水文相关中的最小二乘回归问题探讨

在研究了水文相关中利用最小二乘原理进行回归分析方法的基础上，指出了传统水文回归分析方法的使用条件、局限性和存在的问题。提出了不同性质的变量在回归分析时应区别对待的概念。结合水文观测的实际情况，研究了相关变量观测值均存在误差情况下，以变量的观测误差作权进行回归分析的概念，提出了建立基于最小二乘原理基础上的双加权回归模型，并研究了该模型的解算方法。同时推导了估计参数和预测值的误差估计公式，通过估计参数和模型误差的研究，有助于提高水文变量回归的精度和误差估计水平。     

深基坑土钉支护的模糊可靠度分析

介绍了土钉支护体各种破坏模式下失效隶属函数的建立方法,并用模糊可靠度理论对实际基坑边坡工程的土钉支护体进行了可靠度分析,计算过程中部分数据采用了计算机仿真的方法,分析结果与实际相符,表明模糊可靠度理论对基坑土钉支护体进行分析具有一定现实意义。     

Uncertainty and Reliability Analysis Applied to Slope Stability: A Case Study From Sungun Copper Mine

Nowadays, there are many new methods for slope stability analysis; including probabilistic methods assessing geotechnical uncertainties to develop safety factors. In this paper, a reliability index analysis for the Sungun copper mine slope stability is evaluated based on three methods of uncertainties consisting Taylor series method, Rosenblueth point estimate method and Monte-Carlo simulation method. Sungun copper mine will be one of the Iran’s biggest mines with final pit’s height of 700 meters. For this study two of its main slopes were assessed, one dipping to the NE (030) and the other to the SE (140). Probability density function of cohesion and angle of friction for the slopes were developed using limit equilibrium methods. These shear strengths were then used to determine the probability density function of safety factor and reliability index using the probabilistic methods. Results of the probabilistic analysis indicate that with ascending values of the uncertainties the reliability index decreases. Furthermore, it was determined that with the Monte Carlo simulation the seed number used has little effect on the reliability index of the safety factor especially with seed numbers in excess of 1200. Variations in the overall reliability index of safety factor were observed between the two slopes and this difference is explained by the differences in complexities of the geology within the cross-section.     

基于最小二乘支持向量机测井识别火山岩类型:以辽河盆地中基性火山岩为例

最小二乘支持向量机是在统计学习理论基础上发展起来的模式识别方法。与传统统计学相比,它能有效解决有限样本、非线性、高维数模型的建立问题,而且建立的模型具有很好的预测性能。岩性识别本质是解决分类问题,本文基于最小二乘支持向量机解决分类问题的优势,首先用GR、CNL、DEN、AC、R_LLD等常规测井曲线数据建立样本空间;然后通过耦合模拟退火和交叉验证的方法寻找最佳参数,优化最小二乘支持向量机分类器;最后建立了最小二乘支持向量机岩性识别模型。通过取心段岩心描述和岩心/岩屑薄片鉴定,确定辽河盆地40口井315 m井段2 520个岩性样品作为训练样本,建立岩性识别标准。对8口井13 866 m井段110 928个火山岩数据采样点进行测井识别,可识别致密玄武岩、气孔玄武岩、粗面岩等8种主要火山岩类型。识别结果与8口测试井中316个有取心段岩心描述和岩心/岩屑薄片的精确岩矿定名对比,符合率达到75.2%,与以往测井识别复杂火山岩岩性相比,在识别准确率和效率上都有明显提高。     

An Objective Analysis of Support Vector Machine Based Classification for Remote Sensing

Accurate thematic classification is one of the most commonly desired outputs from remote sensing images. Recent research efforts to improve the reliability and accuracy of image classification have led to the introduction of the Support Vector Classification (SVC) scheme. SVC is a new generation of supervised learning method based on the principle of statistical learning theory, which is designed to decrease uncertainty in the model structure and the fitness of data. We have presented a comparative analysis of SVC with the Maximum Likelihood Classification (MLC) method, which is the most popular conventional supervised classification technique. SVC is an optimization technique in which the classification accuracy heavily relies on identifying the optimal parameters. Using a case study, we verify a method to obtain these optimal parameters such that SVC can be applied efficiently. We use multispectral and hyperspectral images to develop thematic classes of known lithologic units in order to compare the classification accuracy of both the methods. We have varied the training to testing data proportions to assess the relative robustness and the optimal training sample requirement of both the methods to achieve comparable levels of accuracy. The results of our study illustrated that SVC improved the classification accuracy, was robust and did not suffer from dimensionality issues such as the Hughes Effect.     

