迭代法建立的低频模型在储层反演中的应用     

王伟  李炳颖  黄鑫  陈易周 《中国地质调查》2021,8(1):125-133

储层预测的精度直接制约着油气开发的经济性与有效性,而低频信息的补偿是改善储层反演效果的有利途径之一。常规的测井曲线内插低通滤波建模方法难以精细表征复杂地质背景下的低频模型。为降低研究区特殊地质体对储层反演带来的影响,采用迭代法建立低频模型,建模中分步考虑压实作用、特殊岩性等因素影响,并通过反演效果不断迭代更新低频模型,最终准确建立反映不同岩性(包含火山岩)的反演低频模型。研究表明: 该方法能够保证储层反演结果的可靠性,为储层精细描述提供了资料; 同时基于反演结果,对东海西湖凹陷W气田主力层(P1)有利储层进行重新刻画,优化了开发井水平段的位置,该井实施结果证实钻遇了优质储层。用迭代法建立的低频模型为复杂地质背景地区储层预测提供了一种更有效的建模方法。  相似文献   

Spatial landslide susceptibility assessment using machine learning techniques assisted by additional data created with generative adversarial networks     

Husam A.H.Al-Najjar  Biswajeet Pradhan 《地学前缘(英文版)》2021,12(2):625-637

In recent years,landslide susceptibility mapping has substantially improved with advances in machine learning.However,there are still challenges remain in landslide mapping due to the availability of limited inventory data.In this paper,a novel method that improves the performance of machine learning techniques is presented.The proposed method creates synthetic inventory data using Generative Adversarial Networks(GANs)for improving the prediction of landslides.In this research,landslide inventory data of 156 landslide locations were identified in Cameron Highlands,Malaysia,taken from previous projects the authors worked on.Elevation,slope,aspect,plan curvature,profile curvature,total curvature,lithology,land use and land cover(LULC),distance to the road,distance to the river,stream power index(SPI),sediment transport index(STI),terrain roughness index(TRI),topographic wetness index(TWI)and vegetation density are geo-environmental factors considered in this study based on suggestions from previous works on Cameron Highlands.To show the capability of GANs in improving landslide prediction models,this study tests the proposed GAN model with benchmark models namely Artificial Neural Network(ANN),Support Vector Machine(SVM),Decision Trees(DT),Random Forest(RF)and Bagging ensemble models with ANN and SVM models.These models were validated using the area under the receiver operating characteristic curve(AUROC).The DT,RF,SVM,ANN and Bagging ensemble could achieve the AUROC values of(0.90,0.94,0.86,0.69 and 0.82)for the training;and the AUROC of(0.76,0.81,0.85,0.72 and 0.75)for the test,subsequently.When using additional samples,the same models achieved the AUROC values of(0.92,0.94,0.88,0.75 and 0.84)for the training and(0.78,0.82,0.82,0.78 and 0.80)for the test,respectively.Using the additional samples improved the test accuracy of all the models except SVM.As a result,in data-scarce environments,this research showed that utilizing GANs to generate supplementary samples is promising because it can improve the predictive capability of common landslide prediction models.  相似文献   

文本特征提取的研究进展     

曾明睿  袁梦奇  邵曦  鲍秉坤  徐常胜 《南京气象学院学报》2019,11(6):706-715

文本理解是人工智能的一个重要分支,其技术推动了人与计算机之间在自然语言上的有效交互.为了让计算机准确地理解和感知文本数据,文本特征提取是最为基础和关键的步骤之一.基于此,本文介绍文本特征提取研究的发展历史,以及近年来主流特征提取的方法,并对未来的研究方向进行展望.首先,介绍语义最底层的词级表示;接着,总结在词级表示基础上衍生出的句级表示上的研究进展;随后,介绍比词级表示和句级表示更高层的篇分析;最后,通过文本特征提取的一个典型应用——问答系统的介绍,阐述文本特征提取的最新方法和技术在问答系统上的应用,并对未来的研究方向做了展望.  相似文献   

