机器学习在材料服役性能预测中的应用

针对材料服役性能预测存在误差大、计算复杂、适用性差等问题,提出了基于数据挖掘的机器学习预测方法。首先阐述了机器学习的应用流程,并总结了常用模型原理及其在材料性能预测中的应用。然后采用多种机器学习模型对RPV钢的辐照性能进行预测,并通过Stacking集成方法提高了模型的预测精度。结果表明,机器学习可用于材料服役性能预测,具有较高的预测精度和可靠性。根据材料服役数据的不同特征选择合适的学习模型,同时进行模型融合和参数优化,可有效提高模型的预测精度及运算速度。     

环境因素数据质量审核方法研究

目的 解决大气环境试验站的气象数据报表存在数据缺失、数据超过边界、数据内部不一致、数据时间不一致等问题,采用数据质量审核技术找出缺失、可疑或错误的数据,对科研人员进行警示,使其能够追根溯源,分析存在问题的原因。方法 参照相关规程和标准,建立环境因素数据质量审核算法和审核流程,并使用计算机语言编程固化流程和算法,利用多线程算法对数据进行扫描,实现大批量气象数据的并行审核。结果 利用Python语言设计了环境因素质量控制软件,通过该软件的应用证明了该方法合理、有效,能够快速、准确地标注气象数据报表中存在质量问题的数据。利用软件统计了存在问题数据的数量和正确率。结论 通过加载数据测试,证明了环境因素数据质量审核方法和审核流程合理有效,利用设计的审核软件实现了气象数据报表快速审核,提高了审核效率,减少了科研人员的劳动强度,为进一步填补、修正和利用数据奠定了基础。     

人工增雨（雪）效果评估方法探索

人工增雨（雪）常用的评估方法为统计检验和物理检验,统计检验需要大量试验样本,且随机化试验在我国难以实现,大量样本无从获得。物理检验目前主要是雷达观测演变状况和飞机直接观测云内微物理参数,由于技术和能力有限,这些方法都难以实现。为了在人工影响天气作业后尽快得出评估结果供政府及环境保护等部门参考,利用雨滴谱记录数据对一次人工增雪作业后的效果进行了评估,发现这些数据在没有常规降雪记录情况下具有一定的参考价值。从评估结果看,人工增雪作业后,降水强度有明显增大的趋势。     

基于BP神经网络的天线识别

本文比较研究了BP神经网络中的几种常用算法,针对这些不同算法下的BP神经网络进行训练,并得出了各自网络的性能。在此基础上,针对经典BP算法和LM算法进行对比研究,找到LM算法的改进之处。此外,在实际的应用中表明,不仅不同的BP算法对网络的运算速度、泛化能力等有较大的影响,而且BP神经网络对隐含层神经元数目也很敏感。我们希望在BP神经网络的基础上,构建一种合适的天线模型,来应用于天线的分类识别,这将具有很大的现实意义。     

基于双系统理论的消费者价格判断决策模型

参考价格理论是构建价格判断模型的传统理论,其价格判断模型是一种典型的推理性模型.根据双系统理论,人们的决策应是推理性和直觉性两类过程的交互作用,心理账户理论正是描述直觉性决策的基本理论之一.构建了基于参考价格与心理账户的双系统价格判断决策模型,对不同心理账户数据进行分析发现,被试者的目标价格决策过程具有显著差异.     

Effect of Monitoring Technique on Quality of Conservation Science

Monitoring free‐ranging animals in their natural habitat is a keystone of ecosystem conservation and increasingly important in the context of current rates of loss of biological diversity. Data collected from individuals of endangered species inform conservation policies. Conservation professionals assume that these data are reliable—that the animals from whom data are collected are representative of the species in their physiology, ecology, and behavior and of the populations from which they are drawn. In the last few decades, there has been an enthusiastic adoption of invasive techniques for gathering ecological and conservation data. Although these can provide impressive quantities of data, and apparent insights into animal ranges and distributions, there is increasing evidence that these techniques can result in animal welfare problems, through the wide‐ranging physiological effects of acute and chronic stress and through direct or indirect injuries or compromised movement. Much less commonly, however, do conservation scientists consider the issue of how these effects may alter the behavior of individuals to the extent that the data they collect could be unreliable. The emerging literature on the immediate and longer‐term effects of capture and handling indicate it can no longer be assumed that a wild animal's survival of the process implies the safety of the procedure, that the procedure is ethical, or the scientific validity of the resulting data. I argue that conservation professionals should routinely assess study populations for negative effects of their monitoring techniques and adopt noninvasive approaches for best outcomes not only for the animals, but also for conservation science. Efecto de la Técnica de Monitoreo en la Calidad de la Ciencia de la Conservación     

可持续发展环境约束条件下的水资源最优配置及实证研究

在相关理论分析和Weber模型的基础上。拓展建立了面向水资源可持续发展的水资源最优配置模型。引入了基于政府管制的影响作用、沿河流域的水用户的实际消耗水量、实际排放水量、河流中可供使用水量及所排放污水水质水平等5个变量函数．通过政府管制下的水质和水量的河道内流量需求等环境约束条件．确保水资源利用始终满足最小基流水量。通过求量优解，计算得出在环境约束下达到最优配置时各个变量函数与对下游地区外部性之间的相关性。接着。本文对陕北黄土高原沿Y河的35家企业进行了实际调查．收集了2个年度共8个季度的观测值，应用计量经济Pand Data模型。对35个节点、8个季度的共280个数据作为混合样本进行经济计量分析。验证了相关结论。最后。还提出一些制定环境约束条件以及水用户间建立水资源环境生态补偿金机制等政策建议。     

Presence–Absence versus Abundance Data for Monitoring Threatened Species

Abstract:  Effective detection of population trend is crucial for managing threatened species. Little theory exists, however, to assist managers in choosing the most cost-effective monitoring techniques for diagnosing trend. We present a framework for determining the optimal monitoring strategy by simulating a manager collecting data on a declining species, the Chestnut-rumped Hylacola ( Hylacola pyrrhopygia parkeri ), to determine whether the species should be listed under the IUCN (World Conservation Union) Red List. We compared the efficiencies of two strategies for detecting trend, abundance, and presence–absence surveys, under financial constraints. One might expect the abundance surveys to be superior under all circumstances because more information is collected at each site. Nevertheless, the presence–absence data can be collected at more sites because the surveyor is not obliged to spend a fixed amount of time at each site. The optimal strategy for monitoring was very dependent on the budget available. Under some circumstances, presence–absence surveys outperformed abundance surveys for diagnosing the IUCN Red List categories cost-effectively. Abundance surveys were best if the species was expected to be recorded more than 16 times/year; otherwise, presence–absence surveys were best. The relationship between the strategies we investigated is likely to be relevant for many comparisons of presence–absence or abundance data. Managers of any cryptic or low-density species who hope to maximize their success of estimating trend should find an application for our results.