基于多类支持向量机的化学物质生态危害分类研究

应用多类支持向量机(M-SVMs)方法研究了化学物质生态危害程度的分类,以提高分类的准确性和效率.对采集到的61种环境优先污染物的环境行为和生物毒性方面的7项指标进行相关性分析,建立了M-SVMs分类模型并对数据集进行10折交叉验证以评价模型的分类能力,运用所建模型对7种化学物质的生态危害进行预测.结果表明,去除与鱼毒有信息重叠的溞毒指标,选取鱼毒、藻毒、降解性、蓄积性、分配系数和吸附系数6项指标用于构建M-SVMs分类模型;M-SVMs模型识别率较高,交叉验证平均分类正确率达86.89％;对7种化学物质生态危害的预测结果与实际情况基本相符.     

大断面巷道中空预应力注浆锚杆的支护效果研究

针对金川矿区大断面巷道在强构造应力作用下围岩变形严重的情况,提出了中空预应力注浆锚杆的支护工艺。通过数值计算得出以下结论:相比传统的普通砂浆锚杆支护工艺,采用中空预应力注浆锚杆支护工艺能够主动加固围岩,提高支护刚度;巷道两帮的变形减小了约14.56%,最大、最小主应力分别降低了4.4%和7.2%,粘结层破坏范围也随之减小。通过对支护后巷道变形监测发现:两帮最终变形量减小了约36.6%;通过抗拔实验,中空预应力注浆锚杆的抗拔力达到140kN,远大于普通砂浆锚杆的40kN抗拔力,中空预应力注浆锚杆有更好的支护效果。     

基于MFOA-SVR露天矿边坡变形量预测研究

为实现边坡危险性及时预警预报,以露天矿边坡变形量为研究对象,提出采用七项影响指标作为边坡位移变形量的响应参数,建立支持向量机回归预测模型(SVR)。引入修正的果蝇优化算法(MFOA)对模型参数进行优化,构建基于MFOA-SVR露天矿边坡变形量协同预测模型,并以实际监测数据进行模型仿真预测。结果表明:该模型平均绝对误差为0.9167mm,平均相对误差为4.2737%,较其他模型预测精度高,综合性能好,将其运用于露天矿边坡变形量预测研究具有较好的适用性和可靠性。     

基于粗糙集和支持向量机的标准农田地力等级评价

标准农田是耕地的精华,是确保国家粮食安全的关键。科学评价标准农田地力等级对标准农田培肥和土壤改良有着重要意义。将粗糙集(Rough Set,RS)理论和支持向量机(Support Vector Machine,SVM)相结合,提出了基于RS和SVM的标准农田地力等级评价方法,同时,利用遗传算法的并行搜索结构和模拟退火的概率突跳特性,提出了GASA优化SVM参数算法。该方法首先在确定标准农田地力等级评价指标的基础上,利用地力调查样本数据及传统的指数和法评价结果构建RS决策表,应用RS穷尽算法对决策表进行约简,剔除冗余的评价指标,然后用约简后的评价指标作为SVM的输入,运用GASA优化SVM参数算法对SVM进行训练,建立标准农田地力等级的RS-SVM评价模型。应用该方法对温州市鹿城区标准农田地力等级进行评价,与未用RS约简的SVM模型和BP神经网络模型评价结果进行对比,SVM模型和BP神经网络模型的输入指标数均为15个,其评价正确率分别为100%和90%;RS-SVM模型的输入指标数为14个,其评价正确率分别为100%,结果表明,该方法通过RS约简评价指标后,SVM评价精度并没有降低,但降低了SVM输入向量维数和计算复杂度,提高了训练效率;SVM 用于标准农田地力等级评价,具有比BP神经网络更高的评价精度,可有效用于标准农田地力等级评价,为耕地地力评价提供了新方法。     

Sustainability assessment of entire forest value chains: Integrating stakeholder perspectives and indicators in decision support tools

The optimization of value chains is an important process to promote sustainable development, since value chains are closely linked to the satisfaction of human needs and combine different driving forces for environmental change. This article presents a methodological approach for the participatory development of value-chain wide sustainability indicator sets and their integration into a decision support tool in the specific case study of the chain “construction and refurbishment with wood”. There are numerous indicator sets for sustainable development of forests and sustainable forestry available at different levels, ranging from local, regional and national to global scale assessments. Some efforts were also made to integrate later production stages of forest value chains (such as wood processing) in the assessment scope (e.g. for chain-of-custody certification). However, no indicator set has so far been available covering environmental, social and economic aspects for the entire value chain of building with timber. This gap was closed through applied sustainability research in the project “Holzwende 2020: Sustainable future markets for wood in the building sector”.     