一种基于微服务架构的突发事件预警辅助决策系统的设计与实现     

陈石定  刘翔  汪应琼 《南京气象学院学报》2019,11(5):609-620

单体式架构应用在突发事件预警辅助决策系统开发中不能满足现实需求,本文引入了微服务架构设计开发该辅助决策系统.通过分析微服务架构在复杂系统中相对于传统单体式架构的应用优势,设计出一种基于微服务架构的突发事件预警信息发布辅助决策系统,该系统选用Spring Cloud微服务框架,并对其进行适当的扩展,创建了基于该系统设计的注册中心与网关.系统采用二三维一体化地理信息系统作为展示平台,通过接入各行业静态、危险源动态监测数据,根据设定的模型进行数据融合、处理,辅助进行预警信息生成、发布及应急处置阶段的指挥决策.所设计方案在湖北省突发事件预警发布辅助决策系统中得以实际应用,验证了该类系统使用微服务架构的合理性和有效性.  相似文献   

Who governs here? Informal resource extraction,state enforcement,and conflict in Ghana     

《Global Environmental Change》2019

Over the past two decades, “illegal” natural resource extraction has become a significant driver of environmental change and social conflict across the Global South. In response, numerous Sub-Saharan African states have engaged in governance reforms that heed calls to securitize – or, establish and consolidate state control over – natural resources. In Ghana, securitization has served to entrench the informal economy as domestic producers, marginalized in the process of reform, continue to utilize non-state institutions to maintain access. While the Ghanaian state has branded “illegal” resource extraction a major environmental, social, and national security concern, it has responded to this threat unevenly; it has violently enforced its authority in some contexts but remained relatively indifferent in others. This article explores the phenomenon of selective enforcement to explain patterns of violence that have emerged between state and society in response to both securitization and informality. Drawing on a multimethod approach, I find that natural resource governance authority remains fragmented across resource contexts, and that the configuration of authority and interests on the ground shapes the extent of state intervention. I propose a natural resource typology that identifies when the state is most likely to enforce its authority, and the degree of violent conflict likely to result. Ultimately, I contend that domestic patterns of enforcement are shaped primarily by: 1) competition with local power holders over resource entitlements and 2) global conservation and extraction priorities. While specific to Ghana, this argument can provide important insights into the relationship between informal extraction, state enforcement, and social conflict in other Global South contexts.  相似文献   

面向带电作业的手臂末端输出力评估方法     

林子  熊鹏文  何孔飞  张发辉 《南京气象学院学报》2019,11(2):186-191

为了解决带电作业时手臂末端输出力的准确控制,提出一种基于表面肌电信号（sEMG信号）和支持向量机回归（SVR）实现对手臂末端施力的评估方法.通过手握机械手臂末端的手柄,做往复推拉运动,记录此时手柄处的力传感器的数据F,同时利用3组肌电信号传感器同步采集手臂的肌电信号.将肌电信号提取特征后,与力F组合成样本集合S,在样本集合中随机抽取50%的样本数据作为训练集,分别训练BP神经网络、GRNN神经网络以及SVR神经网络.最后用训练好的神经网络对整个样本集中的力F进行预测,并用均方根误差和相关系数评估模型的预测效果.结果显示,SVR神经网络的预测效果较好,其均方根误差为3.074 0,相关系数为0.951 7.  相似文献   

A GIS-based approach for detecting pollution sources and bioavailability of metals in coastal and marine sediments of Chabahar Bay,SE Iran     

