基于GraphSAGE网络的藏文短文本分类研究

文本分类是自然语言处理领域的重要研究方向,由于藏文数据的稀缺性、语言学特征抽取的复杂性、篇章结构的多样性等因素导致藏文文本分类任务进展缓慢。因此,该文以图神经作为基础模型进行改进。首先,在“音节-音节”“音节-文档”建模的基础上,融合文档特征,采用二元分类模型动态网络构建“文档-文档”边,以充分挖掘短文本的全局特征,增加滑动窗口,减少模型的计算复杂度并寻找最优窗口取值。其次,针对藏文短文本的音节稀疏性,首次引入GraphSAGE作为基础模型,并探究不同聚合方式在藏文短文本分类上的性能差异。最后,为捕获节点间关系的异质性,对邻居节点进行特征加权再平均池化以增强模型的特征提取能力。在TNCC标题文本数据集上,该文模型的分类准确率达到了62.50%,与传统GCN、原始GraphSAGE和预训练语言模型CINO相比,该方法在分类准确率上分别提高了2.56%、1%和2.4%。

Carbon Storage Dynamics in Lower Shimentan Formation of the Qiantang Sag, East China Sea Shelf Basin: Stratigraphy, Reservoir ‒ Cap Analysis, and Source ‒ Sink Compatibility

Excessive carbon emissions have resulted in the greenhouse effect, causing considerable global climate change. Marine carbon storage has emerged as a crucial approach to addressing climate change. The Qiantang Sag(QTS) in the East China Sea Shelf Basin, characterized by its extensive area, thick sedimentary strata, and optimal depth, presents distinct geological advantages for carbon dioxide(CO_(2)) storage. Focusing on the lower section of the Shimentan Formation in the Upper Cretaceous of the QTS, this study integrates seismic interpretation and drilling data with core and thin-section analysis. We reveal the vertical variation characteristics of the strata by providing a detailed stratigraphic description. We use petrophysical data to reveal the development characteristics of high-quality carbon-storage layers and favorable reservoircaprock combinations, thereby evaluating the geological conditions for CO_(2) storage in various stratigraphic sections. We identify Layer B of the lower Shimentan Formation as the most advantageous stratum for marine CO_(2) storage. Furthermore, we analyze the carbon emission trends in the adjacent Yangtze River Delta region. Considering the characteristics of the source and sink areas, we suggest a strong correlation between the carbon emission sources of the Yangtze River Delta and the CO_(2) storage area of the QTS, making the latter a priority area for conducting experiments on marine CO_(2) storage.

DIGNN-A:Real-Time Network Intrusion Detection with Integrated Neural Networks Based on Dynamic Graph

The increasing popularity of the Internet and the widespread use of information technology have led to a rise in the number and sophistication of network attacks and security threats.Intrusion detection systems are crucial to network security,playing a pivotal role in safeguarding networks from potential threats.However,in the context of an evolving landscape of sophisticated and elusive attacks,existing intrusion detection methodologies often overlook critical aspects such as changes in network topology over time and interactions between hosts.To address these issues,this paper proposes a real-time network intrusion detection method based on graph neural networks.The proposedmethod leverages the advantages of graph neural networks and employs a straightforward graph construction method to represent network traffic as dynamic graph-structured data.Additionally,a graph convolution operation with a multi-head attention mechanism is utilized to enhance the model’s ability to capture the intricate relationships within the graph structure comprehensively.Furthermore,it uses an integrated graph neural network to address dynamic graphs’structural and topological changes at different time points and the challenges of edge embedding in intrusion detection data.The edge classification problem is effectively transformed into node classification by employing a line graph data representation,which facilitates fine-grained intrusion detection tasks on dynamic graph node feature representations.The efficacy of the proposed method is evaluated using two commonly used intrusion detection datasets,UNSW-NB15 and NF-ToN-IoT-v2,and results are compared with previous studies in this field.The experimental results demonstrate that our proposed method achieves 99.3%and 99.96%accuracy on the two datasets,respectively,and outperforms the benchmark model in several evaluation metrics.

