FLU-net：用于表征页岩储层微观孔隙的深度全卷积网络

页岩孔隙是页岩气储集的主要空间,孔隙的形状、大小、连通性与发育程度很大程度上决定了页岩储集层的储集性能,因此,页岩气开采首先需要对其孔隙有充分的认识。基于阈值分割法获取页岩孔隙结构参数是目前页岩微观结构表征的一种重要手段,但是受扫描电镜图像灰度分布差异的影响,该方法需要逐一修改图像的最佳分割阈值以达到最好的孔隙分割效果,且阈值分割方法无法直接划分孔隙类别,这给后续的页岩微观结构定量表征带来了麻烦。为了实现页岩孔隙的智能识别和分类,笔者设计基于像素级语义分割的深度全卷积神经网络FLU-net,对页岩孔隙识别并分类为有机孔、无机孔（粒内孔、粒间孔）及裂缝,并结合孔隙尺度分类统计方法,分析不同类型孔隙发育数量、孔径大小、孔隙度等参数,实现页岩储层微观孔隙结构的自动化定量表征。以重庆渝西区块足201井区和四川盆地威远地区威204井区的页岩扫描电镜图像为研究对象,在对1 600幅页岩扫描电镜图像原始数据进行人工标注并划分数据集后,使用FLU-net进行孔隙识别,结果表明,本方法具有较高的准确率,同时自动化程度和泛化能力均高于传统预测方法。因此,扫描电镜与基于深度学习的语义分割模型结合是定量研究页岩微观结构表征的有效手段。     

An experimental study on microscopic characteristics of gas-bearing sediments under different gas reservoir pressures

Gas-bearing sediments are widely distributed in five continents all over the world. Most of the gases exist in the soil skeleton in the form of discrete large bubbles. The existence of gas-phase may increase or decrease the strength of the soil skeleton. So far, bubbles’ structural morphology and evolution characteristics in soil skeleton lack research, and the influence of different gas reservoir pressures on bubbles are still unclear. The micro characteristics of bubbles in the same sediment sample were studied using an industrial CT scanning test system to solve these problems. Using the image processing software, the micro variation characteristics of gas-bearing sediments in gas reservoir pressure change are obtained. The results show that the number and volume of bubbles in different equivalent radius ranges will change regularly under different gas reservoir pressure. With the increase of gas reservoir pressure, the number and volume of tiny bubbles decrease. In contrast, the number and volume of large bubbles increase, and the gas content in different positions increases and occupies a dominant position, driving the reduction of pore water and soil skeleton movement.     

Automated multi-scale classification of the terrain units of the Jiaxie Guyots and their mineral resource characteristics

Given the advances in satellite altimetry and multibeam bathymetry, benthic terrain classification based on digital bathymetric models (DBMs) has been widely used for the mapping of benthic topographies. For instance, cobalt-rich crusts (CRCs) are important mineral resources found on seamounts and guyots in the western Pacific Ocean. Thick, plate-like CRCs are known to form on the summit and slopes of seamounts at the 1 000–3 000 m depth, while the relationship between seamount topography and spatial distribution of CRCs remains unclear. The benthic terrain classification of seamounts can solve this problem, thereby, facilitating the rapid exploration of seamount CRCs. Our study used an EM122 multibeam echosounder to retrieve high-resolution bathymetry data in the CRCs contract license area of China, i.e., the Jiaxie Guyots in 2015 and 2016. Based on the DBM construted by bathymetirc data, broad- and fine-scale bathymetric position indices were utilized for quantitative classification of the terrain units of the Jiaxie Guyots on multiple scales. The classification revealed four first-order terrain units (e.g., flat, crest, slope, and depression) and eleven second-order terrain units (e.g., local crests, depressions on crests, gentle slopes, crests on slopes, and local depressions, etc.). Furthermore, the classification of the terrain and geological analysis indicated that the Weijia Guyot has a large flat summit, with local crests at the southern summit, whereas most of the guyot flanks were covered by gentle slopes. “Radial” mountain ridges have developed on the eastern side, while large-scale gravitational landslides have developed on the western and southern flanks. Additionally, landslide masses can be observed at the bottom of these slopes. The coverage of local crests on the seamount is ~1 000 km2, and the local crests on the peak and flanks of the guyots may be the areas where thick and continuous plate-like CRCs are likely to occur.     

