用微生物群落评价水系的自组织人工神经网络方法

利用原生物群落在PFU上群集过程中的变化,可以评价水质和监测水污染,运用T．Kohonen自组织人工神经网络模型,根据NacArthur－Wilson平衡模型提出了3个功能参数和另外2个结构参数,对常德市16个站四季的水质进行了分析,建立了水质污染程度预测的计算机智能专家系统,预测成功率达100％。     

上海市土壤中人工放射性水平调查及评价

调查了１９８９－１９９０年上海市土壤中及黄浦江水系底泥中，人工放射性核素的含量。调查共设３２个点，结果表明，上海市土壤中的人工放射性核素含量，＾９０Ｓｒ、＾１３７Ｃｓ、总β的比活度均值分别为２、４１±０．７８、３．１４±１．４７、７１７．０±１３５．９Ｂｑ／ｋｇ，属正常本底水平。土壤中人工放射性核素的比活度在全市范围内分布没有明显差别，波动范围不大。土壤中＾１３７Ｃｓ的比活度比＾９０Ｓｒ高，这与土     

基于自回归GA-BP神经网络的AQI预测

基于徐州市2013年12月—2018年11月的空气质量指数日均值,建立了时间序列自回归输入的GA-BP神经网络模型用于空气质量指数预测。结果表明,所建立的网络模型能够准确预测徐州市空气质量指数的变化趋势,其中夏季预测相对误差18. 23%,仿真均方根误差(RMSE)为14. 59;冬季预测相对误差9. 14%,仿真RMSE为11. 47。     

广州海洋观测网规划建设及观测数据应用探讨

阐述了广州海洋观测网建设的迫切性和必要性,对海洋观测网建设在海洋防灾减灾、海岸工程建设及海水养殖等方面的重要意义进行了分析说明。总结广州市海洋观测网建设现状和成果,并利用已有观测数据对2017年台风^“天鸽^”和^“帕卡^”期间广州海域水文气象特征、2015—2017年枯水期咸潮入侵特征进行了分析。研究表明, 现有观测数据对台风和咸潮活动均具有较明显的反应,且对海洋防灾减灾工作具有重要的意义;为更有效地利用已有观测数据,将观测数据价值最大化,对观测网建设及运行过程中观测工作机制及业务化流程、数据质量控制、观测站布设合理性以及数据应用分析这几个方面存在的问题进行了探讨,提出了广州海洋观测网的优化、改进措施及未来发展方向。     

基于BP神经网络与马尔可夫链的污水处理厂脱氮效果模拟预测

在实际污水处理厂运行过程中,其最终出水水质会受多种因素影响制约,而基于生物反应机理的活性污泥数学模型(ASM)并未将这些生物反应以外的因素考虑在内,由此带来一些不足.对此,本文提出可通过基于数据挖掘技术的黑箱模型对污水厂处理效果进行模拟预测.结合具体实际分析,提出可将BP神经网络与马尔可夫链组合应用于污水处理脱氮效果预测中.首先,通过BP神经网络模型对北京某大型污水处理厂实际进出水数据和工艺参数进行粗略拟合;其次,利用马尔可夫链对拟合结果及误差进行状态划分以进一步提高预测精确度;最后,运用基于BP神经网络与马尔可夫链的组合模型预测分析了该厂的实际出水水质.试验结果表明,BP神经网络适用于污水处理脱氮过程的拟合计算,而通过与马尔可夫链组合,可以提高模拟预测的精度和可靠性.     

我国鸟类监测的现状、问题与对策

鸟类是开展生物多样性监测的重要指示类群.对鸟类的长期、系统监测工作在欧美已经有百余年历史,且野鸟多样性指数已经成为欧美一些国家开展生物多样性监测工作的官方指标.通过对国内鸟类监测现状的分析,结合监测对象、指标、抽样策略和监测方法等监测工作中应重点关注的几个方面,提出了我国鸟类监测存在的问题,并结合国情提出了下一步开展鸟类监测工作的对策与建议.建议我国有关部门尽快制定鸟类监测技术规程和标准,统一数据收集和分析平台,逐步构建政府引导,科研院所、高等院校、自然保护区、观鸟协会和志愿者等多方参与的鸟类监测网络.     