Occluded Gait Emotion Recognition Based on Multi-Scale Suppression Graph Convolutional Network

In recent years,gait-based emotion recognition has been widely applied in the field of computer vision.However,existing gait emotion recognition methods typically rely on complete human skeleton data,and their accuracy significantly declines when the data is occluded.To enhance the accuracy of gait emotion recognition under occlusion,this paper proposes a Multi-scale Suppression Graph ConvolutionalNetwork(MS-GCN).TheMS-GCN consists of three main components:Joint Interpolation Module(JI Moudle),Multi-scale Temporal Convolution Network(MS-TCN),and Suppression Graph Convolutional Network(SGCN).The JI Module completes the spatially occluded skeletal joints using the(K-Nearest Neighbors)KNN interpolation method.The MS-TCN employs convolutional kernels of various sizes to comprehensively capture the emotional information embedded in the gait,compensating for the temporal occlusion of gait information.The SGCN extracts more non-prominent human gait features by suppressing the extraction of key body part features,thereby reducing the negative impact of occlusion on emotion recognition results.The proposed method is evaluated on two comprehensive datasets:Emotion-Gait,containing 4227 real gaits from sources like BML,ICT-Pollick,and ELMD,and 1000 synthetic gaits generated using STEP-Gen technology,and ELMB,consisting of 3924 gaits,with 1835 labeled with emotions such as“Happy,”“Sad,”“Angry,”and“Neutral.”On the standard datasets Emotion-Gait and ELMB,the proposed method achieved accuracies of 0.900 and 0.896,respectively,attaining performance comparable to other state-ofthe-artmethods.Furthermore,on occlusion datasets,the proposedmethod significantly mitigates the performance degradation caused by occlusion compared to other methods,the accuracy is significantly higher than that of other methods.

基于改进GraphSAGE算法的浏览器指纹追踪

当前Web追踪领域主要使用浏览器指纹对用户进行追踪。针对浏览器指纹追踪技术存在指纹随时间动态变化、不易长期追踪等问题,提出一种关注节点和边缘特征的改进图采样聚合算法(An Improved Graph SAmple and AGgregatE with Both Node and Edge Features,NE-GraphSAGE)用于浏览器指纹追踪。首先以浏览器指纹为节点、指纹之间特征相似度为边构建图数据。其次对图神经网络中的GraphSAGE算法进行改进使其不仅能关注节点特征,而且能捕获边缘信息并对边缘分类,从而识别指纹。最后将NE-GraphSAGE算法与Eckersley算法、FPStalker算法和LSTM算法进行对比,验证NE-GraphSAGE算法的识别效果。实验结果表明,NE-GraphSAGE算法在准确率和追踪时长上均有不同程度的提升,最大追踪时长可达80天,相比其他3种算法性能更优,验证了NE-GraphSAGE算法对浏览器指纹长期追踪的能力。

服务器机箱底座下沉量Sag仿真与测试研究

文章采用Abaqus仿真与批量测试的方法,对服务器机箱底座的下沉量进行深入研究分析。以2U通用机架服务器为例展开分析,通过进行仿真与实测对比,证明了仿真精度足够且演练了满载sag到空载sag的分析和管控过程。该研究提出了全新的空载sag管控理论,并根据满载建议值反推空载建议值,再由仿真计算出空满载差值,该方法有效提升了工厂端的sag管控,对服务器机箱的sag设计和生产有重要指导意义。

基于GraphSage节点度重要性聚合的网络节点分类研究

传统的图嵌入算法及图神经网络模型在对网络节点分类时仅使用了节点本身的属性信息或者特征信息,很少使用节点在网络中的结构信息。如何在图神经网络聚合时引入节点网络结构信息来提升分类准确性也是一个值得深入研究的问题。因此,在GraphSage模型的基础上,根据网络中节点度及节点重要性设计了新的聚合函数并提出了GraphSage-Degree模型。首先,模型根据节点度获得节点在邻域中的重要性,然后再以重要性为依据来聚合节点的特征,使得网络中重要的节点能够尽可能的聚合更多的特征信息,并且在GraphSage-Degree中设置了一个与节点度有关的超参数D,能够通过调节该参数D使得在不同的数据集上达到最佳分类状态。在Cora、Citeseer和Pubmed 3个公开数据集上进行了测试,GraphSage-Degree与其他方法相比,macro-F1的平均提升值分别为8.72%、10.37%和8.29%,在Pubmed上有最大提升值38.84%;micro-F1的平均提升值分别为8.97%、11.16%和6.9%,在Pubmed上有最大提升值38.39%。

