基于EMD的景区客流波动特征及其组合预测——以黄山风景区为例

旅游地的发展演化过程研究大多采用Bulter 的生命周期理论路径, 少有文献从波动的视角理解和分析旅游地的发展演化过程。本文以黄山风景区为例, 采用经验模态分解方法(EMD)尝试从波动的视角分析景区客流波动特征, 并利用波动性特征对其发展进行组合预测(经验模态分解方法和最小二乘支持向量机方法的组合)。研究结果表明:黄山景区客流波动呈现出多种形态, 在增长趋势的基础上叠加了季节性波动、景区旅游周期波动和景区经济周期波动。其与最小二乘支持向量机组合预测模型能够对景区客流进行有效预测, 并且运算速度快, 预测精度有所提高;与生命周期曲线相比较更加直观、微观、准确, 并且能够进行较为准确的客流预报, 有助于景区规划管理和战略决策。     

遗传算法优化的支持向量机湿地遥感分类——以洪河国家级自然保护区为例

湿地遥感分类作为湿地管理、监测与评价的重要手段,受到了广泛的关注。遗传算法(GA)借鉴了生物进化规律进行启发式搜索寻优,支持向量机(SVM)是一种新型的空间数据挖掘方法,二者相结合可以发挥各自的优势,寻找到支持向量机的全局最优参数,从而较准确地对湿地进行遥感分类。以洪河自然保护区为例,采用遗传算法优化的支持向量机方法进行了湿地遥感分类研究。同格网搜索下的支持向量机湿地遥感分类及最大似然监督分类对比,结果表明,遗传算法优化较格网搜索方式总精度提高了7.29%,较最大似然监督分类提高了12.06%,方法改善了沼泽、草地与裸地三种地物间的区分,是湿地遥感分类的有效手段。     

南京地区冬季路面结冰天气标准及其预测

本文通过对南京地区1984—2003年20 a 110个降水结冰样本当日温度的统计分析,讨论了南京地区结冰时间变化和各影响温度的变化规律,总结了对结冰预报具有指示意义的关键因子;同时利用支持向量机方法探讨了南京地区结冰预报方法,该方法具有显著的预报价值。在此基础上根据Norrman提出的路面打滑分类,结合南京地区具体情况得出了南京雨雪天气路面结冰的类别、标准和预测预报方法。     

SVM方法在武汉区域夏季暴雨预报业务中的应用

以2003～2006年ECMWF数值预报产品、Japan和T213降水预报场资料为基础,应用支持向量机（SVM）方法和CMSVM应用软件平台,通过对训练样本进行交叉验证和模型核参数的逐渐逼近,分区建立了武汉区域16,个区SVM24h暴雨预报模型,并在武汉区域5～7月进行实时业务应用。通过预报结果检验,5～7月武汉区域暴雨预报TS评分为33．59％,其中湖北省平均成绩为34．69％、湖南省平均成绩为34．15％、河南省平均成绩为31．71％。检验结果较好,表明SVM方法在区域性暴雨预报中具有一定的预报能力和参考价值。     

双流机场低能见度天气预报方法研究

在信息量较大, 而预报对象与预报因子的关系又不清楚的状况下, 智能机器学习方法是解决这类问题的较好手段。利用1997—2001年成都站的常规探空资料和双流机场的地面观测资料, 使用支持向量机 (Support Vector Machines, 简称SVM) 方法, 选取多种核函数进行双流机场低能见度天气的预报建模试验。测试结果表明:以径向基函数和拉普拉斯函数构造的SVM预报模型实验效果最好, Ts评分分别为0.287和0.292, 远高于双流机场低能见度天气出现的频率 (0.155)。试验结果还表明:以径向基函数构造的SVM预报模型空报较多, 漏报较少; 而以拉普拉斯函数构造的SVM预报模型空报较少, 漏报较多。因此, 如果强调模型对低能见度天气预报的准确性, 则应采用以拉普拉斯函数构造的预报模型, 如果强调对低能见度天气的预防性, 则应采用以径向基函数构造的预报模型。     

支持向量机与卡尔曼滤波集合的西太平洋副热带高压数值预报误差修正

基于T106数值预报产品资料,提出了支持向量机和卡尔曼滤波相结合的方法来进行夏季西太平洋副热带高压数值预报的误差修正与预报优化。首先采用支持向量机方法建立了西太平洋副热带高压面积指数的误差修正模型。基于支持向量机预报优化模型尽管有比较好的拟合精度和预报效果,但与实际副热带高压指数尚有一定的差异。究其原因,除预报对象(副热带高压)本身比较复杂、模型优化因子不够充分以及数值预报误差自身的随机性以外,优化模型的输入、输出基本上是一个静态映射结构,因此前一时刻的预测误差难以得到有效的反馈、调整和修正。为考虑前一时刻预报误差的反馈信息,动态跟踪副高的变化趋势,随后引入卡尔曼滤波方法建立支持向量机-卡尔曼滤波模型,对支持向量机模型的输出结果作进一步的调整和优化。试验结果表明,该方法模型的预报优化效果优于T106数值预报产品以及单纯的神经网络修正模型和卡尔曼滤波修正模型的优化效果,能够较为客观、有效地修正西太平洋副热带高压指数的数值预报误差,改进和优化西太平洋副热带高压的数值预报效果。该方法为副热带高压等复杂天气系统和要素场预报提供了一种新的思路,表现出较好的应用前景。     