《Chemie der Erde / Geochemistry》2015,75(2):185-195

Chabahar Bay in SE of Iran is a shallow semi-enclosed environment affected by anthropogenic activities. In this paper, 19 sediment samples were collected and concentration of selected metals (Cu, Pb, Zn, Cd, Ni, Cr, Co, V and Fe) was determined using ICP-MS analytical method. Sediment samples from five stations were also selected for sequential extraction analysis and concentration of metals in each fraction was determined using ICP-OES. In order to investigate the environmental quality of Chabahar Bay, geographic information system (GIS) along with geochemical data, environmental indices and statistical analyses were used. Calculated contamination degree (C_d) revealed that most contaminated stations (Ch3, S1 and S3) are located SE of Chabahar Bay and contamination decreases in a NW direction. The S9 station, west of the bay, is also contaminated. High organic matter (OM) content in the sediments is most likely the result of fuel and sewage discharge from fishing vessels along with discharge of fishing leftovers. Significant correlation coefficient among OM, Fe, Cu, Pb, Zn and Cd seemingly reflects the importance of the role that OM and Fe oxy-hydroxides play in the metals mobility. The results of hierarchical cluster analysis (HCA), computed correlation coefficient and sequential extraction analysis suggest that Cu, Pb, Zn and Cd probably come from antifouling and sea vessel paints, while Ni, Cr, Co, V and Fe are most likely contributed by ophiolitic formations located north of the bay and/or deep sea sediments. Average individual contamination factors (ICFs) indicated that the highest health hazard from the bay is posed by Cu, Pb and Zn.  相似文献   

Linking pesticides and human health: A geographic information system (GIS) and Landsat remote sensing method to estimate agricultural pesticide exposure     

《Applied geography (Sevenoaks, England)》2015

Accurate pesticide exposure estimation is integral to epidemiologic studies elucidating the role of pesticides in human health. Humans can be exposed to pesticides via residential proximity to agricultural pesticide applications (drift). We present an improved geographic information system (GIS) and remote sensing method, the Landsat method, to estimate agricultural pesticide exposure through matching pesticide applications to crops classified from temporally concurrent Landsat satellite remote sensing images in California. The image classification method utilizes Normalized Difference Vegetation Index (NDVI) values in a combined maximum likelihood classification and per-field (using segments) approach. Pesticide exposure is estimated according to pesticide-treated crop fields intersecting 500 m buffers around geocoded locations (e.g., residences) in a GIS. Study results demonstrate that the Landsat method can improve GIS-based pesticide exposure estimation by matching more pesticide applications to crops (especially temporary crops) classified using temporally concurrent Landsat images compared to the standard method that relies on infrequently updated land use survey (LUS) crop data. The Landsat method can be used in epidemiologic studies to reconstruct past individual-level exposure to specific pesticides according to where individuals are located.  相似文献   

Monitoring land changes in an urban area using satellite imagery,GIS and landscape metrics     

《Applied geography (Sevenoaks, England)》2015

Monitoring land changes is an important activity in landscape planning and resource management. In this study, we analyze urban land changes in Atlanta metropolitan area through the combined use of satellite imagery, geographic information systems (GIS), and landscape metrics. The study site is a fast-growing large metropolis in the United States, which contains a mosaic of complex landscape types. Our method consisted of two major components: remote sensing-based land classification and GIS-based land change analysis. Specifically, we adopted a stratified image classification strategy combined with a GIS-based spatial reclassification procedure to map land classes from Landsat Thematic Mapper (TM) scenes acquired in two different years. Then, we analyzed the spatial variation and expansion of urban land changes across the entire metropolitan area through post classification change detection and a variety of GIS-based operations. We further examined the size, pattern, and nature of land changes using landscape metrics to examine the size, pattern, and nature of land changes. This study has demonstrated the usefulness of integrating remote sensing with GIS and landscape metrics in land change analysis that allows the characterization of spatial patterns and helps reveal the underlying processes of urban land changes. Our results indicate a transition of urbanization patterns in the study site with a limited outward expansion despite the dominant suburbanization process.  相似文献   

基于地貌单元的小区域地质灾害易发性分区方法研究   总被引：10，自引：0，他引：10  

唐川  马国超 《地理科学》2015,(1)

以汶川县城周边区域为研究区,分别以栅格单元与地貌单元作为单位评价单元,以信息量法与逻辑回归法两种评价模型对研究区进行地质灾害易发性评价分区。根据对评价结果的比较分析,在小区域范围内,基于地貌单元的区域易发性分区不仅仅能够更好地体现出区域内局部综合特性,而且评价分区结果与地质灾害实际分布情况更加吻合,分级层次更加明显,数学模型的适用效率很好。由此可见,在小范围区域内,基于地貌单元的地质灾害易发性评价分区具有良好的适用性与可塑性,在大比例尺地质灾害易发性和危险性制图中是一个有益的尝试与启发。  相似文献