Organic Geochemical and Petrographic Characteristics of the Coal Measure Source Rocks of Pinghu Formation in the Xihu Sag of the East China Sea Shelf Basin: Implications for Coal Measure Gas Potential

Coal measure source rocks, located in the Xihu Sag of the East China Sea Shelf Basin, were analyzed to define the hydrocarbon generation potential, organic geochemistry/petrology characteristics, and coal preservation conditions. The Pinghu source rocks in the Xihu Sag are mainly gas-prone accompany with condensate oil generation. The coals and shales of the Pinghu Formation are classified from "fair" to "excellent" source rocks with total organic carbon(TOC) contents ranging from 25.2% to 77.2% and 1.29% to 20.9%, respectively. The coals are richer in TOC and S1+S2 than the shales, indicating that the coals have more generation potential per unit mass. Moreover, the kerogen type of the organic matter consists of types Ⅱ-Ⅲ and Ⅲ, which the maturity Ro ranges from 0.59% to 0.83%. Petrographically, the coals and shales are dominated by vitrinite macerals(69.1%–96.8%) with minor proportions of liptinite(2.5%–17.55%) and inertinite(0.2%–6.2%). The correlation between maceral composition and S1+S2 indicates that the main contributor to the generation potential is vitrinite. Therefore, the coals and shales of the Pinghu Formation has good hydrocarbon generation potential, which provided a good foundation for coal measure gas accumulation. Furthermore, coal facies models indicates that the Pinghu coal was deposited in limno-telmatic environment under high water levels, with low tree density(mainly herbaceous) and with low-moderate nutrient supply. Fluctuating water levels and intermittent flooding during the deposition of peat resulted in the inter-layering of coal, shale and sandstone, which potentially providing favorable preservation conditions for coal measure gas.

Graph Transformers研究进展综述

随着图结构数据在各种实际场景中的广泛应用,对其进行有效建模和处理的需求日益增加。Graph Transformers(GTs)作为一类使用Transformers处理图数据的模型,能够有效缓解传统图神经网络(GNN)中存在的过平滑和过挤压等问题,因此可以学习到更好的特征表示。根据对近年来GTs相关文献的研究,将现有的模型架构分为两类:第一类通过绝对编码和相对编码向Transformers中加入图的位置和结构信息,以增强Transformers对图结构数据的理解和处理能力;第二类根据不同的方式(串行、交替、并行)将GNN与Transformers进行结合,以充分利用两者的优势。介绍了GTs在信息安全、药物发现和知识图谱等领域的应用,对比总结了不同用途的模型及其优缺点。最后,从可扩展性、复杂图、更好的结合方式等方面分析了GTs未来研究面临的挑战。

Evaluation of reservoir connectivity using whole-oil gas chromatographic fingerprint technology: A case study from the Es_3~3 reservoir in the Nanpu Sag, China

In this study, whole-oil gas chromatographic fingerprint analyses were performed on oils from the Es3^3 reservoir in the Liubei area of the Nanpu Sag. The gas chromatographic peaks of cyclic and branched alkanes with relatively high resolution from nCl0 to nC25 were selected to establish a database of whole-oil gas chromatographic peak height ratio fingerprints. Reservoir fluid connectivity was identified by using clustering analysis. This method can reflect the gas chromatography fingerprint information accurately and entirely, and avoid the one-sidedness of the star diagram method which only selects several fixed gas chromatographic peaks.

Defining stratigraphic oil and gas plays by modifying structural plays:A case study from the Xihu Sag,east China Sea Shelf Basin

