Effects of Coastal Lighting on Foraging Behaviorof Beach Mice

Abstract:  Introduction of artificial light into wildlife habitat represents a rapidly expanding form of human encroachment, particularly in coastal systems. Light pollution alters the behavior of sea turtles during nesting; therefore, long-wavelength lights—low-pressure sodium vapor and bug lights—that minimize impacts on turtles are required for beach lighting in Florida (U.S.A.). We investigated the effects of these two kinds of lights on the foraging behavior of Santa Rosa beach mice (  Peromyscus polionotus leucocephalus ). We compared patch use and giving-up densities of mice for experimental food patches established along a gradient of artificial light in the field. Mice exploited fewer food patches near both types of artificial light than in areas with little light and harvested fewer seeds within patches near bug lights. Our results show that artificial light affects the behavior of terrestrial species in coastal areas and that light pollution deserves greater consideration in conservation planning.     

Stability of a Coal Waste Artificial Reef

The feasibility of using U.K. coal-fired power station waste materials for artificial reef production is being examined. in June, 1989, an experimental artificial reef was constructed in Poole Bay, off the central south coast of the U.K., using three different mixtures of pulverised fuel ash (PFA), flue gas desulphurisation (FGD) gypsum and slurry, stabilized with cement and formed into blocks. Fifty tonnes of 40 × 20 × 20 cm blocks were formed into eight conical reef units replicating three different PFA/gypsum mixtures and one concrete control. the reef structure is 10m below chart datum on a flat sandy sea-bed.

Combustion of coal concentrates the heavy metal content in the resultant ash. the purpose of stabilization of the ash as blocks is twofold: to immobilize heavy metals (or other components) and to provide hard substratum for the attachment of organisms. to examine the effectiveness of this stabilization and hence the environmental compatibility of the block materials, heavy metal (Cd, Cr, Cu, Pb, Mn, Ni, Zn) content of the blocks has been monitored routinely over two years, to determine leaching rates. Sectional profiles indicate partial replacement of calcium content by magnesium. Associated with this there has also been some redistribution of heavy metals. Only in the case of cadmium has there been a detectable loss from the surface of blocks. Chromium and manganese concentrations appear to have increased. the metal content of the reef epibiota (including ascidians, Ascidia mentula; hydroids, Halecium spp.; bryozoans, Bugula spp. and red algae) growing on the ash blocks has been compared to that of epibiota attached to the concrete controls and surrounding sea-bed. to date no evidence of excess bioaccumulation of metals has been detected.

The physical integrity of the ash reef blocks has been maintained. There is evidence that the blocks are increasing in compressive strength.

An indication of the fishery enhancement potential of the experimental structure is given by the presence of eight commercially fished species (crustaceans and molluscs) including lobsters (Homarus gammarus).     

人工神经网络在预测深基坑周边地表沉降变形中的应用研究

深基坑开挖引起的周边地表变形预测是一个复杂非线性问题,引起地表沉降的影响因素很多,各因素之间呈高度的非线性关系。传统的基坑用边地表沉降变形预测方法存在着一定的局限性,其预测精度有待提高,而人工神经网络是一种多元非线性动力学系统,可以灵活方便地对多成因的复杂未知系统进行高度建模,实现全面考虑各种主要影响因素的深基坑周边地表沉降变形预测。本文介绍了误差反向传播(BP)网络模型的结构、学习过程及其算法的改进,径向基函数(RBF)网络模型的结构及其学习过程;分析了影响深基坑开挖周边土体沉降变形的主要影响因素;以25个基坑工程的地表沉降实测资料为训练样本,建立了11个输入影响因素的BP神经网络模型和RBF神经网络模型,通过对样本的学习训练过程及对5个检验样本的预测精度,说明了人工神经网络用于预测基坑周边地表沉降的可行性和准确性。     

人工智能技术对长江流域水污染治理的思考

随着经济的快速发展和城市化进程的不断加速,促使水污染严重的长江流域需从污染物去除过程的建模与优化、污水处理过程的优化控制、水污染监测系统的构建开展水污染治理研究.传统的水污染处理技术存在污染物去除效率预测精度较低、污水优化控制成本较高、水污染监测滞后效应严重的问题.人工智能技术能够有效克服上述问题,因此通过梳理国内外学者利用人工智能技术在污水污染物去除过程的建模与优化、污水处理过程的优化控制及水污染监测系统的构建等方面的研究成果,为全面加强长江流域水污染治理能力提供科学可靠的技术指导.结果表明:①利用人工神经网络技术（径向基神经网络、多层前馈网络-人工神经网络、多层感知器神经网络）对污水污染物去除过程进行建模与优化,为精确预测长江流域重金属（Cr、Cu）、营养盐（TN、TP）、持久性有机污染物〔PBDEs（多溴二苯醚）、HCH（六氯环己烷）〕的去除率提供重要参考价值.②采用污水处理的自动控制技术与人工智能技术（递归神经网络、支持向量机、模糊神经网络等）构建污水智能控制系统,为长江流域实现高效节能的污水优化控制提供重要的技术指导.③利用在线监测仪器和人工智能技术（小波神经网络、多元线性回归-人工神经网络、叠层去噪自动编码器等）建立水污染智能监测系统,为解决长江流域水污染监测响应滞后问题提供有力的技术支持.因此,人工智能技术对长江流域提高污水污染物去除率,降低污水优化控制成本,提升水污染监测时效性具有重要的推广价值.      

