基于决策树特征提取的支持向量机在岩性分类中的应用

由于支持向量机属于黑箱模型,因此在进行模型学习时无法直接对特征进行选择,而决策树模型在递归创建的过程中自身具有一定的特征选择能力。针对岩性分类问题,本文将决策树和支持向量机结合,通过决策树的建立,在考虑特征重要性的前提下,利用树节点的高度对特征进行提取,并将具有更高分类能力的特征送入支持向量机进行岩性分类。结果表明:通过决策树的特征提取,减少了支持向量机模型的输入特征,从而有效控制了模型的复杂度,使得模型更加稳定并具有更高的分类精度,测试集精度能够提升10%以上。     

四川龙门山中段上三叠统须家河组特征

上三叠统须家河组广泛分布于四川汶川县、都江堰市、崇州市、大邑县等毗邻地区，呈NE向展布，出露面积大于150km^2，厚度大于2851m。笔者在进行1：5万“三江幅”和“万家坪幅”区域地质调查时，于该区测制了须家河组剖面。本文对这一地区的须家河组进行了一、二、三段的划分，并对岩石特征、地层对比、底顶界线、生物地层和年代地层者概略讨论；须家河组的沉积环境可划分为三角洲相和河流相。     

姑婆山复式岩体的基本特征及其与成矿作用的关系

姑婆山复式岩体由晚侏罗世里松岩体、姑婆山岩体及早白垩世新路岩体组成。复式岩体为壳幔混合源成因。据岩石地球化学判断和分析,姑婆山岩体和新路岩体为含锡岩体;整个姑婆山复式岩体为含钨岩体,里松岩体和姑婆山岩体为含稀有、稀土岩体。上述矿产的形成与岩石中挥发份F、B及放射性U、T h等元素的高含量有关。     

基于ASTER遥感影像的西昆仑岩性信息提取方法研究

基于西昆仑西段布伦口地区各岩性段内岩石样品的矿物组成及其光谱特征分析,提取代表各岩性单元的岩性端元波谱曲线;对研究区内ASTER可见光(VNIR)和短波红外(SWIR)数据进行匹配滤波处理,成功提取了研究区内9种重要的岩性单元(包括古元古界布仑阔勒群的黑云石英岩、黑云斜长片麻岩、黑云石英片岩和黑云角闪斜长片麻岩,志留系温泉沟群的绿泥石绢云母板岩、黑色千枚岩和绢云母石英片岩,以及石英闪长岩和英云闪长岩)。经已知地质资料和野外查证资料分析证明,用上述方法提取岩性信息的结果可靠,能为岩性填图及矿床勘查工作提供参考。     

河道砂体内部夹层岩性与遮挡性识别

河道砂体内部夹层作为储层构型界面,厚度较薄,岩性、遮挡性存在差异,对河道砂体内流体渗流及剩余油分布的影响不尽相同。本文以大庆油田萨北二区为例,利用密闭取芯井岩芯和纵向分辨率较高的微电极测井曲线等资料,以岩芯识别夹层岩性为基础,通过对测井曲线幅值、幅差、回返率交汇分析,优选出微电位回返最低值和微梯度回返率作为夹层岩性判别标准,夹层岩性识别符合率达82%;并以夹层含油性为依据,将夹层按遮挡性分为完全阻流型、强限流型、弱限流型等三种类型;分析密闭取芯井河道砂体内部夹层岩性与遮挡性对应关系,建立了非取芯井河道砂体内部夹层遮挡性的岩性解释法,夹层遮挡性识别符合率达72%。以此为深入研究地下河道砂体内部构型对注入剂驱替路径及剩余油分布的影响奠定基础。     

Impact of lithology and soil properties on abandoned dryland terraces during the early stages of soil erosion by water in south‐east Spain

Soil erosion by water in abandoned dry terraces is one of the most important environmental problems in semiarid areas, enhancing biological degradation and reducing possible resources that can be obtained. However, little is known about the effects of the types of lithology and soil properties on the early stages of soil erosion. Therefore, the main aim of this research was to assess the effect of different lithologies (marls, limestones, and metamorphic—phyllites, schists, and greywackes—materials) and soil properties on the early stages of soil erosion by water in abandoned dry terraces, compared with similar terraces still in agricultural use. Soil analyses (texture, aggregate stability, and bulk density) and 22 rainfall simulations were carried out under dry conditions. During the experiments, local inclination, vegetation and stone cover, total organic matter, and antecedent soil moisture were also quantified. The results showed that the highest soil loss (41.41 g/m² in cultivated plots and 17.05 g/m² in the abandoned plots) and runoff (3.79 L/m² in the abandoned plot) occurred on marl substrata. Marls also showed the shallowest infiltration front (9 cm) and lowest infiltration rate (4.3 cm/min). Limestones and, especially, metamorphic areas, showed a lower degree of soil erosion, higher infiltration rates, and deeper infiltration fronts.     