The study focuses on an area of relatively mature oil and gas exploration located in the western slope of the Xihu Sag,East China Sea Shelf Basin.Three stratigraphic oil and gas plays are introduced to replenish the shrinking prospect inventory in the area.The reservoirs of these plays are traditional pay intervals of the Eocene Pinghu Formation and Baoshi Formation composed of tide-dominated delta front,tidal flat and delta front sand bar facies.By investigating conventional seismic data,seismic inversion volumes,and well log data,multiple tidal-influenced delta front channels,beach sand packages have been mapped out in different reservoir sand intervals of the Pinghu Formation and Baoshi Formation.We recognize four types of stratigraphic terminations:channel flank pinch-outs,axial pinch-outs of sand-fills,channel mouth sand bar pinch-outs,and onlap pinch-outs for the Baoshi Formation.Both the depositional facies and relatively low sand-shale ratio of the reservoir formations favor the occurrence of stratigraphic terminations.The closure mechanism of all these plays are similar to the traditional structure plays in the area:fault blocks or fault-bounded rollover anticlines,except that one or more closing faults are replaced by these stratigraphic terminations.Several small-sized closures should exist but the relatively large ones are centered around a major intra-slope rise,raising the exploration potential in this maturely explored area.The new exploration drilling campaign has so far tested the play of delta front channel facies,with three out of four wells commercially successful.These play concepts open up a novel approach to identify new traps in the study area and many other rift basins with similar settings in eastern China.

基于改进SAGGAN模型的齿轮故障分类方法研究

针对齿轮故障样本获取困难,导致深度学习驱动故障分类模型的可靠性和准确性不足这一问题,提出了一种基于改进自注意力门单元生成对抗网络(SAGGAN)的半监督齿轮故障分类模型。首先,为增强改进SAGGAN模型的特征表示能力,提升齿轮故障的半监督分类效果,在自注意力生成对抗网络(SAGAN)的基础上,引入了门控通道转换模块(GCT)、改进自注意力门控模块(SAG)和预训练的Inception V3分支;然后,使用齿轮故障实验装置采集齿轮断齿、磨损、周节误差和正常四种状态下的振动信号,并将数据划分为训练集、验证集与测试集;最后,将计算结果与现有的半监督分类方法:TripleGAN、Bad-GAN、Reg-GAN、SF-GAN进行了对比,并对改进模块进行了消融实验研究。研究结果表明:在标签样本为40、60、80、100时,改进SAGGAN模型的整体分类准确率分别为89%、90%、92%、94.25%,远高于其他四种方法,特别在只有少量标签样本情况下的优越性更为明显。以上结果揭示了改进的SAGGAN模型在齿轮故障分类领域中的实用性和优越性。

基于Graph Transformer的半监督异配图表示学习模型

现有的图卷积网络(GCN)模型基于同配性假设,无法直接应用于异配图的表示学习,且许多异配图表示学习的研究工作受消息传递机制的限制,导致节点特征混淆和特征过度挤压而出现过平滑问题。针对这些问题,提出一种基于Graph Transformer的半监督异配图表示学习模型HPGT(HeteroPhilic Graph Transformer)。首先,使用度连接概率矩阵采样节点的路径邻域,再通过自注意力机制自适应地聚合路径上的节点异配连接模式,编码得到节点的结构信息,用节点的原始属性信息和结构信息构建Transformer层的自注意力模块;其次,将每个节点自身的隐层表示与它的邻域节点的隐层表示分离更新以避免节点通过自注意力模块聚合过量的自身信息,再把每个节点表示与它的邻域表示连接,得到单个Transformer层的输出,另外,将所有的Transformer层的输出跳连到最终的节点隐层表示以防止中间层信息丢失;最后,使用线性层和Softmax层将节点的隐层表示映射到节点的预测标签。实验结果表明,与无结构编码(SE)的模型相比,基于度连接概率的SE能为Transformer层的自注意力模块提供有效的偏差信息,HPGT平均准确率提升0.99%~11.98%;与对比模型相比,在异配数据集(Texas、Cornell、Wisconsin和Actor)上,模型节点分类准确率提升0.21%~1.69%,在同配数据集(Cora、CiteSeer和PubMed)上,节点分类准确率分别达到了0.8379、0.7467和0.8862。以上结果验证了HPGT具有较强的异配图表示学习能力,尤其适用于强异配图节点分类任务。

Geochemical identification of a source rock affected by migrated hydrocarbons and its geological significance:Fengcheng Formation,southern Mahu Sag,Junggar Basin,NW China

