Prediction of Stellar Atmospheric Parameters using Instance-Based Machine Learning and Genetic Algorithms   总被引：1，自引：0，他引：1  

J. Federico Ramírez  Olac Fuentes  Ravi K. Gulati 《Experimental Astronomy》2001,12(3):163-178

In this article we present a method for the automated prediction of stellar atmospheric parameters from spectral indices. This method uses a genetic algorithm (GA) for the selection of relevant spectral indices and prototypical stars and predicts their properties, using the k-nearest neighbors method (KNN). We have applied the method to predict the effective temperature, surface gravity, metallicity, luminosity class and spectral class of stars from spectral indices. Our experimental results show that the feature selection performed by the genetic algorithm reduces the running time of KNN up to 92%, and the predictive accuracy error up to 35%. This revised version was published online in July 2006 with corrections to the Cover Date.  相似文献   

Early warning research on salt-alkalization desertification in western Songnen Plain     

BIAN Jian-min  LIN Nian-feng  TANG Jie College of Environment  Resources  Jilin  University  Changchun  Jilin  China 《东北亚地学研究》2005,(Z1)

Desertification is an environmental issue in the world. The salt-alkalization desertification land area formed by both primary and secondary salt-alkalization has extended in a large scale, which has become a significant eco-environmental problem. Based on the characteristics of eco-environment and the situation of desertification in western Songnen plain, this paper reports the analyzes of its formation in background and cause. An early warning system on the salt-alkalization desertification is established and the GIS technology is used to abstract the information of desertification evaluation index. Supported by the integrated technology of the GIS and ANN, the orientation and quantitative result of desertification are gained, which is helpful to the eco-environment protection and resource development in western Songnen Plain.  相似文献   

天文光干涉与综合孔径技术的发展     

郭红锋 《紫金山天文台台刊》2003,(1)

本文简单介绍了光干涉与综合孔径技术发展的历史、国际上用于天文观测的一些著名光干涉仪的技术特点和进展、以及近年来我国开展的与光干涉 ,综合孔径技术有关的工作 ,最后简要介绍了在光学综合孔径技术领域所发展的光纤与集成光学等新技术  相似文献   

成都市冬季重污染日气象条件成因分析及预报     

张波  杨柏生 《成都信息工程学院学报》1992,(3)

本文通过对成都10个重污染日进行天气学分析,将污染浓度与气象要素进行聚类、研究了重污染日形成原因及污染浓度与气象要素的关系。在此基础上,建立了SO_2、TSP日平均浓度分级预报方程。  相似文献   

An operational multiscale system for hazards prediction, mapping, and response     

David P. Bacon  Nash’at N. Ahmad  Thomas J. Dunn  Michael C. Monteith  Ananthakrishna Sarma 《Natural Hazards》2008,44(3):317-327

By definition, a crisis is a situation that requires assistance to be managed. Hence, response to a crisis involves the merging of local and non-local emergency response personnel. In this situation, it is critical that each participant: (1) know the roles and responsibilities of each of the other participants; (2) know the capabilities of each of the participants; and (3) have a common basis for action. For many types of natural disasters, this entails having a common operational picture of the unfolding events, including detailed information on the weather, both current and forecasted, that may impact on either the emergency itself or on response activities. The Consequences Assessment Tool Set (CATS) is a comprehensive package of hazard prediction models and casualty and damage assessment tools that provides a linkage between a modeled or observed effect and the attendant consequences for populations, infrastructure, and resources, and, hence, provides the common operational picture for emergency response. The Operational Multiscale Environment model with Grid Adaptivity (OMEGA) is an atmospheric simulation system that links the latest methods in computational fluid dynamics and high-resolution gridding technologies with numerical weather prediction to provide specific weather analysis and forecast capability that can be merged into the geographic information system framework of CATS. This paper documents the problem of emergency response as an end-to-end system and presents the integrated CATS–OMEGA system as a prototype of such a system that has been used successfully in a number of different situations.  相似文献   

