0.8),with a delay of~100 Myr.Specifically,wavelet coherence analysis suggests a~500-800 Myr cycle of correlation between two records,implying a coupling between the major downward processes(subduction and recycling sediments)and upward processes(magmatic events)related to the aggregation and segregation of supercontinents.The results clearly reveal the long-term cyclic feedback mechanism between sediment accumulation and magmatism intensity through aggregation of supercontinents.
基金granted by the National Science&Technology Major Projects of China(Grant No.2016ZX05033).
文摘1 Introduction Information technology has been playing an ever-increasing role in geoscience.Sphisicated database platforms are essential for geological data storage,analysis and exchange of Big Data(Feblowitz,2013;Zhang et al.,2016;Teng et al.,2016;Tian and Li,2018).The United States has built an information-sharing platform for state-owned scientific data as a national strategy.
文摘In the new era of earth system science in conjunction with the digital revolution,new platforms and programs are required for facilitating the utilization of geoscience data,especially to improve the integration of structured data with unstructured data for solving complex problems.Big data is not just matter of size but most importantly how easily and effectively it can be used.A major goal is to facilitate a move from traditional scientific approaches to a more modern approach that involves big data analytics.
文摘1 Introduction Sedimentary rocks archive important information for understanding how the earth system operates and how life and environments have evolved through earth history.Properly identifying characteristics of sedimentary rocks,along with the subsequent interpretation of depositional processes and sedimentary environments in a basin or locality.
基金supported by the National Natural Science Foundation of China No.41630318Deep-Time Digital Earth(DDE)Plan and Hydrology Team of DDE plan in China University of Geosciences,Wuhan。
文摘Groundwater is an important water resource.The total amount of active groundwater in a hydrological cycle is about 3.5 times that of the total amount of surface water.The information in the deep groundwater records the material exchange and dynamics in the earth’s evolution,which is an important aspect of the Deep-Time Digital Earth(DDE)plan.In recent years,scientists have discussed the distribution of transboundary aquifers and the environmental significance of groundwater resources through groundwater databases established by international organizations,such as the Global Groundwater Information System and the chronicles consortium,and national institutes,such as national geological surveys.The application of the groundwater database in the DDE plan,however,has been limited by the management,interactivity,and monitoring method of the groundwater data.The ability to further integrate data that are private and scattered across research institutions and individuals,while establishing an open,unified,and shared groundwater data platform,is essential to enhance our understanding of groundwater,ranging from shallow to deep water,which is a goal of the DDE plan.In this study,we introduced the current situation of groundwater database operations in domestic and international research and provided frontier research with groundwater big data.Considering the related objectives of the DDE plan and the limitations of existing groundwater databases,we proposed an improvement plan and new prospects for applying groundwater databases in the research of the deep earth.
基金granted by the National Science and Technology Major Project of China(Grant No.2017ZX05035002-001)the National Natural Science Foundation of China(Grant Nos.41802017 and 41725007)+1 种基金the Strategic Priority Research Program of Chinese Academy of Sciences(Grant No.XDB26000000)the State Key Laboratory of Palaeobiology and Stratigraphy(Grant No.20172112).
文摘Paleogeography is a discipline that studies spatial distribution and evolutionary characteristics of geographic objects in earth history(Feng,2003;Feng et al.,2012).It focuses on the sediments,organisms and environmental proxies,most of which are preserved in the rocks.However,a large amount of this geological and biological information was no longer preserved after the geological process of burial.
文摘短期预测在智能电网建设中扮演着重要角色,深刻影响电网发输变配用各个环节的智能化改造。短期预测一般基于系统实测数据,而传感器故障,数据传输错误等原因会导致数据质量下降,严重影响短期预测的精确性。为建立数据质量受损情况下的精确短期预测模型,提出了结合数据预处理和双向长短期记忆(bi-directional long short-term memory,Bi-LSTM)的短期预测框架Bi-LSTM-DP(bi-directional long short-term memory data preprocessing)。在Bi-LSTM-DP中,采集的数据首先通过均值填补缺失值,进而基于Savitzky-Golay滤波器对数据降噪,最后采用Bi-LSTM提取时间序列的信息,实现短期预测。为了评估所提方法的性能,文中使用实测的公开数据集分别预测风电发电量和负荷需求,与其他参考方法对比表明了所述方法的有效性和鲁棒性。
文摘传统时序预测模型通常仅关注捕捉复杂时序中的趋势和模式,而忽略了变量间的相互作用,限制了该模型在复杂时序预测中应用.提出一种Dualformer双模型并联方案,该模型并联iTransformer(inverted transformer)和PatchTST(patch time series transformer),通过激活函数替代前馈神经网络,并通过多层感知机计算输出结果.Dualformer利用注意力机制同时捕捉复杂时序中的时间维度和变量维度信息,关注时间趋势与多变量交互.实验结果显示,Dualformer在复杂时序预测效果上显著优于对比模型iTransformer、PatchTST和DLinear(decomposition linear),在实际应用中可显著提高复杂时序预测的准确度,具有广泛应用前景.