The Fengcheng Formation is a crucial source rock and the primary reservoir for oil accumulation in the Mahu Sag.Crude oils are distributed throughout the Fengcheng Formation,ranging from the edge to the interior of the sag in the southern Mahu Sag.These crude oils originate from in-situ source rocks in shallowly buried areas and the inner deep sag.During migration,the crude oil from the inner deep sag affects the source rocks close to carrier beds,leading to changes in the organic geochemical characteristics of the source rocks.These changes might alter source rock evaluations and oil-source correlation.Based on data such as total organic carbon(TOC),Rock-Eval pyrolysis of source rocks,and gas chromatography-mass spectrometry(GC-MS)of the saturated fraction,and considering the geological characteristics of the study area,we define the identification characteristics of source rock affected by migrated hydrocarbons and establish the various patterns of influence that migrated hydrocarbons have on the source rock of the Fengcheng Formation in the southern Mahu Sag.The source rocks of the Fengcheng Formation are mostly fair to good,containing mainly Type II organic matter and being thermally mature enough to generate oil.Source rocks affected by migrated hydrocarbons exhibit relatively high hydrocarbon contents(S1/TOC>110 mg HC/g TOC,Extract/TOC>30%,HC:hydrocarbon),relatively low Rock-Eval Tmax values,and relatively high tricyclic terpane contents with a descending and mountain-shaped distribution.Furthermore,biomarker composition parameters indicate a higher thermal maturity than in-situ source rocks.Through a comparison of the extract biomarker fingerprints of adjacent reservoirs and mudstones in different boreholes,three types of influence patterns of migrated hydrocarbons are identified:the edge-influence of thin sandstone-thick mudstone,the mixed-influence of sandstone-mudstone interbedded,and the full-influence of thick sandstone-thin mudstone.This finding reminds us that the influence of migrated hydrocarbons must be considered when evaluating source rocks and conducting oil-source correlation.

Multiple enrichment mechanisms of organic matter in the Fengcheng Formation of Mahu Sag,Junggar Basin,NW China

Based on core and thin section data,the source rock samples from the Fengcheng Formation in the Mahu Sag of the Junggar Basin were analyzed in terms of zircon SIMS U-Pb geochronology,organic carbon isotopic composition,major and trace element contents,as well as petrology.Two zircon U-Pb ages of(306.0±5.2)Ma and(303.5±3.7)Ma were obtained from the first member of the Fengcheng Formation.Combined with carbon isotopic stratigraphy,it is inferred that the depositional age of the Fengcheng Formation is about 297-306 Ma,spanning the Carboniferous-Permian boundary and corresponding to the interglacial period between C4 and P1 glacial events.Multiple increases in Hg/TOC ratios and altered volcanic ash were found in the shale rocks of the Fengcheng Formation,indicating that multiple phases of volcanic activity occurred during its deposition.An interval with a high B/Ga ratio was found in the middle of the second member of the Fengcheng Formation,associated with the occurrence of evaporite minerals and reedmergnerite,indicating that the high salinity of the water mass was related to hydrothermal activity.Comprehensive analysis suggests that the warm and humid climate during the deposition of Fengcheng Formation is conducive to the growth of organic matter such as algae and bacteria in the lake,and accelerates the continental weathering,driving the input of nutrients.Volcanic activities supply a large amount of nutrients and stimulate primary productivity.The warm climate and high salinity are conducive to water stratification,leading to water anoxia that benefits organic matter preservation.The above factors interact and jointly control the enrichment of organic matter in the Fengcheng Formation of Mahu Sag.

Paleoenvironmental Characteristics of Paleogene Lacustrine Source Rocks in the Western Bozhong Sag,Bohai Bay Basin,China:Evidence from Biomarkers,Major and Trace Elements