Inherent conflicts at the coast

Because choice is conflict, decision-making is necessarily about conflict resolution. Choices are necessary because the options are mutually exclusive but the nature of this inherent conflict varies. Typically, these conflicts are multidimensional. In coasal zones, the complex interactions between systems makes decision-making particularly complex; in particular, environmental interests are themselves frequently in conflict. In making a choice, it is important to determine why that choice is necessary in the first place. There are further conflicts about the objectives to be satisfied by the decision process; between the determination of the best outcome and the best decision process. Social scientists centre upon the requirement for a fair decision process rather than upon seeking an optimum outcome. Unlike physical scientists who seek more and better information, social scientists focus upon the development and maintenance of institutions.     

HOW CLIMATE UNCERTAINTY SHOULD BE INCLUDED IN GREAT LAKES MANAGEMENT: MODELING WORKSHOP RESULTS1

ABSTRACT: In two workshops, we evaluated decision analysis methods for comparing Lake Erie levels management alternatives under climate change uncertainty. In particular, we wanted to see how acceptable and effective those methods could be in a public planning setting. The methods evaluated included simulation modeling, scenario analysis, decision trees and structured group discussions. We evaluated the methods by interviewing the workshop participants before and after the workshops. The participants, who were experienced Great Lakes water resources managers, concluded that simulation modeling is user-friendly enough to enable scenario analysis even in workshop settings for large public planning studies. They felt that simulation modeling can improve not only understanding of the system, but also of the options for managing it. Scenario analysis revealed that the decision for the case study, Lake Erie water level regulation, could be altered by the likelihood of climate change. The participants also recommended that structured group discussions be used in public planning settings to elicit ideas and opinions. On the other hand, the participants were less optimistic about decision trees because they felt that the public might view subjective probabilities as difficult to understand and subject to manipulation.     

Stress and team performance: principles and challenges for intelligent decision aids

Advances in computer technology and artificial intelligence are providing powerful capabilities for developing intelligent decision aids (IDAs) to support operating teams in managing complex systems. Early system designs, which acted as independent computer advisors, constrained human decision making, were brittle and encountered problems of user acceptance. As a result, there has been a shift towards making IDAs more cooperative in assisting users to make decisions under stress. Although there is a growing body of research on how to design IDAs as collaborate team players, this article provides additional insights by focusing on the competencies manifested by efficient teams in adapting to stress. To this extent, a survey of how teams adapt their decision-making strategies, cooperation patterns and team structure has provided a good basis for proposing design principles for collaborative IDAs. The article concludes with some challenges for further developments in information technology and research needs in the area of teamwork under stress.     

基于遥感影像的木兰溪水质参数反演

水质监测对水环境评价及污染预防至关重要,但地面监测成本高、监测面积有限等,难以满足实时、大范围监测的要求。为了更好地解决该问题,基于遥感影像的空中监测技术越来越得到研究人员的青睐。以木兰溪为研究区,利用和地面监测数据同步的Landsat-8卫星遥感影像数据,对木兰溪的典型水质参数总磷、总氮、溶解氧、高锰酸盐指数的反演问题进行研究。首先,根据Landsat-8的水体敏感波段,分别选取总磷、总氮、溶解氧、高锰酸盐指数的反演特征波段组合为(b1-b2)/(b2+b3),(b1-b2)/(b3-b4),b2/(b1+b4),b1/b2;其次,利用反演特征波段组合分别构建总磷、总氮、溶解氧、高锰酸盐指数浓度的SVR(Support Vector Regression)反演模型,通过IPSO算法对SVR模型的参数进行优选;然后,将IPSO-SVR反演模型和统计回归反演模型、广义回归神经网络(GRNN)反演模型在验证集上进行评估,以平均绝对误差和均方根误差作为评价指标进行对比分析,结果表明IPSO-SVR反演模型的平均绝对误差和均方根误差最小,说明IPSO-SVR反演模型具有较高的精度和较好的实用性...     

针对大型振动试验辅助支撑系统的结构设计与技术改进

对振动台辅助支撑系统进行了结构改进,增加了空气弹簧和导向轴。并且针对偏心问题,采用多个气源对不同位置分布的空气弹簧施加不同的气压进一步增强振动台的抗倾覆能力。建立了一套可以应用于轨道交通等大型设备的具有较大承载能力(14 t),较大抗倾覆能力的振动台辅助支撑系统。