中国滑坡预测预报研究综述   总被引：14，自引：1，他引：13  

王念秦  王永锋  罗东海  姚勇 《地质论评》2008,54(3):355-361

滑坡预测预报是有效预防滑坡灾害的重要途径之一,这方面的研究不仅受到广泛重视,且硕果累累。将中国滑坡预测预报的研究历史划分为四个阶段：① 经验判断——被动防灾避灾阶段;② 定性——半定量分析预测预报阶段;③ 理论方法探索——检验预测预报阶段;④ 理论方法深化——综合应用预测预报阶段。从监测（观测）方法、预测预报方法,以及研究特点等方面进行简要回顾,总结已有监测方法（手段）、预测预报理论、方法的研究现状,认为尚存在：① 监测方法（手段）,包括仪器、设备的精度不足;② 预测预报方法综合性、实用性不强;③ 预测预报专门理论尚待完善等问题。在分析的基础上,提出自己的观点,并进行了发展趋势展望。  相似文献   

钱二块铀矿床采铀注液结垢趋势的理论分析与预测   总被引：1，自引：0，他引：1  

薛海凤  朱建华  刘红研  齐建华 《铀矿地质》2008,24(1):48-56,64

用离子系数矩阵法对钱二块铀矿床地浸采铀试验注液中存在的独立离子反应进行了确定,由溶度积规则及反应平衡原理,借助Matlab编程,估算出了钱二块铀矿床地浸采铀试验注液可能会生成的沉淀物种类及数量,为防治结垢提供了一定的理论依据.  相似文献   

基于AGA的SVM需水预测模型研究   总被引：1，自引：0，他引：1  

张灵  陈晓宏  刘丙军  王兆礼 《水文》2008,28(1):38-42,46

需水预测是一个由城市人口、工业水平、社会经济水平共同作用的多因素、多层次的复杂非线性系统.其结果将直接影响受区域水资源承载力约束的产业结构、布局形态等决策.作为一种集中参数预报方法,支持向量机方法具有对未来样本的较好的泛化性能,对于这类资料缺乏、系统结构尚欠清晰的问题可以取得较好的模拟和预测结果.基于此,本文将支持向量机方法引入需水预测领域,建立了需水预测支持向量机模型.同时,本文将加速遗传算法和支持向量机方法耦合起来,构造了支持向量机模型参数的自适应优化算法.模型在珠海市的应用实例表明:与简单遗传算法比较,AGA的模型参数寻优效率更高;与BP神经网络模型相比,SVM模型较好地解决了小样本、经验性等问题,并取得了较高的预测精度.  相似文献   

青岛奥运水域主要污染物环境容量的预测     

徐艳东  娄安刚  谭海涛  龙绍桥  石晓勇 《海洋科学》2006,30(2):38-42

通过对青岛奥运水域现场调查和资料分析,确定了奥运水域污染物的主要来源和主要污染物,然后在潮流模拟的基础上,利用物质输运方程数值模拟了2000~2003年污染物浓度的空间分布,其结果与现状调查基本吻合。最后再利用该输运方程,预测了奥运帆船水域的化学需氧量(COD)、氨氮(NH4 -N)、总磷(TP)的环境容量(中潮时分别为:69.948 t/d,7.46 t/d,0.5455 t/d),为奥运水域的目标管理提供科学依据。  相似文献   

海洋环境立体监测系统的设计方法   总被引：9，自引：1，他引：9  

罗续业  周智海  曹东  李彦 《海洋通报》2006,25(4):69-77

“九五”和“十五”期间,在国家海洋863计划的支持下,我国分别在上海和台湾海峡及毗邻海域建立了两个区域性海洋环境立体监测示范系统。在这两个示范系统的技术研究成果的基础上,通过分析国际海洋立体监测系统的设计模型,提出了区域性海洋环境立体监测系统的设计原则和设计方法,包括:系统结构、数据与信息服务通信网络、数据处理中心、数据流程以及系统功能等方面的设计方法。  相似文献