Extending self-organizing maps for supervised classification of remotely sensed data

An extended self-organizing map for supervised classification is proposed in this paper. Unlike other traditional SOMs, the model has an input layer, a Kohonen layer, and an output layer. The number of neurons in the input layer depends on the dimensionality of input patterns. The number of neurons in the output layer equals the number of the desired classes. The number of neurons in the Kohonen layer may be a few to several thousands, which depends on the complexity of classification problems and the classification precision. Each training sample is expressed by a pair of vectors ： an input vector and a class codebook vector. When a training sample is input into the model, Kohonen＇s competitive learning rule is applied to selecting the winning neuron from the Kohouen layer and the weight coefficients connecting all the neurons in the input layer with both the winning neuron and its neighbors in the Kohonen layer are modified to be closer to the input vector, and those connecting all the neurons around the winning neuron within a certain diameter in the Kohonen layer with all the neurons in the output layer are adjusted to be closer to the class codebook vector. If the number of training sam- ples is sufficiently large and the learning epochs iterate enough times, the model will be able to serve as a supervised classifier. The model has been tentatively applied to the supervised classification of multispectral remotely sensed data. The author compared the performances of the extended SOM and BPN in remotely sensed data classification. The investigation manifests that the extended SOM is feasible for supervised classification.     

Characteristics and evolution of lacustrine turbidite of Chang-7 Member of Yanchang Formation in northern Shaanxi

Lacustrine turbidite of Chang-7 Member in the studied area consists of sihstone and fine sandstone with respect to grain size, which is feldspathic lithie sandstone, syrosem arkose and arkose with respect to mineral constitution affected by provenance. There are such apparent signatures as lithology, sedimentary structure, sedimentary sequence and well logs, to recognize turbidite. During the paleogeographic evolution of Chang-7 Member, lake basin and deep lake are both at their maximum extent during Chang-73 stage, resulting in the deposition of Zhangjiatan shale with widespread extent and of turbidite with fragmental-like. Deep lake line is gradually moving toward lake center and turbidite sand bodies are gradually turning better with better lateral continuity, connectivity and more thickness, from stages of Chang-73, Chang-72 and Chang-7t, which can be favorable reservoir in deep-water.     

地下水位对定点形变观测干扰的抽水实验

抽水所造成的地下水位的变化会即时在局部范围内造成地表的形变，干扰定点地壳形变观测。在蓟县地震台进行的抽水实验表明：这种干扰的幅度与抽水水井到形变监测仪器的距离有关，也和抽水水井水位的最大降深有关。根据实验数据得到了抽水对定点形变观测的影响范围的经验公式。     

山区遥感图像自动分类研究——以西南地区为例(英文)

In mountainous areas, it is the undulant terrain, various types of geomorphic and land use that make the remote sensing images great metamorphism. Moreover, due to the elevation, there are many areas covered with shadow, clouds and snow that make the images more inaccurate. As a result, it would be very difficult to carry out auto-classification of RS images in these areas. The study took Southwest China as the case study area and the TM images, SPOT images as the basic information sources assisted by the a...     

An internal-external optimized convolutional neural network for arbitrary orientated object detection from optical remote sensing images

Due to the bird's eye view of remote sensing sensors, the orientational information of an object is a key factor that has to be considered in object detection. ...     

Study on Flow Field Around Vertical Breakwater Under Different Overtopping Conditions Based on Numerical Simulation

A numerical wave flume is constructed based on the Reynolds Averaged Navier-Stokes (RANS) equations with turbulence closure by a modified k-ε model to study the viscous interactions of waves with vertical breakwaters for different overtopping cases. The governing equations,the turbulence model,boundary conditions,and solution method for the numerical wave flume are introduced briefly. The reliability of the numerical wave flume is examined by comparing the numerical results with the experimental measurement...     

关于我国1957年旧重力基本网的精度与系统转换

简述了原国家重力基本网(57网)的历史和技术要点,详细地分析了57网的各类误差和产生原因,提出了新、旧系统转换的方法。本文研究表明,57网基本点相对观测的实际精度约为±0.06mgal,仪器平均值误差为1.6×10~(-4)。基本点重力值含-13.56mgal的基准误差和1.9×10~(-4)的尺度差,并含有±0.1～0.2mgal的非线性系统误差。对基本点实行新、旧系统转换误差为±0.05mgal,基本不损失其观测精度。     

船舶气象导航随船验证

通过横流太平洋往返两个航次随船调查，研究了采用气象导航对减少燃油消耗和保证船舶安全、班期等，不但有定的经济效益，而且是一种非常有效的航运管理方法。     

SETTLING PROPERTIES OF COHESIVE AND NON-COHESIVE PARTICULATE MIXTURES IN WATER

1. INTRODUCTIONAs a wide range of size distirbution including usually a certain POrtion of cohesive material is thecommon feature of the sediment constituting hyperconcentrated flows. it is desirable to study the settling properties of mixtures of cohesive and non--cohesjve sediment particles at high concentrations.Past studies on the settling of discrete particles in a suspension of fine cohesjve sediment is scarcein the literature. The Sediment Research Laboratory of Tsinghua Universi…     

A NUMERICAL MODEL FOR SEDIMENTATION IN FENHE RESERVOIR AND THE ADJOINING REACHES

In this paper, a numerical model for sedimentation in Fenhe Reservoir and the adjoining reaches has been presented on the basis of the theory of non-equilibrium sediment transport. The model is calibrated by using a part of the sediment data collected for Fenhe Reservoir and checked by simulating the remaining data. Moreover, the method of optimization in nonlinear programming has been applied to determine the basic parameters of the model applying a concept of fuzzy mathematics to formulate the objective functions. The computed amounts of reservoir deposition and channel deformation arc found to be substantially in agreement with the values observed.