基于粗糙集和BP神经网络的流域水资源脆弱性预测研究——以淮河流域为例

水资源是一种重要的自然资源和经济资源,对其未来的脆弱性进行预测可以预估研究区未来的水安全状况,对其脆弱性问题做出预警,从而及时采取治理措施。因此,合理科学的水资源脆弱性预测研究是缓解水资源脆弱性的有效手段。目前,水资源脆弱性研究主要是针对水资源现状进行评价,对其未来状况的预测较少。集成了粗糙集和BP神经网络两种方法,首先采用改进了的盲目删除法对构建的流域水资源脆弱性评价指标体系进行约简,其次通过BP神经网络拟合约简后的指标数据与脆弱度之间的映射关系,构建流域水资源脆弱性评价预测模型。基于之前研究的样本数据和脆弱性结果,探讨淮河流域未来的水资源脆弱性状况。结果表明:淮河流域2015年、2020年和2025年的水资源脆弱度分别为0.305、0.359和0.390,处于轻度脆弱和中度脆弱的状况,除2015年脆弱性状况有所好转以外,2020年和2025年的水资源脆弱性程度与近几年相比有所加剧,根据指标数据可知该现象主要是受年降水量、人均用水量、万元GDP废水排放量、垦殖指数、有效灌溉面积比和干旱面积受灾比6个指标的影响,为避免水资源脆弱性的加剧,应当有针对性的加强这几个方面的管理和控制。     

基于人工神经网络的半连续式混合厌氧消化产气量预测

研究采用BP神经网络和模糊神经网络(FNN)模型对逐步提高有机负荷的半连续式餐厨垃圾和猪粪混合厌氧消化试验进行日产气量预测.结果表明,BP神经网络模型的预测准确率为77.63％,FNN模型为82.33％,2种模型均可用于产气预测,但FNN模型在传统神经网络模型基础上加入了模糊控制,可提高其准确率,更适用于混合厌氧消化产气量预测.     

苏皖交界河网区浮游植物群落结构及其与环境因子关系的研究

苏皖交界处的石臼湖是长江下游唯一的通江淡水湖,通过青弋江和姑溪河直接与长江相连,形成了复杂的河网水系。为探讨这种复杂的河网水系中浮游植物种群结构特征,2012年平水期和枯水期分别对石臼湖及其周边入湖支流进行了浮游植物调查,研究河网水系中河网与湖区浮游植物的种类组成、季节变化及与环境因子的关系。结果显示:共采集到浮游植物105种,平水期与枯水期种类数差别不大,两次调查均出现的种类约有70%相同;浮游植物丰度最高可达1×108cell/L,达到了水华暴发的标准。优势种类主要绿藻门和蓝藻门为主,但是从生物量来看硅藻门占优。排序分析显示河网区域浮游植物季节演替明显,且河网与湖区浮游植物群落结构差异明显,进一步分析则表明影响浮游植物主要的环境因子是氮、磷等营养元素。     

Weather,climate, politics,or God? Determinants of American public opinions toward global warming

2012 American National Election Study data supplemented with monthly temperature data from the United States Historical Climatology Network are used to examine how religion, politics, and weather and climate affect views of global warming. Evangelical fundamentalism is the most consistent factor among all religion-related variables in determining perceptions of global warming, those more oriented toward evangelical fundamentalism being less likely than others to believe in the existence, anthropogenic cause, and adverse impact of global warming. Controlling for the effects of traditional political predisposition variables, including party identification and political ideology, support for the Tea Party plays a dominant role in determining views of global warming; support for the Tea Party leading to higher likelihood of disbelief in the existence, anthropogenic cause, and negative impact of global warming. Warming winters coupled with cooling springs of the past decade are positively related with belief in the existence of global warming.     

湖北省道路网络中心性与土地利用景观格局关系分析

深入理解道路网络与土地利用之间的关系有助于开展可持续的土地利用与道路网络规划。引入多中心性评价模型,对临近中心性、中介中心性、直线中心性3个指标,运用UNA对湖北省道路网络中心性进行测度;选取景观百分比,香农多样性指数,平均斑块大小,平均形状指数4个景观格局指数计算土地利用景观格局特征,并通过斯皮尔曼相关方法对两者之间的关系进行探讨。结果表明:(1)湖北省道路网络中心性格局和空间特征各异,整体上东高西低,临近中心性呈现条带状分布,中介中心性呈孔隙状分布,直线中心性呈片状分布;(2)景观层面上,土地利用景观破碎化和多样化对直线中心性最为敏感,而临近中心性与中介中心性与景观格局指数关系相对复杂;(3)在类型层面上,道路网络中心性与各类土地利用景观格局相关性各异,其中高中心性区域对林地表现为鲜明的排斥和破碎化效应,而对建设用地表现为强烈的吸引和空间集聚现象。该研究以道路网络中心性视角探讨道路网络与土地利用景观格局之间的关系,为区域空间形态和构成及其相关影响因素提供了新的视角。     

