基于色度平面的自适应颜色聚类

本文的目标是寻找具有更高灵活性和自适应性的颜色聚类方法。在分析了多种颜色聚类方法的基础上 ,提出了 2种无监督的二维色度平面颜色聚类方法 :基于密度的三角化方法和遗传算法优化方法 ,并通过实验对 2种方法进行了比对分析。结果表明 ,基于密度的三角化方法具有很好的边界拟合效果 ,而遗传算法优化对于复杂的数据集和解决干扰噪声有更好的效果。     

Estimation of pile group scour using adaptive neuro-fuzzy approach

An accurate estimation of scour depth around piles is important for coastal and ocean engineers involved in the design of marine structures. Owing to the complexity of the problem, most conventional approaches are often unable to provide sufficiently accurate results. In this paper, an alternative attempt is made herein to develop adaptive neuro-fuzzy inference system (ANFIS) models for predicting scour depth as well as scour width for a group of piles supporting a pier. The ANFIS model provides the system identification and interpretability of the fuzzy models and the learning capability of neural networks in a single system. Two combinations of input data were used in the analyses to predict scour depth: the first input combination involves dimensional parameters such as wave height, wave period, and water depth, while the second combination contains nondimensional numbers including the Reynolds number, the Keulegan–Carpenter number, the Shields parameter and the sediment number. The test results show that ANFIS performs better than the existing empirical formulae. The ANFIS predicts scour depth better when it is trained with the original (dimensional) rather than the nondimensional data. The depth of scour was predicted more accurately than its width. A sensitivity analysis showed that scour depth is governed mainly by the Keulegan–Carpenter number, and wave height has a greater influence on scour depth than the other independent parameters.     

APPLICATION OF THE CLUSTERING METHOD IN ANALYSING SHALLOW WATER MASSES AND MODIFIED WATER MASSES IN THE HUANGHAI SEA AND EAST CHINA SEA

The idea of modified water masses is introduced and a cluster analysis is used for determining the boundary of modified water masses and its variety in the shallow water area of the Huanghai Sea (Yellow Sea) and the East China Sea. According to the specified standards to make the cluster, we have determined the number and boundary of the water masses and the mixed zones.The results obtained by the cluster method show that there are eight modified water masses in this area. According to the relative index of temperature and salinity,the modified water masses are divided into nine different characteristic parts. The water, masses may also be divided into three salinity types. On the TS-Diagram, the points concerning temperature and safinity of different modified mater masses are distributed around a curve, from which the characteristics of gradual modification may be embodied. The variation ranges of different modified water masses are all large, explaining the intensive modification of water masses in th     

夏季南海水团垂直分布的聚类分析研究

以南海夏季不同深度层次的各站位的温度，盐度，pH，O2，硝酸盐，亚硝酸盐，铵，磷酸盐，硅酸盐等水化学参数作为变量，实施Q型多维聚类分析，聚类分析结果表明，在垂直方向上，南海的水团可划分为南海表层水，南海次表层水，南海中层水，南海深层水和南海深海盆水等5种类型，聚类分析结果与温盐点聚图解所得的结论完全一致，南海夏季调查的多维聚类分析及T－S点聚图一致表明，南海的海水有着良好的成层结构，自海面至海底的水体运动自然形成了化学性质各异的五个水团。     

南海北部海区水团分析

以模糊聚类为主要方法,在南海北部海区划出8个水团:沿岸冲淡水团(F)、近岸混合水团(M)、暖表层水团(WS)、表层水团(S)、表-次层混合水团(SU)、次层水团(U)、次-中层混合水团(UI)和中层水团(I).对各水团的形成、基本特征、变性特点以及消长变化和分布规律进行了综合分析.可将它们分为3种类型:径流冲淡型——F,浅海变性型——M、WS、S、SU和深海大洋型——U、UI和I.     