垦东滩海地区浅部储层精细描述

我国东部滩海地区浅部具有地震采集条件差、资料品质低、储层岩性变化大、砂泥和泥岩难以区分等缺点,导致储层描述较为困难。为了解决这一问题,以垦东滩海地区为例,通过井震结合,形成了"合成地震记录标定、地震反演追踪、属性提取查明"的储层精细描述方法。在具体描述时,先将环境校正后的合成地震记录与井旁地震道相位、能量准确对比,从而标定储层;同时进行测井约束下的地震反演,从而实现砂岩储层的横向追踪;并通过均方根振幅属性提取,明确储层的平面分布。储层描述发现,垦东滩海地区馆陶组IV砂组储层呈SN向条带状分布,显示曲流河沉积特征。     

湖底扇水道相控建模技术及应用

随着渤海勘探力度加强,大型湖底扇岩性圈闭逐渐成为新的勘探目标,但是湖底扇不同期次水道垂向相互叠合,部分水道下切,砂体展布以及砂体间的连通关系复杂。针对湖底扇储层具有非均质性强,储层刻画难度大的特点,以渤海垦利10-A构造为例,充分利用多种地震信息,高度综合地质、钻井、测井、地震等资料,将传统的“相控建模”思想引入湖底扇储层建模当中,提出了湖底扇储层相控建模新技术。该技术在对湖底扇沉积构型模式和富砂性深入研究的基础上,利用湖底扇储集相和三维甜点体属性进行双重控制和约束,在地质认识指导下,应用地质统计学理论和随机建模方法建立符合地质规律的三维岩相模型,在多次建模实现后求取砂岩概率体,完成对湖底扇水道的精细刻画,砂体连通性分析和储层预测。研究结果表明,该方法能有效地降低储层属性模拟的不确定性和多解性,提高储层预测的精度,为后期勘探布井奠定了基础。     

渤海MN油田南区相控地质建模

在精细地层对比、沉积相分析和隔夹层分布等研究基础上,笔者采用相控方法进行渤海MN油田南区储层三维地质建模。在沉积相模拟中,以沉积模式为蓝本,将沉积亚相展布、井震结合预测的泥岩夹层分布等确定性认识和随机模拟技术相结合,同时依据各沉积亚相内储层发育的特征和差异,选择不同的“砂包泥”和“泥包砂”模拟思路,实现逐级相控、定量表征储层的空间分布。研究结果表明,以精细油田地质特征认识为基础,采用多条件地质约束的相控建模方法,可以更好地反映沉积认识,提高储层建模的精确度。     

曲线重构技术在鄂尔多斯盆地岩性圈闭储层预测中的应用

在井约束的随机反演过程中,通常利用单一测井曲线来指示储层,这种方法使用的曲线类型单一,不能完整地反映储层特征。因此,提出利用多种测井曲线来重构一种更接近储层真实特性的曲线,相比较伽马、中子等曲线而言,重构后的曲线与波阻抗具有更好的相关性,反演出来的岩性剖面更加真实。针对D区实际资料,利用曲线重构反演技术进行目标区储层预测,取得了相对常规单一曲线岩性反演更好的效果,证明了该方法的有效性。     

我国海岸潟湖卫星遥感分类方法研究

参照Landsat-5TM和HJ-1CCD遥感影像,依据实地踏勘资料及解译经验,分析各种海岸潟湖地貌学成因和发育演变阶段,提出基于潟湖地貌学成因的遥感分类方法。并将我国海岸潟湖划分为滨外坝型、沙坝型、沙嘴型、湾顶坝型、连岛坝型和河口型共6种地貌类型。建立基于发育演变阶段的潟湖遥感分类标准,将海岸潟湖分为青壮年期、老年期和死亡期共3个发育演变过程;结合潟湖在影像中的特征,以近红外、红、绿波段组合后的假彩色影像为例,从色彩、纹理、地物邻接关系等方面建立不同潟湖类型的遥感解译标志;根据所建立的遥感解译标志,对山东省53个海岸潟湖进行遥感分类验证,结果吻合。     

西湖凹陷Y构造花港组气藏特征及成藏主控因素

以常规和非常规油气成藏理论为指导,结合储层、流体等测试分析结果,开展西湖凹陷Y构造花港组气藏特征及成藏主控因素研究。结果表明：① 花港组垂向上符合中下部致密砂岩气、上部常规天然气藏的分布序列;② 常规气藏气水关系正常,受断盖配置对沿断裂运移油气的封闭作用和断层侧向封堵能力影响,油气主要在区域盖层之下的断背斜顶部富集;③ 致密气藏具叠覆跨越源储组合关系,含气饱和度低,无明显气水界面,属先致密后成藏类型,不同部位含气性受构造幅度和储层物性共同控制。本次研究丰富和完善了西湖凹陷常规-非常规天然气序列成藏规律,并为致密砂岩气的勘探提供理论指导。