Log evaluation of fractured igneous reservoirs in Songliao Basin

The petrophysical parameters are bad in most igneous reservoirs of Songliao Basin because of the very low porosity and permeability. The evaluation of igneous reservoirs has not been fully studied so far. The current technique of formation evaluation and interpretation used in sedimentary formations face a series of prob- lems and difficulties. In this study, The PCA was used to identify lithology, a multi-mineral model “QAPM” was proposed. “Surface effect” must be considered when evaluating saturation. A software “SIMPLE” was developed and was used to deal with the logging data in over 70 wells with good results were achieved.     

岩性识别：方法、现状及智能化发展趋势

岩性识别是地质工作中一项基础而又重要的工作。传统的岩性识别方法过于依赖经验和地质专业知识积累,不仅耗时长、专业性强,还易受主观因素影响,导致准确率不理想。笔者等首先回顾了传统的岩性识别方法,之后总结了最新涌现的智能化识别方法,最后详细介绍了基于岩石图像、镜下图像、图像与元素信息融合等的智能识别方法。基于岩石图像的识别方法对于文中的岩石识别准确率可达90%以上,基于图像与元素融合的岩性识别方法可以缓解图像相似度高、风化破坏表观特征等因素对识别准确度的影响。笔者等认为当前岩性智能化识别研究仍处于初级阶段,无法满足工程需求。综合各类数据源的优势,利用机器学习深度挖掘岩石元素、矿物、光谱和表观特征间的内在关联性,有利于突破单源信息的局限性,实现岩性快速准确识别。     

岩性和种植年限对火龙果地土壤碳、氮、磷生态化学计量特征的影响

以石漠化问题突出区域——广西平果县太平镇耶圩火龙果种植园不同岩性背景(白云岩、碎屑岩)和不同种植年限(1、3、5a)土壤为研究对象,采用相关性分析和冗余分析方法探讨了不同岩性背景和火龙果种植年限下土壤碳、氮、磷生态化学计量特征及其影响因素。结果表明：①白云岩区土壤全磷含量显著高于碎屑岩区,而土壤有机碳含量、生态化学计量比(C/N、C/P和N/P)显著低于碎屑岩区;且白云岩和碎屑岩背景下的生态化学计量比(5.96、11.78、1.96和8.71、19.78、2.28)均远低于全国水平。②随着火龙果种植年限的增加,土壤有机碳、全氮含量和C/N、C/P、N/P呈现出逐渐增加的趋势,而土壤有效氮、全磷和有效磷含量无显著变化规律。随着土层深度增加,土壤有机碳、全氮、有效氮含量和C/N、C/P、N/P均增加,而土壤全磷含量无明显变化规律。③土壤C/N和C/P与有机碳、有效氮均呈显著正相关(P<0.01),而与土壤水分、容重呈显著负相关,土壤N/P与全磷呈显著负相关。④冗余分析表明不同岩性背景和火龙果种植年限下土壤有效氮含量是土壤碳、氮、磷及其生态化学计量比的重要影响因子,且呈显著正相关关系(P<0.01)。白云岩背景下火龙果的生长受到氮元素的影响更大,长期火龙果种植有利于碳、氮元素固存,土壤有效氮含量是影响土壤碳、氮、磷及其生态化学计量比的关键因子。     

Source Lithology and Magmatic Processes Recorded in the Mineral of Basalts from the Parece Vela Basin

Since the Early Cenozoic, the Philippine Sea Plate (PSP) has undergone a complex tectonic evolution. During this period the Parece Vela Basin (PVB) was formed by seafloor spreading in the back-arc region of the proto-Izu-Bonin-Mariana (IBM) arc. However, until now, studies of the geological, geophysical, and tectonic evolution of the PVB have been rare. In this study, we obtained in situ trace element and major element compositions of minerals in basalts collected from two sites in the southern part of the PVB. The results reveal that the basalts from site CJ09-63 were likely formed via ~10% partial melting of spinel-garnet lherzolite, while the basalts from site CJ09-64 were likely formed via 15%–25% partial melting of garnet lherzolite. The order of mineral crystallization for the basalts from site CJ09-64 was olivine, spinel, clinopyroxene, and plagioclase, while the plagioclase in the basalts from site CJ09-63 crystallized earlier than the clinopyroxene. Using a plagioclase-liquid hygrometer and an olivine-liquid oxybarometer, we determined that the basalts in this study have high H2O contents and oxygen fugacities, suggesting that the magma source of the Parece Vela basalts was affected by subduction components, which is consistent with the trace element composition of whole rock.