多波地震深度学习的油气储层分布预测案例   总被引：3，自引：1，他引：2       下载免费PDF全文

付超  林年添  张栋  文博  魏乾乾  张凯 《地球物理学报》2018,61(1):293-303

有机并有效利用纵波与转换横波在油气储层敏感度上存在的差异,有助于突出地震油气储层特征,有助于提高地震油气储层分布边界刻画的精度.基于此,本文设计了一种卷积神经网络与支持向量机方法相结合的多波地震油气储层分布预测的深度学习法（Deep Learning Method）.首先,利用莱特准则剔除所生成的多波地震属性中可能存在的异常值降低网络变体数量.然后,通过能突出多波地震油气储层特征的聚类算法和无监督学习算法构建隐藏层,用于增加网络共享,提取油气特征.最后,将增加网络罚值后的井点样本作为支持向量机预测的输入样本,以降采样后的C3卷积层属性作为学习集,进行从已知到未知的地震油气储层的预测.本方案应用于HG地区晚三叠统HGR组的碳酸盐岩油气储层预测,所预测的地震油气储层边界更加清晰,预测结果与实际情况基本吻合.应用结果表明：本论文方案不仅具有可行性,且具有有效性.  相似文献   

基于神经网络的地磁观测数据重构研究   总被引：2，自引：0，他引：2       下载免费PDF全文

姚休义  滕云田  杨冬梅  姚远 《地球物理学报》2018,61(6):2358-2368

在距离数据缺失台站一定范围内选取参考台作为输入,构建非线性BP神经网络并进行地磁观测数据重构研究.数据仿真结果显示,重构数据和原始记录数据吻合程度较高,重构残差较小,磁静日重构平均残差仅为0.11 nT,磁扰日平均重构残差为0.23 nT.重点对磁场活动最剧烈时段内的数据进行了短时重构,平均残差由0.4 nT降低到0.2 nT,重构效果得到较大改进.计算了原始数据与重构数据的功率谱密度,除部分高频信号外,二者变化特征基本相同,相关性高达1.0.从时域和频域验证了BP神经网络在地磁相对记录数据重构上的有效性,并将其运用于实际缺失数据重构,取得较好效果.  相似文献   

基于卷积神经网络的地震偏移剖面中散射体的定位和成像   总被引：1，自引：0，他引：1       下载免费PDF全文

奚先  黄江清 《地球物理学报》2020,63(2):687-714

本文提出了一种基于深度学习卷积神经网络(CNN)的全波形反演方法,可对地震散射波场中的散射体进行成像和定位.本文的灵感来自如下猜想:在散射波场剖面上的每个点附近的局部波场与该点到各散射体之间的最小距离有关系,并且这个关系可以被CNN网络所识别.我们将该最小距离定义为散射距离场,并将散射距离场的类别(即大小等级)作为CNN网络的预期输出,而输入就是该点附近的局部波场.最后用上述CNN网络对散射波场进行逐点训练和识别.计算结果证实了我们的灵感猜想,即上述CNN网络能够在复杂散射波场中对散射体进行成像.只通过一个训练模型的学习,CNN网络即可反演多种散射模型的偏移剖面,最后得到"类别函数预测值"和"滤波剖面"两种成像结果,由此可以辨识出在复杂的偏移剖面中各散射体的位置.  相似文献   

瓦屋山水库地震台网的恢复重建     

王翠芳  何涛 《地震地磁观测与研究》2020,(1):104-111

瓦屋山水库地震台网于2016年恢复重建,恢复重建的主要任务是对4个台站的观测设施进行改造、台站设备的升级换代、数据传输方式的恢复等,4个台站台址和1个台网中心不变.经过1年的恢复重建,瓦屋山水库地震台网考核运行率达到99.31%,监测能力满足可监测ML≥0.5地震的要求,2个台站的观测动态范围优于恢复重建前的水平,2个台站不如恢复重建前.  相似文献   

Are temporal variations in the nitrate content of UK upland freshwaters linked to the North Atlantic Oscillation?     

D. T. Monteith  C. D. Evans  B. Reynolds 《水文研究》2000,14(10):1745-1749

Synchronous patterns of variation in NO₃ concentration, observed in upland lakes and streams across gradients of climate, altitude, land use and nitrogen deposition over the last decade, show a strong negative correlation with winter values for the North Atlantic Oscillation Index and mean winter temperature. Variations in a longer term stream NO₃ record validate this relationship, and although mechanisms are yet unclear, may be linked to the length of time the soil profile remains frozen during the winter. These findings are of particular significance to our understanding of the relationship between atmospheric N deposition and concentrations and fluxes of NO₃ in runoff, and the potential response to future climatic changes. Copyright © 2000 John Wiley & Sons, Ltd.  相似文献   

The impact of the Sustainable Development Goals on a network of 276 international organizations     

《Global Environmental Change》2022

Global sustainability governance is marked by a highly fragmented system of distinct clusters of international organizations, along with states and other actors. Enhancing inter-organizational coordination and cooperation is thus often recognized as an important reform challenge in global sustainability governance. The 17 Sustainable Development Goals, agreed by the United Nations in 2015, thus explicitly aim at advancing policy coherence and institutional integration among the myriad international institutions. Yet, have these goals been effective in this regard? We assess here the impact of the Sustainable Development Goals on the network structure of 276 international organizations in the period 2012–2019, that is, four years before and four years after the launch of the Sustainable Development Goals. The network structure was approximated by analyzing data from the websites of these 276 international organizations that were joined by more than 1.5 million hyperlinks, which we collected using a custom-made web crawler. Our findings are contrary to what is widely expected from the Sustainable Development Goals: we find that fragmentation has in fact increased after the Sustainable Development Goals came into effect. In addition, silos are increasing around the 17 SDGs as well as around the social, economic, and environmental dimensions of sustainable development.  相似文献   

Multi-hazard susceptibility mapping based on Convolutional Neural Networks     

《地学前缘(英文版)》2022,13(5):101425

Multi-hazard susceptibility prediction is an important component of disasters risk management plan. An effective multi-hazard risk mitigation strategy includes assessing individual hazards as well as their interactions. However, with the rapid development of artificial intelligence technology, multi-hazard susceptibility prediction techniques based on machine learning has encountered a huge bottleneck. In order to effectively solve this problem, this study proposes a multi-hazard susceptibility mapping framework using the classical deep learning algorithm of Convolutional Neural Networks (CNN). First, we use historical flash flood, debris flow and landslide locations based on Google Earth images, extensive field surveys, topography, hydrology, and environmental data sets to train and validate the proposed CNN method. Next, the proposed CNN method is assessed in comparison to conventional logistic regression and k-nearest neighbor methods using several objective criteria, i.e., coefficient of determination, overall accuracy, mean absolute error and the root mean square error. Experimental results show that the CNN method outperforms the conventional machine learning algorithms in predicting probability of flash floods, debris flows and landslides. Finally, the susceptibility maps of the three hazards based on CNN are combined to create a multi-hazard susceptibility map. It can be observed from the map that 62.43% of the study area are prone to hazards, while 37.57% of the study area are harmless. In hazard-prone areas, 16.14%, 4.94% and 30.66% of the study area are susceptible to flash floods, debris flows and landslides, respectively. In terms of concurrent hazards, 0.28%, 7.11% and 3.13% of the study area are susceptible to the joint occurrence of flash floods and debris flow, debris flow and landslides, and flash floods and landslides, respectively, whereas, 0.18% of the study area is subject to all the three hazards. The results of this study can benefit engineers, disaster managers and local government officials involved in sustainable land management and disaster risk mitigation.  相似文献