多属性回归与神经网络串联反演预测薄储集层

在储集层地球物理响应分析和研究的基础上,应用多属性回归与神经网络串联反演方法,对研究区进行了可以表征薄储集层的自然伽马曲线反演。分析认为,砂体预测结果符合研究区整体沉积特征,纵向分辨率较高,横向砂体边界清晰,能够反映储集层的分布规律,为研究区今后的勘探指明了方向。

基于保幅纯波的多属性模型回归在储层描述中的应用——以准西车排子地区沙一段1砂组为例

车排子地区沙一段1砂组储层较薄且结构复杂,受地震资料分辨率的影响难以直接识别与描述。基于保幅纯波数据,尝试以均方根属性描述储层分布范围,以振幅平方差属性描述有利储层的发育范围。同时,结合属性独立性分析与储层厚度-属性相关性分析,优选出多个敏感属性进行储层厚度模型回归,对研究区的有利储层空间展布进行了精细刻画。预测结果认为,研究区存在东北、西北、西南3个可识别的物源。受其影响,沙一段1砂组储层厚度主体自南北向中间逐渐减薄,且平面上存在大面积不同物源砂体的交汇区,造成研究区沉积、储层岩性及组分变化较快。

利用地震属性预测煤层顶底板含水性研究

文章通过地震属性来预测岩性参数,即选择利用多属性线性回归和概率神经网络技术对纵波速度、密度、视电阻率和孔隙度这些岩性参数进行反演,进而从获得的波阻抗体、视电阻率体和孔隙度体来预测煤层顶底板岩石的含水性。应用实例中,预测含水性相对较强的区域为低波阻抗、低视电阻率和高孔隙度分布的区域,这符合岩石物理的认识,同时与矿区地质认识的含水区也是一致的。煤层顶底板含水性的分析,对于防患煤矿突水事故具有现实意义。

基于多属性变换的煤田波阻抗反演应用研究

随着煤炭资源勘探深度的日益增加,复杂的地质条件对岩性勘探提出了新的要求,常规的反演技术捉襟见肘。本文避开了以褶积模型为基础的常规反演,从基于地震属性技术的反演技术出发,选择利用多元线性回归技术和径向基神经网络技术进行反演研究。论文以山西阳泉某矿地震勘探资料为例进行反演计算,计算研究结果表明,基于多属性变换的反演技术效果优于常规的反演方法,在煤田反演中可以得到广泛的推广。这就为煤田岩性地震勘探提供了一项有效的技术,有很好的应用前景。

基于多层感知机网络的薄储层预测

相比地震反演方法和技术,基于多属性回归方法的储层预测技术能够缓解分辨率有限、过于模型化等问题,但模型泛化能力不足常造成井间薄储层预测结果不合理。为此,提出基于多层感知机深度学习网络的多属性回归薄储层预测方法,即以地震数据(提供背景信息)、90°相移数据(提供储层结构近似信息)、储层不连续界限属性(提供储层空间分布信息)为输入,以井点高频自然伽马为期望输出,利用多层感知机深度学习网络训练模型,预测井间自然伽马值,利用自然伽马值与砂—泥岩性的高度相关特性刻画薄储层。A油田实际资料测试表明,自然伽马预测值与真实值平均相关系数达到86.4%(训练集,10口井)和85.5%(验证集,两口井),明显优于传统多属性回归方法。应用该方法解释重点层段6套小层,薄储层预测结果与156口井实钻砂岩厚度平均相关系数较相移数据提升约38%,证实该方法应用效果良好。

Prediction of Soil Depth from Digital Terrain Data by Integrating Statistical and Visual Approaches