北黄海及渤海变性水团的初步分析

根据1978—1980年渤海及北黄海70个测站的表、底层温、盐资料,用预先给定控制临界值的聚类方法,在该海域划分出5个水团。分析结果表明。1.渤黄海暧水团在冬季为高盐特征,夏季为中盐性质;其分布范围在冬—春季较小而夏—秋季较大。2.渤海水团为中温中盐性质:其温、盐度变化较小而冬—春季范围较大。3.黄海冷水团是一个高盐水团,它在5个水团中保守性最强,而从5月至8月范围较大。4.渤海沿岸水是一个不稳定的水团,其盐度较低,温度变化较小,春季和秋季范围较大而夏季和冬季较小。5.江河冲淡水是温度变化较大的低盐水,其范围夏季大而冬季小。水团的分布,在地理位置上是从该海区之东向西,一层套一层,而各水团在不同季节有自己的模式。此外,本文还探讨了水团消长变化和渔场的关系。     

Objective classification of oceanic ridge-crest terrains using two-dimensional spectral models of bathymetry: Application to the Juan de Fuca Ridge

An important application of detailed bathymetric mapping is the interpretation of geological processes based on the nature of the fine-scale morphology of the seafloor. This interpretation is usually accomplished through qualitative analysis of contour maps. In this paper, an objective classification technique, based on a two-dimensional spectral model of bathymetry developed by Fox and Hayes (1985) is applied to detailed Sea Beam data from the Juan de Fuca Ridge. Parameters of the model can be directly related to seafloor properties corresponding to 1) isotropic (non-directionally dependent) roughness; 2) anisotropic (directionally dependent) roughness; 3) orientation of the anisotropic component; and 4) spectral rool-off ( fractal dimension), by fitting the model surface to two-dimensional amplitude spectra of bathymetry determined on a regular grid over the study area. A test area was selected which encompasses the southern volcanic rift zone of Axial Volcano and the northern terminus of the Vance Segment. Parameters of the model clearly define the contrast between the constructional volcanic terrain (rough, isotropic, with high fractal dimension) and the tectonic extensional terrain (smoother, anisotropic, with low fractal dimension). An agglomerative, hierarchical cluster analysis is applied to the data, independent of spatial information, to delineate groups of spectra with similar characteristics. Distinct, mappable regions, corresponding to volcanic and tectonic provinces, are objectively determined. Also, coherent sub-regions of consistent spectral properties occur within the larger volcanic/tectonic divisions. The classification is extended to the Juan de Fuca Ridge system from 44°30 N to 47°20 N through combining these results with an a priori technique (K-means clustering). Broad-scale physiographic regions of the Juan de Fuca Ridge are delineated by the technique, which may aid geologists in the interpretation of crustal accretion processes at seafloor spreading centers.The U.S. Government right to retain a non-exclusive royaltyfree license in and to any copyright is acknowledged.     

Climatological Tools for Low Visibility Forecasting

Forecasters need climatological forecasting tools because of limitations of numerical weather prediction models. In this article, using Finnish SYNOP observations and ERA-40 model reanalysis data, low visibility cases are studied using subjective and objective analysis techniques. For the objective analysis, we used an AutoClass clustering algorithm, concentrating on three Finnish airports, namely, the Rovaniemi in northern Finland, Kauhava in western Finland, and Maarianhamina in southwest Finland. These airports represent different climatological conditions. Results suggested that combining of subjective analysis with an objective analysis, e.g., clustering algorithms such as the AutoClass method, can be used to construct climatological guides for forecasters. Some higher level subjective “meta-clustering” was used to make the results physically more reasonable and easier to interpret by the forecasters.     

井资料聚类联合地震属性优化储层预测方法

针对单纯地震属性优化方法储层预测符合率低的实际情况,运用井资料聚类联合地震属性优化方法,对临江地区双30区块进行储层预测。依据井砂岩厚度发育情况及空间分布分为Ⅰ类井和Ⅱ类井。Ⅰ类井与Ⅱ类井实钻砂岩厚度与地震预测砂岩厚度相关系数分别为0.81237和0.6889,全区55口井砂岩厚度与地震预测砂岩厚度相关系数由原来的0.513提高到0.794,储层预测符合率由64%提高到80%。     

强台风“云娜”灾害特征及其评估

根据0414号台风“云娜”灾情调查,使用模糊聚类方法对1949~2004年影响浙江省的重大台风灾害进行分析比较,认为台风“云娜”是浙江省1956年以来所遭遇的最严重台风灾害。综合评估结论:①建国以来台风灾害损失与工农业总产值的比值呈上升趋势,台风“云娜”造成的经济损失与当年生产总值之比为3.54:100;②风暴潮为沿海台风灾害的主要因子,建成标准海塘后,大风上升为首要致灾因子;③沿海农村新建(构)筑物和城市广告牌在台风“云娜”中安全问题突出,民营企业抗灾能力也凸显薄弱环节。