软岩高边坡喷锚挡护的试验研究

结合南昆铁路软岩深路堑高边坡采用喷锚挡护的工程，开展了地质力学模型试验研究。结果表明：采用喷锚挡护时可明显减小开挖在坡体内形成的松动区范围；开挖坡面的变形具有“臌肚子”特征。还给出了喷层上土压力分布、锚杆受力规律等结果。在此基础上对原设计和施工提出了“保住中部，稳定坡脚”的修改原则。     

西南某工程边坡支护方案案例分析及理正计算可靠性分析

边坡区斜坡为粉质粘土覆盖,下部为基岩层;部分地段为平台。斜坡坡角15°～20°左右。场坪标高541.50～544.50m,场地整平后形成长161m,高5.7～10.5m的土岩混合挖方边坡。距离拟建18层高建筑物8.3m,边坡破坏后果严重。确保边坡在工程年限内,出现天然,暴雨等作用下,不发生浅部整体滑动;确保小区居民生命财产安全;选取针对性强的"桩板式挡墙"工程措施和治理方案,利用理正计算软件对工程边坡支护方案设计,分析评价方案的可行性,通过对理正软件的计算结果进行复核对比分析,优化软件计算结果。对类似工程具有一定参考借鉴作用。     

Prediction of Safe Charge to Protect Surrounding Structures Using Support Vector Machine

The present paper mainly with deals the prediction of safe explosive charge used per delay (Q_MAX) using support vector machine (SVM) incorporating peak particle velocity (PPV) and distance between blast face to monitoring point (D). 150 blast vibration data sets were monitored at different vulnerable and strategic locations in and around a major coal producing opencast coal mines in India. 120 blast vibrations records were used for the training of the SVM model vis-à-vis to determine site constants of various conventional vibration predictors. Rest 30 new randomly selected data sets were used to compare the SVM prediction results with widely used conventional predictors. Results were compared based on coefficient of correlation (R) between measured and predicted values of safe charge of explosive used per delay (Q_MAX). It was found that coefficient of correlation between measured and predicted Q_MAX by SVM was 0.997, whereas it was ranging from 0.063 to 0.872 by different conventional predictor equations.     

基于支持向量机的降雨-径流预测研究

本文探讨了支持向量机方法在降雨-径流预测中的应用.该方法采用结构风险最小化准则,弥补了人工神经网络在预测应用中的不足,较好地解决了小样本,非线性、高维数和局部最小点等实际问题.并且本研究通过与人工神经网络预测方法、传统的回归分析预测方法比较研究,得出支持向量机能取得更高精度的降雨-径流预测值.     

加筋土坡稳定可靠度分析

将可靠度分析的JC法运用于加筋土坡稳定分析中,以瑞典法为计算模型,以土的抗剪强度指标C,φ为基本随机变量,结合一工程实例探讨了加筋土坡稳定可靠度分析中的若干规律性问题,得出了一些有益的结论.     

改进的最小二乘法在水文分析计算中的应用

在水分析计算中，经常涉及到变量之间的线性或非线性拟合，而在拟合各种特性曲线时，通常应用以实测资料与拟合曲线间的误差平方和最小作为目标函数的方法——最小二乘法，但这种方法忽视了所有实测点应与拟合曲线间的相对误差尽量不超过某一百分比的原则，为了达到上述要求，提出了非线性的加权最小二乘法及线性相关方程的最小距离平方和法，探讨改进了传统的最小二乘法达到优化的效果。最小距离平方和法与常用的图解法相比，本法所得成果较为客观；与传统的单方向(x或y方向)最小二乘回归法相比，所求线性方程不会因坐标系的选取而改变。最后应用算例进行了初步讨论。     

A Comparative Study of Least Square Support Vector Machines and Multiclass Alternating Decision Trees for Spatial Prediction of Rainfall-Induced Landslides in a Tropical Cyclones Area

