采用非线性决策树的学生课堂教学满意度研究

学生反馈是评估高等院校课堂教学质量的重要指标。目前,对学生反馈的问卷仅进行主观理解和简单统计,无法提供准确定量的分析和支持依据。使用非线性决策树,对近3年本科必修双语课程《数字图像处理》的学生评教问卷进行数据挖掘,首先将其分成3类和10个不同输入,然后通过数据预处理、模型选择和建模,最后构建树状模型对其进行分析。分析结果符合对于该课程学生反应和争议较大的问题预期,为课程设计提供定量有效的教学分析工具。     

基于ENVI 的唐山湾三岛土地利用遥感分类方法的比较分析

对唐山湾三岛2010年10月10 m分辨率的SPOT5多光谱数据源,采用不同分类方法进行识别和判断,并对比不同分类器在遥感影像分类中的应用效果和分类精度。有针对性地探究海岛土地利用遥感分类过程中不同方法的优劣,获取最适于岛陆地区土地利用的遥感分类方法。根据土地利用现状分类标准(GB/T21010-2007)和海岛陆域土地利用类型划分的相关规定,将唐山湾三岛主要分为滩涂、裸地、林地、草地、居住区、内陆水体和潮间带(潮水覆盖区)6类。并分别构建结合人为控制的非监督分类、监督分类和基于专家知识的决策树分类系统,参照更高分辨率影像、先验知识和野外调查资料,评价分类结果与实地调查结果的吻合程度,最终通过总体分类精度和Kappa系数等指标对各分类器精度进行评价和对比分析。     

Forest law enforcement in the Brazilian Amazon: Costs and income effects

Despite recent success in reducing forest loss in the Brazilian Amazon, additional forest conservation efforts, for example, through ‘Reducing Emissions from Deforestation and Forest Degradation’ (REDD+), could significantly contribute to global climate-change mitigation. Economic incentives, such as payments for environmental services could promote conservation, but deforestation often occurs on land without crucial tenure-security prerequisites. Improving the enforcement of existing regulatory disincentives thus represents an important element of Brazil's anti-deforestation action plan. However, conservation law enforcement costs and benefits have been much less studied than for conditional payments. We develop a conceptual framework and a spatially explicit model to analyze field-based regulatory enforcement in the Brazilian Amazon. We validate our model, based on historical deforestation and enforcement mission data from 2003 to 2008. By simulating the current conservation law enforcement practice, we analyze the costs of liability establishment and legal coercion for alternative conservation targets, and evaluate corresponding income impacts. Our findings suggest that spatial patterns of both deforestation and inspection costs markedly influence enforcement patterns and their income effects. Field-based enforcement is a highly cost-effective forest conservation instrument from a regulator's point of view, but comes at high opportunity costs for land users. Payments for environmental services could compensate costs, but will increase budget outlays vis-à-vis a command-and-control dominated strategy. Both legal and institutional challenges have to be overcome to make conservation payments work at a larger scale. Decision-makers may have to innovatively combine incentive and disincentive-based policy instruments in order to make tropical forest conservation both financially viable and socially compatible.     

结合地形因子与分层策略的喀斯特地区无人机影像分类

西南喀斯特山区地形起伏较大,地物分布较为破碎,致使传统的光谱特征一次分类方法的精度较低。本文基于高分辨率无人机正射影像和地形指标,充分利用无人机遥感影像空间特征、光谱特征、纹理特征及地形特征,采取面向对象CART决策树算法与分层策略提取了研究区土地覆盖类型。研究表明,结合空间地形因子和分层策略的方法减少了破碎区地物间的相干扰,故具有较高的分类精度,总体分类精度达91.2%,Kappa系数为0.87,较传统一次分类精度提高了9.8%,Kappa系数提高了0.13。该方法对西南喀斯特地区土地覆盖解译精度较好,可为土地利用监测提供参考。     

层次分析及 GIS空间分析在矿山岩溶塌陷预测评估中的应用--以某大理石矿为例

以某大理石矿矿山地质环境调查资料为基础,通过对矿山岩溶塌陷的机理分析,采用层次分析法,选取地下水活动、覆盖层特征、岩溶发育程度和人类活动强度四个方面,共6个评价指标,建立某大理石矿岩溶塌陷预测评估体系。在确定各评价指标权重和各评价因子分级标准的基础上,以 MAPGIS 空间分析作为数据处理工具和系统运行平台,生成某大理石矿岩溶塌陷易发性分区图。     

The critical scale of fluctuation for active lateral forces in spatially variable undrained clays

This study addresses the phenomenon of the critical scale of fluctuation (SOF) for active lateral force (P_a) in undrained clay when there is a spatial variability in the clay. The phenomenon is significant under shear strength (τ_f) random fields but is insignificant under unit weight (γ) random fields. It is found that the phenomenon of the critical SOF is connected to the nature of the spatial averaging, which is “line averaging” under τ_f random fields and is “area averaging” under γ random fields. The former averaging effect (line) is significantly weaker than the latter (area), so the tendency for the critical slip plane to seek for a favorable location is stronger for the τ_f random field than for the γ random field. Hence, the phenomenon of the critical SOF is more pronounced under τ_f random fields than under γ random fields. The underlying mechanisms for the phenomenon of the critical SOF will be explored in this paper.     