Information about the spatial distribution of soil attributes is indispensable for many land resource management applications; however, the ability of soil maps to supply such information for modern modeling tools is questionable. The objectives of this study were to investigate the possibility of predicting soil depth using some terrain attributes derived from digital elevation models （DEMs） with geographic information systems （GIS） and to suggest an approach to predict other soil attributes. Soil depth was determined at 652 field observations over the A1-Muwaqqar Watershed （70 km2） in Jordan. Terrain attributes derived from 30-m resolution DEMs were utilized to predict soil depth. The results indicated that the use of multiple linear regression models within small watershed subdivisions enabled the prediction of soil depth with a difference of 50 cm for 77% of the field observations. The spatial distribution of the predicted soil depth was visually coincided and had good correlations with the spatial distribution of the classes amalgamating three terrain attributes, slope steepness, slope shape, and compound topographic index. These suggested that the modeling of soil-landscape relationships within small watershed subdivisions using the three terrain attributes was a promising approach to predict other soil attributes.

Statistical Approach to Identify Environmental Factors in Controlling Heavy Metal Concentrations in Sediment

Surface sediment samples were collected from 35 locations in Sulaibikhat Bay, Kuwait. Co, Cr, Cu, Ni, Pb and Zn concentrations were determined. Grain sizes, TOC （total organic carbon）, carbonate, mineralogical and environmental data were also determined. Multiple linear regression is applied to the data from the sediment sequential extractions to assess the relative importance of mineralogical and sedimentological factors in controlling heavy metal concentrations in individual chemical fractions （exchangeable, reducible, oxidizable, residual） under different environmental conditions. The analysis shows that grain size, TOC, calcium carbonate and minerals clearly influence heavy metal concentrations. For the exchangeable fraction, clay, grain size and the mineral pyrite are the main factors, whereas for the reducible fraction, TOC is the main factor influencing concentrations ofZn, Pb, Ni, Cu and Cr. For the oxidizable fraction, modelling shows that TOC is the main factor influencing Zn, Ni, Cu, Cr and Co concentrations. The residual fraction concentrations of Zn, Ni, Cr and Co were best predicted by the abundance of sand, with sand content having a negative effect on heavy metal concentrations in this fraction. The statistical techniques in environmental data interpretation are quite useful in cutting down the volume of the data and identifying identical classes which are statistically distinct.

Estimation of reservoir porosity using probabilistic neural network and seismic attributes

Porosity is one of the most important properties of oil and gas reservoirs. The porosity data that come from well log are only available at well points. It is necessary to use other method to estimate reservoir porosity.Seismic data contain abundant lithological information. Because there are inherent correlations between reservoir property and seismic data,it is possible to estimate reservoir porosity by using seismic data and attributes.Probabilistic neural network is a powerful tool to extract mathematical relation between two data sets. It has been used to extract the mathematical relation between porosity and seismic attributes. Firstly,a seismic impedance volume is calculated by seismic inversion. Secondly,several appropriate seismic attributes are extracted by using multi-regression analysis. Then a probabilistic neural network model is trained to obtain a mathematical relation between porosity and seismic attributes. Finally,this trained probabilistic neural network model is implemented to calculate a porosity data volume. This methodology could be utilized to find advantageous areas at the early stage of exploration. It is also helpful for the establishment of a reservoir model at the stage of reservoir development.

利用地震地质资料综合研究X凹陷煤系地层分布

Y组的煤系源岩是X凹陷天然气的重要源岩,准确预测其分布对于科学地评价X凹陷天然气勘探前景具有重要意义。在充分消化吸收前人工作成果的基础上,针对存在的主要问题,通过对井区煤层组进行岩石物理分析,确定能区分煤层与围岩的测井序列,从正演模拟研究出发,对煤系地层的地球物理响应特征进行分析,结合属性分析等技术手段,进行煤系地层地质特征的地球物理识别,综合运用岩心、测井、地球化学、古生物等资料,分析凹陷的成煤环境,对煤系地层的分布进行预测。经研究,认为X凹陷的西北部是Y组煤系地层最有利发育区,为富煤区所在,以多属性回归分析技术为代表的地震属性分析技术系列可以较好地预测薄煤层组合的分布规律。