Using pan-sharpened high resolution satellite data to improve impervious surfaces estimation

Impervious surface is an important environmental and socio-economic indicator for numerous urban studies. While a large number of researches have been conducted to estimate the area and distribution of impervious surface from satellite data, the accuracy for impervious surface estimation (ISE) is insufficient due to high diversity of urban land cover types. This study evaluated the use of panchromatic (PAN) data in very high resolution satellite image for improving the accuracy of ISE by various pan-sharpening approaches, with a further comprehensive analysis of its scale effects. Three benchmark pan-sharpening approaches, Gram-Schmidt (GS), PANSHARP and principal component analysis (PCA) were applied to WorldView-2 in three spots of Hong Kong. The on-screen digitization were carried out based on Google Map and the results were viewed as referenced impervious surfaces. The referenced impervious surfaces and the ISE results were then re-scaled to various spatial resolutions to obtain the percentage of impervious surfaces. The correlation coefficient (CC) and root mean square error (RMSE) were adopted as the quantitative indicator to assess the accuracy. The accuracy differences between three research areas were further illustrated by the average local variance (ALV) which was used for landscape pattern analysis. The experimental results suggested that 1) three research regions have various landscape patterns; 2) ISE accuracy extracted from pan-sharpened data was better than ISE from original multispectral (MS) data; and 3) this improvement has a noticeable scale effects with various resolutions. The improvement was reduced slightly as the resolution became coarser.     

Progress of Research on the Support System for Economic Growth

China has achieved a long-term and high-speed growth in terms of national economy, but faces a series of highlighted problems concerning economic growth and resource and environment support. This paper summarizes the progress of research on economic growth and its support system (resource and environment) mainly from the perspective of geography, and puts forward the main research direction of the support system for economic growth in future.     

Integrating economy, ecology and uncertainty in an oil-spill DSS: The Prestige accident in Spain, 2002

Major accidental oil spills still affect sensitive marine areas and shorelines around the world, constituting a challenge for operational as well as strategic contingency management. As a rationale basis for addressing both issues we here propose a Decision Support System (DSS) consisting of a combination of modelling and evaluation methods which in particular assesses various impacts on habitats and local economies. By integrating the state-of-the-art oil spill contingency simulation system OSCAR with wind and current forecasts, environmental GIS data and multi-criteria analysis techniques, the DSS is able to rank different response actions to a chemical or oil spill. In this study, the usefulness of the approach is tested by hindcasting the Prestige accident off the coast of Spain in 2002. In particular, the short- to mid-term economic and ecological consequences of different mitigation measures are estimated. We identified clearly one worst option matching the actual decision taken by the responsible parties and one or two almost equally well performing routes. Two procedures of including uncertainty at various stages of the DSS are tested. The first method averages ensembles of outcomes between each modelling/evaluation stage, while the second one preserves the entire degree of freedom till the final ranking procedure. Results in the Prestige case turned out to be rather insensitive against both ways to account for uncertainties. The robustness as well as clarity of the DSS has the potential to enhance the efficiency of decision making even in politically sensitive situations. Limitations as well as ongoing improvements of the system are highlighted, in particular emphasizing linkages to environmental economics.     

Forced vibration analysis of an offshore tower carrying an eccentric tip mass with rotary inertia due to support excitation

Dynamic responses of structures due to earthquake excitation are the important problems in engineering, thus, the information concerned is plenty. However, most of the literature is relating to the discrete methods, particularly to the finite element method (FEM), and the one relating to the method combining both the “continuous” and “discrete” models is rare. The objective of this paper is to provide some information in this respect. First, the analytical solution for the natural frequencies and normal mode shapes of a “continuous” tower, without contacting water (or “dry” tower), carrying an eccentric tip mass possessing rotary inertia is determined. Next, the partial differential equation of motion for the forced vibration of the tower, contacting water (or “wet” tower), subjected to support excitation is transformed into a matrix equation by using the last natural frequencies and normal modes shape of the freely vibrating dry tower. Finally, the numerical integration method is used to solve the matrix equation to yield the seismic response of the wet tower. In theory, the mode superposition method is correct only if the total number of modes considered approaches infinity, however, numerical results of this paper reveal that superposition of only the lowest six modes will yield excellent results to be very close to the corresponding ones obtained from the conventional FEM. For this reason, the CPU time required by the presented approach is less than 5% of that required by the conventional FEM.