一种基于机器学习算法的岩性填图方法

通过野外地质调查与机器学习方法的有机融合,提出了一种基于梯度提升决策树算法的岩性单元填图方法。研究以多龙矿集区为模型试验区,选择1∶5万勘查地球化学数据为基础预测数据,以1∶5万区域地质图为参考,进行基于梯度提升决策树算法的岩性预测填图模型试验。首先选择研究区内小范围空白区开展野外填图,建立原始数据集并初步构建岩性单元与预测数据对应关系;其次利用机器学习方法对预测数据进行多分类任务,进而开展目标填图区预测填图工作;最后通过概率选区选定概率较低目标区,开展进一步的小范围野外地质调查填图,对原始数据和知识库进行补充,迭代循环以上流程,直至预测填图达到要求。试验显示,随着迭代次数的增加,模型精度不断提高,并在7次迭代后模型准确率达到87%。该方法强调在实际应用中野外地质调查与基于机器学习预测填图的深度融合,以及野外实地工作在整个流程中的重要性和不可或缺性;同时能够充分挖掘已有数据资料的有用信息,用于辅助修正已有岩性填图内容,或根据已勘探区资料对邻近的未勘探区进行岩性分类,有效减少野外填图工作量,是对岩性填图方法、地质单元定量预测识别的有益探索,为区域地质填图工作提供了新的参考思路和辅助手段。      

Landslide susceptibility zonation method based on C5.0 decision tree and K-means cluster algorithms to improve the efficiency of risk management

Machine learning algorithms are an important measure with which to perform landslide susceptibility assessments,but most studies use GIS-based classification methods to conduct susceptibility zonation.This study presents a machine learning approach based on the C5.0 decision tree(DT)model and the K-means cluster algorithm to produce a regional landslide susceptibility map.Yanchang County,a typical landslide-prone area located in northwestern China,was taken as the area of interest to introduce the proposed application procedure.A landslide inventory containing 82 landslides was prepared and subse-quently randomly partitioned into two subsets:training data(70％landslide pixels)and validation data(30％landslide pixels).Fourteen landslide influencing factors were considered in the input dataset and were used to calculate the landslide occurrence probability based on the C5.0 decision tree model.Susceptibility zonation was implemented according to the cut-off values calculated by the K-means clus-ter algorithm.The validation results of the model performance analysis showed that the AUC(area under the receiver operating characteristic(ROC)curve)of the proposed model was the highest,reaching 0.88,compared with traditional models(support vector machine(SVM)=0.85,Bayesian network(BN)=0.81,frequency ratio(FR)=0.75,weight of evidence(WOE)=0.76).The landslide frequency ratio and fre-quency density of the high susceptibility zones were 6.76/km2 and 0.88/km2,respectively,which were much higher than those of the low susceptibility zones.The top 20％interval of landslide occurrence probability contained 89％of the historical landslides but only accounted for 10.3％of the total area.Our results indicate that the distribution of high susceptibility zones was more focused without contain-ing more"stable"pixels.Therefore,the obtained susceptibility map is suitable for application to landslide risk management practices.     

基于逆推法和德尔菲法的地质灾害气象服务效益评估

地质灾害气象服务发挥越来越重要的作用,既有可量化的经济效益,也有不可忽视难以量化的、潜在的社会效益和生态效益。根据历年地质灾害调查与分析数据,运用逆推法结合德尔菲法,建立地质灾害气象服务效益评估模型,并根据已有研究及防汛经验对模型的系数进行量化。模型以地质灾害气象预报评分和灾害直接经济损失为输入,以防灾减灾效益值、防灾减灾效益百分率、气象服务直接经济效益、气象服务直接经济效益百分率为输出,可同时对各区域、各时间段的地质灾害过程进行气象服务效益分段评估,也可评估年度地质灾害气象服务效益。该模型在2017年地质灾害气象效益评估中表现良好,有一定指导意义。     

我国中东部平原地区临界气温条件下降水相态判别分析

基于2001—2013年地面观测和探空资料,对地面气温位于0～2℃(以下称临界气温)我国降雪的时空分布及其与降雨的垂直热力特征进行了研究,引入了决策树判别方法对上述条件下雪和雨进行了判别分析,结果表明:临界气温下降雪出现频率总体高于降雨、雨夹雪出现频率,且在我国华北南部至江南北部的中东部地区分布较多,年均可达7.69～15.38站次;临界气温下,降水相态为雨或雪对应的平均温度廓线最大差异位于650 hPa附近,且地面气温较低时,平均温度差异更明显,平均湿度廓线差异则主要位于低层,且在地面气温较高时,平均湿度差异更明显;临界气温下,降水相态为雨时,地面上空存在暖层样本占比,较降水相态为雪时更高,且降雨时暖层主要位于中层,降雪时暖层则主要位于低层,降雨时其暖层强度显著大于降雪时暖层强度;在临界气温下雨雪判别分析中,地面气温能显著提升判别准确率,湿球温度能在一定程度上提升判别准确率,基于云顶温度、中层融化参数、低层湿球温度构建的决策树判别模型,判别准确率达到91.86%,能较好地解决临界气温下雨和雪的判别问题。     