Optimization of thermal performance of the parabolic trough solar collector systems based on GA-BP neural network model

The aim of this paper is to optimize the thermal performance (system output energy, thermal efficiency, and heat loss of cavity absorber) of parabolic trough solar collector (PTC) systems in order to improve its thermal performance, based on the genetic algorithm-back propagation (GA-BP) neural network model. There are a number of undefined problems, fuzzy or incomplete information and a complex thermal performance of the PTC systems. Therefore, the thermal performance prediction of the PTC systems based on GA-BP neural network model was developed. Subsequently, the metrics performances have been adopted to comprehensively understand the algorithm and evaluate the prediction accuracy. Results revealed that the GA-BP neural network model can be successfully used to predict the complex nonlinear relationship between the input variables and thermal performance of the PTC systems. The cosine effect has a great influence on the thermal performance; thereby the geometrical structure of the PTC systems was optimized. It was found that the optimized geometrical structure was beneficial to improve the thermal performance of the PTC system. In conclusion, the GA-BP neural network model has higher prediction accuracy than the other algorithm and it can be feasible and reliable.     

Non-linear autoregressive neural network approach for inside air temperature prediction of a pillar cooler

The volcanic plate made pillar cooler system is designed for outdoor spaces as a heat exchanging medium and reduces the outcoming air temperature which flows through the exhaust port. This paper proposes the use of artificial neural networks (ANNs) to predict inside air temperature of a pillar cooler. For this purpose, at first, three statistically significant factors (outside temperature, airing and watering) influencing the inside air temperature of the pillar cooler are identified as input parameters for predicting the output (inside air temperature) and then an ANN was employed to predict the output. In addition, 70%, 15% and 15% data was chosen from a previously obtained data set during the field trial of the pillar cooler for training, testing and validation, respectively, and then an ANN was employed to predict inside air temperature. The training (0.99918), testing (0.99799) and validation errors (0.99432) obtained from the model indicate that the artificial neural network model (NARX) may be used to predict inside air temperature of pillar cooler. This study reveals that, an ANN approach can be used successfully for predicting the performance of pillar cooler.     

Evaluating efforts to build sustainable WEEE reverse logistics network design: comparison of regulatory and non-regulatory approaches

Many developing countries such as Turkey are still making an effort on building an infrastructure for waste of electrical and electronic equipment (WEEE) reverse logistic network design (RLND) processes. It is obvious that policies/laws/regulations related to WEEE management provide a sustainable framework for implementation in the RLND. The question is here: Does the implementation of WEEE directives make sense in terms of reducing the total cost of the network in the long term? This study aims to compare regulatory and non-regulatory situations of WEEE RLND in developing countries by formulating two models named as ‘regulatory’ and ‘non-regulatory’. Model 1 is considered as sustainable with economic, environmental and social goals, and the quotas imposed by the environmental directive are taken into consideration as the data of product return amount. In Model 2, only economic goal is considered, and product return amount is forecasted using Artificial Neural Network (ANN). A case study is conducted in a recycling company in order to evaluate performance of the proposed models. This study contributes to the relevant literature by (1) comparing the regulatory and non-regulatory situations RL models explicitly and (2) proposing ANN model to forecast EEE product return or WEEE quantity for non-regulatory situation.     

Addressing challenges for future strategic‐level emergency management: reframing,networking, and capacity‐building

The mounting frequency and intensity of natural hazards, alongside growing interdependencies between social‐technical and ecological systems, are placing increased pressure on emergency management. This is particularly true at the strategic level of emergency management, which involves planning for and managing non‐routine, high‐consequence events. Drawing on the literature, a survey, and interviews and workshops with Australia's senior emergency managers, this paper presents an analysis of five core challenges that these pressures are creating for strategic‐level emergency management. It argues that emphasising ‘emergency management’ as a primary adaptation strategy is a retrograde step that ignores the importance of addressing socio‐political drivers of vulnerabilities. Three key suggestions are presented that could assist the country's strategic‐level emergency management in tackling these challenges: (i) reframe emergency management as a component of disaster risk reduction rather than them being one and the same; (ii) adopt a network governance approach; and (iii) further develop the capacities of strategic‐level emergency managers.     

斜井送排式通风隧道的火灾救援通风研究

公路隧道发生火灾开启横通道后,形成通风网络。本文以重庆地区吕家梁隧道为工程依托,进行了斜井前后不同位置发生火灾的通风网络模拟。结果表明,斜井前发生火灾时,受斜井浮力效应、风流密度变化等的影响,主风机的工作压力降低,而体积流量增加;当火灾发生在斜井前隧道时,采用斜井单抽方式可实现全部火灾烟流从竖井中排除,斜井前设射流风机增压调节、斜井后设射流风机增阻调节是一较好方案;对于斜井后发生火灾,采用全射流火灾通风和斜井压入两种通风方案均能满足火灾风流控制要求,虽然后者需要开启轴流风机,通风能耗大,但火灾通风的时效性要好于前者。