The objective of this study is to explore and compare the least square support vector machine (LSSVM) and multiclass alternating decision tree (MADT) techniques for the spatial prediction of landslides. The Luc Yen district in Yen Bai province (Vietnam) has been selected as a case study. LSSVM and MADT are effective machine learning techniques of classification applied in other fields but not in the field of landslide hazard assessment. For this, Landslide inventory map was first constructed with 95 landslide locations identified from aerial photos and verified from field investigations. These landslide locations were then divided randomly into two parts for training (70 % locations) and validation (30 % locations) processes. Secondly, landslide affecting factors such as slope, aspect, elevation, curvature, lithology, land use, distance to roads, distance to faults, distance to rivers, and rainfall were selected and applied for landslide susceptibility assessment. Subsequently, the LSSVM and MADT models were built to assess the landslide susceptibility in the study area using training dataset. Finally, receiver operating characteristic curve and statistical index-based evaluations techniques were employed to validate the predictive capability of these models. As a result, both the LSSVM and MADT models have high performance for spatial prediction of landslides in the study area. Out of these, the MADT model (AUC = 0.853) outperforms the LSSVM model (AUC = 0.803). From the landslide study of Luc Yen district in Yen Bai province (Vietnam), it can be conclude that the LSSVM and MADT models can be applied in other areas of world also for and spatial prediction. Landslide susceptibility maps obtained from this study may be helpful in planning, decision making for natural hazard management of the areas susceptible to landslide hazards.     

填土边坡稳定性的可靠度分析

为了系统地建立填土边坡稳定性的可靠度分析方法, 首先, 在可靠度分析原理的基础上, 对填土边坡的不确定性进行了讨论; 然后, 建立了多变量影响下填土边坡可靠度分析的基本流程; 最后, 以广西平乐县二塘锰矿区典型填土边坡为例, 基于GeoStudio软件, 应用所提出的分析流程对典型填土边坡的可靠度指标进行了计算, 通过"安全概率"对边坡的安全性进行了评价.研究结果表明: (1)填土边坡的不确定性包括内部结构和环境因素两方面, 前者不确定因素来自于填土土体不确定性和边坡的几何特征不确定性, 后者不确定性因素来自于降雨、地震和人工加载等; (2)可靠度分析的基本流程为填土边坡系统不确定性分析、建立可靠度极限状态方程、求解可靠度指标和边坡安全性评价; (3)广西平乐二塘锰矿填土边坡敏感性因素排序为: 内摩擦角Φ＞黏聚力C＞车辆荷载F; (4)考虑50年一遇极值降雨过程, 稳定性系数在降雨12 h达到最小, 其可靠度指标(β)为8.79, 破坏概率为0.根据《滑坡防治工程设计与施工技术规范》所规定的安全系数, 填土边坡的安全概率为69.84%.      

岩石边坡稳定的可靠度分析

在岩石边坡稳定可靠度分析中,利用贝叶斯方法对断层带抗剪强度参数进行分析,充分利用滑动面以外的地质信息和现场实践经验,较好地解决了小样本实验数据问题。可靠度分析采用离散化降维解法,以原工程采用的边坡稳定设计分析方法为基础,编制了相应的ＲＳＳＡＰ程序,在该程序中直接调用原设计程序,确保工程结构的可靠度设计和评价与现行工程设计方法的和谐统一。     

基于粗糙集的支持向量机滑坡易发性评价

区域滑坡易发性评价对灾害中长期预测预报具有重要意义。以三峡库区秭归至巴东段为研究区,利用粗糙集理论对20个初始评价因子进行属性约简,去掉冗余或干扰信息,得到13个核心评价因子,并以此作为支持向量机的输入特征集,构建支持向量机模型,实现滑坡易发性评价。在易发性分区图中高易发区占8.2%,主要分布在童庄河右岸、归州河沿岸、青干河左岸、树坪至范家坪长江右岸、牛口到东壤口长江左岸和巴东附近;不易发区占 52.7%,主要分布于店子湾至巴东旧城以及远离长江水系及植被覆盖度高的区域。通过验证与分析,粗糙集-支持向量机模型在高中易发区中的预测精度为85.6%,其预测能力优于支持向量机模型;与野外调查对比,预测结果与实际情况吻合较好。研究表明,应用粗糙集和支持向量机相结合进行滑坡易发性评价具有预测能力强、计算效率高等优点。     

支持向量机在煤层地应力预测中的应用

为了探讨煤层地应力的有效预测方法,将支持向量机回归方法用于计算煤层最小水平主应力,进而得到最大水平主应力,结合垂向主应力的求取,最终构建地应力的地质模型,实现地应力场的三维可视化。利用灰色关联法筛选出与煤层最小水平主应力关联度最好的测井参数;结果表明,井径测井(CAL)、补偿中子测井(CNL)、自然伽马测井(GR)、密度测井(DEN)和深浅侧向电阻率测井值的平均值(R)与煤层最小水平主应力关联度较好。以这5个测井参数作为训练因子,利用支持向量机回归方法建立煤层最小水平主应力预测模型。基于该模型,对鄂尔多斯盆地韩城区块H3井组煤层地应力进行计算,发现研究区内三个方向的地应力随埋深的增加呈现递增的趋势,应力场状态也随着埋深的变化发生转换,由浅部的大地动力型逐渐转换为大地静力型,煤储层所处的应力环境也相应地由挤压带过渡为伸张带。     