气象因子对半冬性小麦灌浆速度的影响效应研究

选用黄淮海冬麦区4个半冬性小麦品种郯麦98、山农18、徐麦33、皖麦52为试验材料,通过分期播种试验,利用方差分析、相关分析、逐步回归和通径分析等方法,分析半冬性小麦籽粒灌浆速度变化趋势和气象因子对灌浆速度的影响。结果表明,正常播期冬小麦灌浆速度波动性最小、千粒重最大,迟播10 d冬小麦灌浆速度波动性最大、千粒重最小;华北区品种郯麦98灌浆速度表现最稳定、千粒重最高,而黄淮区品种皖麦52灌浆速度最大;半冬性小麦灌浆持续期为35～39 d;南北气候差异是影响各品种冬小麦灌浆速度不同的原因之一。半冬性小麦各播期灌浆速度的变化趋势一致,灌浆速度变化与相关显著气象因子的变化规律相符合;灌浆速度峰值期一般出现在开花后15～25 d,迟播冬小麦最大灌浆速度出现时间较对照处理提前,不利于提高粒重;气温条件对冬小麦灌浆速度影响显著,其中最高气温要素是影响不同播期品种灌浆速度的共有关键因子。通径分析表明,最高气温对灌浆速度的作用由自身的直接效应决定,而日照时数与最低气温对灌浆速度的作用与间接效应一致;最高气温平均值对灌浆速度的影响最重要,日照时数和最低气温平均值对灌浆速度的影响较弱;最高和最低气温平均值、日照时数均为灌浆速度的限制因子,其中最高气温平均值对灌浆速度变化的决策作用最大。     

Explicit integration of a porosity‐dependent hydro‐mechanical model for unsaturated soils

An adaptive substepping explicit integration scheme is developed for a porosity‐dependent hydro‐mechanical model for unsaturated soils. The model is referred to as the modified σ –Θ model in this paper, which features the employment of the subloading surface plasticity and the stress–saturation approach. On numerical aspects, convex/nonconvex subloading surfaces in the σ –Θ space may result in incorrect loading–unloading decisions during the integration. A new loading–unloading decision method is developed here to solve the problem and then embedded into the explicit integration scheme for the modified σ –Θ model. In addition, to enhance the accuracy of the explicit integration, local errors from both hydraulic and mechanical components are included in the error control for each substep. A drift correction method is also developed to ensure the state point lies on the subloading surface in the σ –Θ space within a set error level. The performance of the loading–unloading decision method for the modified σ –Θ model is discussed through comparing it with the conventional loading–unloading decision method. The importance of involving the hydraulic component in the error control is also demonstrated. The accuracy and efficiency of the proposed adaptive substepping explicit integration scheme for the modified p–Θ model are also studied via several numerical examples. Copyright © 2016 John Wiley & Sons, Ltd.     

专题制图决策支持系统的设计

专题制图中有很多决策问题,如何建立一个专题制图决策支持系统是本文要讨论的问题。本文对下面的问题进行了讨论和介绍;专题制图决策支持系统的总体设计、子系统间的信息交换、地图表达手段、数据处理方法等。     

The Location of Office Space in the Metropolitan Service Economy of the United States, 1985–1990

As the economic base of most American metropolitan areas relies increasingly on services, office industries have shifted to a more pivotal role in the new metropolitan service economy. Using primary office-space usage data of the time period 1985–1990, the changing spatial patterns of this new metropolitan service economy are investigated. It is found that the primary office activities are predominantly concentrated in a relatively small number of the largest metropolitan areas. However, an emerging spatial dispersion in primary office activities is also exhibited. Such dispersion is extremely strong at the upper end of the urban hierarchy. The Sunbelt-Snowbelt dichotomy fails to reveal any differences in the growth pattern of the new metropolitan service economy. A more diversified growth pattern of primary office activities is observed. Concentrated dispersion is the major spatial characteristic of this new metropolitan service economy.     

艾比湖湿地调节气候生态服务价值评价

增湿调温的气候调节功能是湿地重要的生态功能。位于干旱区的湿地,其增湿调温功能尤为明显。湿地自由水面巨大的水汽蒸发及湿地茂密植被剧烈的水汽蒸腾,是其增湿调温、调节气候的主要物质基础。通过计算艾比湖湿地年水汽蒸发、蒸腾量,得出其每年调节气候的生态服务价值为97788.86×104元,占艾比湖湿地总生态服务价值的31.9%,位居研究区各项生态价值之首。结果表明,增湿调温的气候调节功能是处于极端干旱地理条件下的艾比湖湿地最重要的生态服务功能。     

Utility Efficient Frontier: An Application in the Oil and Gas Industry

Current practice shows that the use of portfolio and utility theory is very low among petroleum companies. This article advocates the use of both portfolio theory and utility theory as decision-making tools to improve performance of oil and gas companies. We introduce a model that can be practically used and applied in the oil and gas industry. This model generates an optimized, efficient portfolio and, at the same time, enables the decision maker to incorporate his risk attitude and policy. This can only be done by combining both the portfolio theory and utility theory through an approach called the utility mean-variance model. A typical oil portfolio optimization problem is investigated by applying both portfolio and utility theories. Through the utility mean-variance model, an efficient frontier that captures decision maker risk attitude is achieved.