基于神经网络的东北地区秸秆焚烧预测

选取农作物秸秆露天燃烧严重的东北地区,采用人工神经网络的方法,结合卫星火点和气象数据,开展秸秆露天燃烧预测研究.结果表明：人工神经网络预测模型成功验证了松嫩平原地区2015年10月25日~11月15日的秸秆露天燃烧情况,其准确度为67.1%,经过多次试验,在神经网络建模与验证数据配比为80：20时,预测准确度最高,可达69.7%,同时该模型的稳定性较好.而对不同区域,不同时间段的预测研究表明,人工神经网络较适用于长时间序列的预测.就影响因素而言,相对湿度是影响秸秆露天燃烧的最重要因素.本研究结果可为空气质量模式提供火点预测数据,提高其预报预警能力,为区域联防联控政策的制定提供科技支持.     

Land User Participation in Developing a Computerised Decision Support System for Combating Desertification

Combating desertification in natural rangelands has recently become a priority in large parts of southern Africa. Rangeland managers, farmers, scientists, conservationists and land users have been applying a variety of restoration technologies to address this problem. Bush encroachment, as part of the desertification process, involves the natural replacement of the herbaceous plant cover by undesirable problem woody species. The active and passive restoration technologies that are applied, are mainly based on indigenous knowledge and include the chemical, mechanical or manual reclamation of unproductive rangelands, as well as the combating of woody and alien species encroachment. Indigenous practices and knowledge play a major role in the effectiveness and success rate of these technologies. This project faces the challenge of bringing together both local and scientific knowledge in a single user-friendly, computerised Decision Support System (DSS) which is directly accessible by land users to support them in the process of decision making, concerning the combating of desertification. Case studies from central and northern Namibia were used to combine qualitative and quantitative data to develop this Decision Support System. The DSS currently consists of two databases and an expert system, which evaluates the results of land users’ management practices, and provides easily accessible information and advice for participants in the system, based on the incorporated data. The DSS is also linked to national and international web sites and databases to offer a wider range of information on technologies concerning agricultural and conservation practices.     

BP人工神经网络预测邻苯二甲酸酯光化学降解

将反向传播人工神经网络（BP－ANN）用于邻苯二甲酸酯类化合物的光化学降解的预测中，选取正交设计的试验点作为反向传播人工神经网络的训练集，实现对全实验域试验点的预测，并与实测的试验数据比较。结果表明反向传播人工神经网络（BP－ANN）具有良好的预测能力。     

基于人工神经网络的行业无害化生产能力评价模型研究

利用BP前向人工神经网络方法 ,建立了一种全新的基于人工神经网络的行业无害化生产能力评价模型 ,该模型采用动量梯度下降反向传播和学习速率自适应调整相结合的训练学习算法。最后 ,以造纸及纸制品业为例 ,对中国各省市造纸行业的无害化生产能力进行评价 ;并进一步分析中国各省造纸行业无害化生产能力的时空分布规律 ,为我国行业规划、布局决策提供科学依据。     

兼性生化处理生活污水最佳工况研究

在常温条件下进行兼性生化处理生活污水试验,研究COD去除率与HRT、MLSS、进水有机物浓度和混合液水温的关系。在试验中最佳的水平搭配为MLSS=5500mg/L,进水有机物浓度=180mg/L,HRT=8h和混合液水温=20℃,与回归分析所得出MLSS=5881mg/L,进水有机物浓度=192.7mg/L,HRT=8.9063h和混合液水温=21.3790℃的最佳工艺条件相吻合。最后通过等高线分析得出常温下生活污水兼性生化的适宜范围。     

循环式活性污泥法中厌氧生物选择区的运行条件研究

研究了循环式活性污泥法中厌氧生物选择区的停留时间、进水有机物浓度和系统中泥龄、曝气时间等运行参数对选择区内厌氧释磷以及有机物的吸收贮存的影响。结果表明，选择区停留时间lh，系统泥龄5d，曝气2h，进水有机物浓度COD／TP=60--70，选择器中释磷效果及微生物的吸附性能最优，可去除进水中78％的COD。而且污泥沉降性能良好，试验运行过程中，SVI一直保持在30--40ml／g左右。