The organic matter(OM)enrichment mechanisms and depositional environment characteristics of lacustrine source rocks in the western Bozhong Sag,Bohai Bay Basin in Northeast China remain controversial.To address these issues,based on Rock-Eval pyrolysis,kerogen macerals,H/C and O/C ratios,GC-MS,major and trace elements,the Dongying Formation Member(Mbr)3(E_(3)d_(3)),the Shahejie Formation mbrs 1 and 2(E_(2)s_(1+2)),and the Shahejie Mbr 3(E_(2)s_(3))source rocks in the western Bozhong Sag were studied.The above methods were used to reveal their geochemical properties,OM origins and depositional environments,all of which indicate that E_(2)s_(1+2)and E_(2)s_(3)are excellent source rocks,and that E_(3)d_(3)is of the second good quality.E_(3)d_(3)source rocks were formed under a warm and humid climate,mainly belong to fluvial/delta facies,the E_(3)d_(3)sediments formed under weakly oxidizing and freshwater conditions.Comparatively,the depositional environments of E_(2)s_(1+2)source rocks were arid and cold climate,representing saline or freshwater lacustrine facies,and the sediments of E_(2)s_(1+2)belong to anoxic or suboxic settings with large evaporation and salinity.During the period of E_(2)s_(3),the climate became warm and humid,indicating the freshwater lacustrine facies,and E_(2)s_(3)was characterized by freshwater and abundant algae.Moreover,compared with other intervals,the OM origin of E_(3)d_(3)source rocks has noticeable terrestrial input.The OM origin of the E_(2)s_(1+2)and E_(2)s_(3)are mainly plankton and bacteria.Tectonic subsidence and climate change have affected the changes of the depositional environment in the western Bozhong Sag,thus controlling the distribution of the source rocks,the geochemical characteristics in the three intervals of lacustrine source rocks have distinct differences.Overall,these factors are effective to evaluate the paleoenvironmental characteristics of source rocks by biomarkers,major and trace elements.The established models may have positive implications for research of lacustrine source rocks in offshore areas with few drillings.

Discovery and petroleum geological significance of delta in the third member of Oligocene Lingshui Formation in southern Baodao Sag,Qiongdongnan Basin,South China Sea

Based on the 3D seismic data and the analysis and test data of lithology,electricity,thin sections and chronology obtained from drilling of the Qiongdongnan Basin,the characteristics and the quantitative analysis of the source-sink system are studied of the third member of the Upper Oligocene Lingshui Formation(Ling 3 Member)in the southern fault step zone of the Baodao Sag.First,the YL10 denudation area of the Ling 3 Member mainly developed two fluvial systems in the east and west,resulting in the formation of two dominant sand transport channels and two delta lobes in southern Baodao Sag,which are generally large in the west and small in the east.The evolution of the delta has experienced four stages:initiation,prosperity,intermittence and rejuvenation.Second,the source-sink coupled quantitative calculation is performed depending on the parameters of the delta sand bodies,including development phases,distribution area,flattening thickness,area of different parent rocks,and sand-forming coefficient,showing that the study area has the material basis for the formation of large-scale reservoir.Third,the drilling reveals that the delta of the Ling 3 Member is dominated by fine sandstone,with total sandstone thickness of 109-138 m,maximum single-layer sandstone thickness of 15.5-30.0 m,and sand-to-strata ratio of 43.7%-73.0%,but the physical properties are different among the fault steps.Fourth,the large delta development model of the small source area in the step fault zone with multi-stage uplift is established.It suggests that the episodic uplift provides sufficient sediments,the fluvial system and watershed area control the scale of the sand body,the multi-step active fault steps dominate the sand body transport channel,and local fault troughs decide the lateral propulsion direction of the sand body.The delta of the Ling 3 Member is coupled with fault blocks to form diverse traps,which are critical exploration targets in southern Baodao Sag.

Discovery and inspiration of large-and medium-sized glutenite-rich oil and gas fields in the eastern South China Sea:An example from Paleogene Enping Formation in Huizhou 26 subsag,Pearl River Mouth Basin

Based on the practice of oil and gas exploration in the Huizhou Sag of the Pearl River Mouth Basin,the geochemical indexes of source rocks were measured,the reservoir development morphology was restored,the rocks and minerals were characterized microscopically,the measured trap sealing indexes were compared,the biomarker compounds of crude oil were extracted,the genesis of condensate gas was identified,and the reservoir-forming conditions were examined.On this basis,the Paleogene Enping Formation in the Huizhou 26 subsag was systematically analyzed for the potential of oil and gas resources,the development characteristics of large-scale high-quality conglomerate reservoirs,the trapping effectiveness of faults,the hydrocarbon migration and accumulation model,and the formation conditions and exploration targets of large-and medium-sized glutenite-rich oil and gas fields.The research results were obtained in four aspects.First,the Paleogene Wenchang Formation in the Huizhou 26 subsag develops extensive and thick high-quality source rocks of semi-deep to deep lacustrine subfacies,which have typical hydrocarbon expulsion characteristics of"great oil generation in the early stage and huge gas expulsion in the late stage",providing a sufficient material basis for hydrocarbon accumulation in the Enping Formation.Second,under the joint control of the steep slope zone and transition zone of the fault within the sag,the large-scale near-source glutenite reservoirs are highly heterogeneous,with the development scale dominated hierarchically by three factors(favorable facies zone,particle component,and microfracture).The(subaqueous)distributary channels near the fault system,with equal grains,a low mud content(<5%),and a high content of feldspar composition,are conducive to the development of sweet spot reservoirs.Third,the strike-slip pressurization trap covered by stable lake flooding mudstone is a necessary condition for oil and gas preservation,and the NE and nearly EW faults obliquely to the principal stress have the best control on traps.Fourth,the spatiotemporal configuration of high-quality source rocks,fault transport/sealing,and glutenite reservoirs controls the degree of hydrocarbon enrichment.From top to bottom,three hydrocarbon accumulation units,i.e.low-fill zone,transition zone,and high-fill zone,are recognized.The main area of the channel in the nearly pressurized source-connecting fault zone is favorable for large-scale hydrocarbon enrichment.The research results suggest a new direction for the exploration of large-scale glutenite-rich reservoirs in the Enping Formation of the Pearl River Mouth Basin,and present a major breakthrough in oil and gas exploration.