Reliability analysis of piles in spatially varying soils considering multiple failure modes

In most limit state design codes, the serviceability limit checks for drilled shafts still use deterministic approaches. Moreover, different limit states are usually considered separately. This paper develops a probabilistic framework to assess the serviceability performance with the consideration of soil spatial variability in reliability analysis. Specifically, the performance of a drilled shaft is defined in terms of the vertical settlement, lateral deflection, and angular distortion at the top of the shaft, corresponding to three limit states in the reliability analysis. Failure is defined as the event that the displacements exceed the corresponding tolerable displacements. The spatial variability of soil properties is considered using random field modeling. To illustrate the proposed framework, this study assesses the reliability of each limit state and the system reliability of a numerical example of a drilled shaft. The results show the system reliability should be considered for the serviceability performance. The importance measures of the random variables indicate that the external loads, the performance criteria, the model errors of load transfer curves and soil strength parameter are the most important factors in reliability analysis. Moreover, it is shown that the correlation length and coefficient of variation of soil strength can exert significant impacts on the calculated failure probability.     

基于腹地划分的中国城市群空间影响范围识别

城市群空间影响范围的界定是认清城市群内中心城市与腹地、城市与城市间相互关联的基础。采用主成分分析法计算中国287个地级及以上城市的结节性指数,利用累积耗费距离法和k阶数据场,综合测度了交通可达性与空间场能,根据场强"取大"原则对城市腹地进行了划分,依据城市腹地范围界定了城市群的空间影响范围。结果表明:①中国地级以上城市最大和最小结节性指数相差157.53倍,城市平均可达时间为193.43 min,场能平均值为5 412,最大和最小城市腹地相差3 751倍;②23个城市群中,空间影响范围最大的是北疆城市群,空间平均场强最大的是中原城市群;③城市群在空间上呈现为发育程度不同的"11+9+3"的分布格局和逆时针90°旋转的"β"型城市群连绵带发展格局;④基于腹地划分的城市群空间影响范围充分考虑了现实的交通网络和地形地貌特点,实现了对广域空间范围内城市腹地范围和城市群空间影响范围的定量测度。     

三维辅助决策平台功能设计及数据建设研究

三维数据由于其直观、精细的特性成为数字城市建设中不可或缺的部分,三维辅助决策平台也成为近年来信息化建设的重要方面。本文从三维辅助决策平台建设时的功能设计和数据建设两个方面进行阐述,对其中运用的技术进行研究。最后,给出了针对不同应用领域系统建设的示例。     

Bayesian area-to-point kriging using expert knowledge as informative priors

Area-to-point (ATP) kriging is a common geostatistical framework to address the problem of spatial disaggregation or downscaling from block support observations (BSO) to point support (PoS) predictions for continuous variables. This approach requires that the PoS variogram is known. Without PoS observations, the parameters of the PoS variogram cannot be deterministically estimated from BSO, and as a result, the PoS variogram parameters are uncertain. In this research, we used Bayesian ATP conditional simulation to estimate the PoS variogram parameters from expert knowledge and BSO, and quantify uncertainty of the PoS variogram parameters and disaggregation outcomes. We first clarified that the nugget parameter of the PoS variogram cannot be estimated from only BSO. Next, we used statistical expert elicitation techniques to elicit the PoS variogram parameters from expert knowledge. These were used as informative priors in a Bayesian inference of the PoS variogram from BSO and implemented using a Markov chain Monte Carlo algorithm. ATP conditional simulation was done to obtain stochastic simulations at point support. MODIS (Moderate Resolution Imaging Spectroradiometer) atmospheric temperature profile data were used in an illustrative example. The outcomes from the Bayesian ATP inference for the Matérn variogram model parameters confirmed that the posterior distribution of the nugget parameter was effectively the same as its prior distribution; for the other parameters, the uncertainty was substantially decreased when BSO were introduced to the Bayesian ATP estimator. This confirmed that expert knowledge brought new information to infer the nugget effect at PoS while BSO only brought new information to infer the other parameters. Bayesian ATP conditional simulations provided a satisfactory way to quantify parameters and model uncertainty propagation through spatial disaggregation.