地震多属性综合解释的支持向量机方法研究

能够同时对多种属性进行训练,具有优秀推广能力的支持向量机(Support Vector Machine,简称SVM)方法是进行高精度地震参数预测的有力保障。然而,支持向量机中用于构建回归估计函数的参数最优解很难确定。针对该问题,通过建立数学模型进行参数选择研究,总结出了参数ε、C、σ2对样本预测的影响规律。在此基础上提出了求取惩罚因子C和核参数σ2的权系数公式。结合提出的参数求取公式,利用支持向量机方法,以地震属性为输入向量对渤海SZ36-1油田的砂泥岩百分比和孔隙度进行了预测。结果表明,利用该方法对储层参数进行预测具有较高的预测精度;权系数公式的提出极大地缩短了构建回归估计函数所耗用的时间,简化了参数选取的难度。     

基于成矿条件数值模拟和支持向量机算法的深部成矿预测——以粤北凡口铅锌矿为例

随着计算机科学和地质大数据技术的迅猛发展,数值模拟和机器学习已成为当今地学领域定量发展的重要前沿方向。数值模拟综合运用了研究区地质、构造、地球物理、地球化学等多源信息,将成矿条件与过程进行量化模拟分析,对研究成矿动力学演化过程及成矿响应有重要意义,可对已有成矿要素/信息在时空上进行扩展/外推,扩大了成矿预测信息的广度和深度,为解决深部成矿预测中获取深部信息难题提供了一种可能的有效途径。支持向量机是一种重要的机器学习分类算法,它具有简洁、方便、高效和计算结果较稳定等特点,在众多领域中得以成功应用,是成矿预测中多源信息提取与融合的一种可靠的技术手段。为了充分利用数值模拟与机器学习的优势,本文提出将计算机数值模拟方法和机器学习(即支持向量机算法)相结合来进行深部成矿预测的新方法。以粤北凡口超大型铅锌矿为例,首先,对凡口矿区勘探线剖面进行构造应力场模拟;进而,以已知钻孔数据作为训练集和测试集,运用支持向量机算法对模拟结果中的不同参量(也即模拟所得的成矿条件)进行训练学习;最后,建立相应的定量找矿预测模型对研究区(或剖面)外围和深部找矿进行预测评价。研究结果表明,本文所建立的预测模型精确度和召回...     

多分类支持向量机在滑坡稳定性判识中的应用

如何准确地判识和评价滑坡的稳定性一直是滑坡研究中的关键问题。基于多分类支持向量机的基本理论,利用三峡库区的37个典型滑坡（27个训练样本,10个测试样本）,建立了滑坡稳定性判识的多分类支持向量机模型,并与距离判别分析方法进行了比较。结果表明,SVM模型对测试样本和训练样本的判识准确率均达到100％,而距离判别法对测试样本和训练样本的判识准确率分别为80％和77.8％,前者的判识精度明显优于后者。在此基础上,将SVM模型运用于溪洛渡库区牛滚凼滑坡的稳定性判识中,结果与实际情况吻合较好。     

Classification and Recognition of Polyhalite in Chuanzhong Based on Support Vector Machine

Polyhalite is mainly solid mineral potassium in Sichuan Basin, The most of polyhalite layer in Sichuan region is impurity, and usually accompanied by layers of gypsum, anhydrite, rock salt, and even deposited in the same layer. Conventional logging interpretation method can only roughly identificate polyhalite layers. Based on the theory of Support Vector Machine and logging interpretation methods,this paper creates prediction model with the input of logging curves, and discriminates the polyhalite reservoirs in the lower-middle Triassic strata. Compared with logging data, the accuracy rate of the discrimination results reaches 90%. According to the prediction model, identification model can be established with the curve features of polyhalite to discriminate pure polyhalite reservoirs, gypsiferous polyhalite reservoirs and polyhalite-gypsum reservoirs, the accuracy rate is 91.78%. The study demonstrates that Support Vector Machine is superior to the method of logging interpretation, and it has broad prospects in potash exploration.