Assessment of present and future risk to Italian forests and human health: Modelling and mapping

A review of ozone pollution in Italy shows levels largely above the thresholds established by EU regulation for vegetation and human health protection. The Italian air quality monitoring network appears quantitatively inadequate to cover all the territorial surface, because of scarcity and unequal distribution of monitoring sites. By applying the integrated assessment model RAINS-Italy to the year 2000, the whole of Italy exceeds the AOT40 critical level for forest, while Northern and central areas show strong potential of O₃ impact on human health with ∼11% of territory >10 O₃-induced premature deaths. Two scenarios for the year 2020, the Current Legislation and the Maximum Technical Feasible Reduction, show a reduction of AOT40Forest by 29% and 44%, SOMO35 by 31% and 47%, and O₃-induced premature deaths by 32% and 48%, compared to 2000. RAINS-Italy can be used to improve the map quality and cover areas not reached by the national monitoring network.     

River channel network design for drought and flood control: A case study of Xiaoqinghe River basin, Jinan City, China

Vulnerability of river channels to urbanization has been lessened by the extensive construction of artificial water control improvements. The challenge, however, is that traditional engineering practices on isolated parts of a river may disturb the hydrologic continuity and interrupt the natural state of ecosystems. Taking the Xiaoqinghe River basin as a whole, we developed a river channel network design to mitigate river risks while sustaining the river in a state as natural as possible. The river channel risk from drought during low-flow periods and flood during high-flow periods as well as the potential for water diversion were articulated in detail. On the basis of the above investigation, a network with “nodes” and “edges” could be designed to relieve drought hazard and flood risk respectively. Subsequently, the shortest path algorithm in the graph theory was applied to optimize the low-flow network by searching for the shortest path. The effectiveness assessment was then performed for the low-flow and high-flow networks, respectively. For the former, the network connectedness was evaluated by calculating the “gamma index of connectivity” and “alpha index of circuitry”; for the latter, the ratio of flood-control capacity to projected flood level was devised and calculated. Results show that the design boosted network connectivity and circuitry during the low-flow periods, indicating a more fluent flow pathway, and reduced the flood risk during the high-flow periods.     

人工神经网络方法在拟建小区域环境质量评价中的应用

人工神经网络的评价方法用于小区域环境质量评价中,根据本地区特点因地制宜地选择环境质量参数,代入模型中进行环境质量评价及预测,对用于环境质量评价的BP人工神经网络模型进行了改进,即对网络模型的训练样本进行了扩充,从而提高了模型的抗干扰能力和准确性.将改进了的BP人工神经网络模型应用于四川省资阳市沱江二桥拟建项目小区域的大气、地表水环境质量评价中, 对该市小区域大气、地表水环境质量状况进行评价,评价结果表明,BP人工神经网络模型用于环境质量评价是可行的,且评价结论客观,评价模型普遍适用.     

大型活动生物恐怖应急处置研究与系统开发

针对非传统安全威胁的现状及其应急处置中的主要问题,以典型的非传统安全事件-大型活动举办过程中生物恐怖事件为背景,通过比较分析,给出了生物恐怖的定义;从大型活动生物恐怖应急指挥与处置的角度,通过应急处置业务流程分析,提出了大型活动生物恐怖事件应急处置的系统框架;根据系统框架和处置功能分析,基于三维GIS和AJAX技术开发了大型活动生物恐怖应急处置原型系统,对复杂的应急处置体系进行了分层模块化和可视化,可为应急救援部门制定更为详细的救援方案和应急决策提供技术参考。     

基于模糊神经网络的机动车驾驶教练员职业适宜性研究

提出应用模糊神经网络系统,建构教练员职业适宜性的3个要素(即心理素质、驾驶技能和知识的表达阐述能力)的学习样本,分析"三要素"的8项特征参数指标——场依存性、速度估计能力、交通安全意识、简单反应、选择反应、跟踪能力、行车注意力、表达阐述能力等,使用K-均值法对实验样本进行初始分类,形成标准学习样本,使用该样本对所构建系统进行训练和调试。利用经调试训练后的系统,依据所测教练员的心理、心理参数对其职业适宜性进行评价。试验表明:建立的教练员职业适宜性仿真模型能取得很好的评价效果。     

我国危险化学品安全监管网络整合研究

分析我国危险化学品安全监管网络的特征,指出安全监管网络中存在的法律法规、监管部门信息共享、合作协调机制等方面存在的突出问题,提出了我国危险化学品安全监管网络整合的主要对策,包括建立监管部门之间的常态合作协调机制、无缝隙化城市安全监管平台以及跨区域合作监管机制。危险化学品安全监管网络整合,对提高我国危险化学品监管水平具有重要意义。     

水资源问题安全化及其本质

从安全问题、安全化入手,探讨水资源问题安全化,解释了安全、安全问题及安全化的内涵;指出水资源问题来源于人类活动与水资源之间不和谐的运动,及其运动的逐渐升级,将产生一些危害性较大的水资源问题,水资源安全问题是水资源问题严重化的终极形态,其安全化是水资源问题转变为水资源安全问题的过程。在水资源安全化过程中,水资源问题是起点,安全化是过程,水资源安全问题是结果和终点。研究结果表明,水资源问题安全化的本质是水资源的稀缺性,安全的基础是健康的水循环。     

基于粗糙集-神经网络的矿山地质环境影响评价模型及应用

采用衡山白果地区石膏矿山的11个评价指标,综合运用粗糙集和神经网络理论,构建了基于粗糙集-神经网络(RS-ANN)的矿山地质环境影响评价模型,对RSES软件约简的数据和无约简的数据采用EasyNN-plus软件进行预测评价。神经网络模型的输入属性为8个,而粗糙集-神经网络模型的输入属性为6个,训练样本均为13个,预测样本均为4个,前者的平均预测精度为1.85%～24.86%,后者为1.23%～15.28%。研究发现,粗糙集在保留关键信息的前提下可有效地对数据表进行约简,约简后的神经网络预测结果与实际情况吻合,并比无约简时总体精度有较大幅度提高。     

人工神经网络在化学和环境科学中应用的若干问题

讨论了人工神经网络中最常用的多层前馈网络 ( BP网络 )及误差反向传播算法应用于化学和环境科学时要考虑的几个问题 :网络的输入与数据的归一化 ;隐含层数、隐含层节数和学习速率 ;训练集与监控集 ;网络误差 ;初始权重     

Artificial neural network based carbon monoxide persistence models for episodic urban air quality management

This paper describes the development of artificial neural network (ANN) based carbon monoxide (CO) persistence (ANNCOP) models to forecast 8-h average CO concentration using 1-h maximum predicted CO data for the critical (winter) period (November–March). The models have been developed for three 8-h groupings of 10 p.m. to 6 a.m., 6 a.m. to 2 p.m. and 2–10 p.m., at two air quality control regions (AQCRs) in Delhi city, representing an urban intersection and an arterial road consisting heterogeneous traffic flows. The result indicates that time grouping of 2–10 pm is dominantly affected by inversion conditions and peak traffic flow. The ANNCOP model corresponding to this grouping predicts the 8-h average CO concentrations within the accuracy range of 68–71%. The CO persistence values derived from ANNCOP model are comparable with the persistence values as suggested by the Environmental Protection Agency (EPA), USA. This work demonstrates that ANN based model is capable of describing winter period CO persistence phenomena.