Scale Mismatches,Conservation Planning,and the Value of Social‐Network Analyses

Many of the challenges conservation professionals face can be framed as scale mismatches. The problem of scale mismatch occurs when the planning for and implementation of conservation actions is at a scale that does not reflect the scale of the conservation problem. The challenges in conservation planning related to scale mismatch include ecosystem or ecological process transcendence of governance boundaries; limited availability of fine‐resolution data; lack of operational capacity for implementation; lack of understanding of social‐ecological system components; threats to ecological diversity that operate at diverse spatial and temporal scales; mismatch between funding and the long‐term nature of ecological processes; rate of action implementation that does not reflect the rate of change of the ecological system; lack of appropriate indicators for monitoring activities; and occurrence of ecological change at scales smaller or larger than the scale of implementation or monitoring. Not recognizing and accounting for these challenges when planning for conservation can result in actions that do not address the multiscale nature of conservation problems and that do not achieve conservation objectives. Social networks link organizations and individuals across space and time and determine the scale of conservation actions; thus, an understanding of the social networks associated with conservation planning will help determine the potential for implementing conservation actions at the required scales. Social‐network analyses can be used to explore whether these networks constrain or enable key social processes and how multiple scales of action are linked. Results of network analyses can be used to mitigate scale mismatches in assessing, planning, implementing, and monitoring conservation projects. Discordancia de Escalas, Planificación de la Conservación y el Valor del Análisis de Redes Sociales     

Use of Community‐Composition Data to Predict the Fecundity and Abundance of Species

Abstract: Species distribution models are critical tools for the prediction of invasive species spread and conservation of biodiversity. The majority of species distribution models have been built with environmental data. Community ecology theory suggests that species co‐occurrence data could also be used to predict current and potential distributions of species. Species assemblages are the products of biotic and environmental constraints on the distribution of individual species and as a result may contain valuable information for niche modeling. We compared the predictive ability of distribution models of annual grassland plants derived from either environmental or community‐composition data. Composition‐based models were built with the presence or absence of species at a site as predictors of site quality, whereas environment‐based models were built with soil chemistry, moisture content, above‐ground biomass, and solar radiation as predictors. The reproductive output of experimentally seeded individuals of 4 species and the abundance of 100 species were used to evaluate the resulting models. Community‐composition data were the best predictors of both the site‐specific reproductive output of sown individuals and the site‐specific abundance of existing populations. Successful community‐based models were robust to omission of data on the occurrence of rare species, which suggests that even very basic survey data on the occurrence of common species may be adequate for generating such models. Our results highlight the need for increased public availability of ecological survey data to facilitate community‐based modeling at scales relevant to conservation.     

基于神经网络的煤矿底板突水预测

阐述了运用人工神经网络建立煤矿底板突水预测模型的思路与方法,并以山东国家庄煤矿为例,对该方法的合理性和准确性进行了验证．研究表明,利用人工神经网络建立非线性系统的预测模型,具有自学习、自适应、精度高等显著优点．     

四川盆地西北部“92.1.22”电网特大污闪的成因及指标

四川盆地酉北部“９２·１·２２”电网特大污闪是全国电力史上最严重的污问事故,经济损失很大．它的成因：主要是大气被严重污染,空中污物多,气象条件利于污物在电网瓷瓶上大量积累,为污问的发生奠定了基础,污闪发生期内,气象条件利于形成引发闪污的闪雾的形成和持续;其次是电网的防污问能力差．其指标有：大气污染指标;利于污物在电网上大量积累的气象指标,与污问有关的气象要素历史背景指标;引发污问的污问雾的形成指标,污问将发生指标．