Graph neural network-based scheduling for multi-UAV-enabled communications in D2D networks

In this paper,we jointly design the power control and position dispatch for Multi-Unmanned Aerial Vehicle(UAV)-enabled communication in Device-to-Device(D2D)networks.Our objective is to maximize the total transmission rate of Downlink Users(DUs).Meanwhile,the Quality of Service(QoS)of all D2D users must be satisfied.We comprehensively considered the interference among D2D communications and downlink transmissions.The original problem is strongly non-convex,which requires high computational complexity for traditional optimization methods.And to make matters worse,the results are not necessarily globally optimal.In this paper,we propose a novel Graph Neural Networks(GNN)based approach that can map the considered system into a specific graph structure and achieve the optimal solution in a low complexity manner.Particularly,we first construct a GNN-based model for the proposed network,in which the transmission links and interference links are formulated as vertexes and edges,respectively.Then,by taking the channel state information and the coordinates of ground users as the inputs,as well as the location of UAVs and the transmission power of all transmitters as outputs,we obtain the mapping from inputs to outputs through training the parameters of GNN.Simulation results verified that the way to maximize the total transmission rate of DUs can be extracted effectively via the training on samples.Moreover,it also shows that the performance of proposed GNN-based method is better than that of traditional means.

Petroleum geological characteristics and exploration targets of the oil-rich sags in the Central and West African Rift System

Based on seismic,drilling,and source rock analysis data,the petroleum geological characteristics and future exploration direction of the oil-rich sags in the Central and West African Rift System(CWARS)are discussed.The study shows that the Central African Rift System mainly develops high-quality lacustrine source rocks in the Lower Cretaceous,and the West African Rift System mainly develops high-quality terrigenous organic matter-rich marine source rocks in the Upper Cretaceous,and the two types of source rocks provide a material basis for the enrichment of oil and gas in the CWARS.Multiple sets of reservoir rocks including fractured basement and three sets of regional cap rocks in the Lower Cretaceous,the Upper Cretaceous,and the Paleogene are developed in the CWARS.Since the Late Mesozoic,due to the geodynamic factors including the dextral strike-slip movement of the Central African Shear Zone,the basins in different directions of the CWARS differ in terms of rifting stages,intervals of regional cap rocks,trap types and accumulation models.The NE-SW trending basins have mainly preserved one stage of rifting in the Early Cretaceous,with regional cap rocks developed in the Lower Cretaceous strata,forming traps of reverse anticlines,flower-shaped structures and basement buried hill,and two types of hydrocarbon accumulation models of"source and reservoir in the same formation,and accumulation inside source rocks"and"up-source and down-reservoir,and accumulation below source rocks".The NW–SE basins are characterized by multiple rifting stages superimposition,with the development of regional cap rocks in the Upper Cretaceous and Paleogene,forming traps of draping anticlines,faulted anticlines,antithetic fault blocks and the accumulation model of"down-source and up-reservoir,and accumulation above source rocks".The combination of reservoir and cap rocks inside source rocks of basins with multiple superimposed rifting stages,as well as the lithologic reservoirs and the shale oil inside source rocks of strong inversion basins are important fields for future exploration in basins of the CWARS.