基于因子分析的BP神经网络对成都市需水量的预测

在对四川省成都市的水资源进行综合规划与评价的过程中,通过主成分因子分析可知人口、GDP、给排水管道长度等因素对需水量预测有较大影响,如何建立这些因素与需水量之间的数学关系是预测工作的重点。本文将介绍通过MATLAB数学分析软件建立BP神经网络预测模型,并对模型的预测结果进行评价。     

基于模糊神经网络的煤炭企业循环经济评价模型

针对煤炭企业循环经济水平具有模糊性的特点,利用模糊神经网络具有模糊化和良好泛化的能力,在探讨煤炭企业发展循环经济影响因素的基础上,从经济发展、资源利用、节能减排、环境状况、循环特征五个方面建立了煤炭企业循环经济评价指标体系,构建基于模糊神经网络的煤炭企业循环经济评价模型,并按照模糊神经网络结构的建立、输入数据的模糊化、输出数据的反模糊化、BP神经网络训练进行模型求解和运算,算例验证了该模型具有较好的学习能力.利用该模型评价煤炭企业循环经济具有有效性和准确性.     

基于BP神经网络的城市旅游环境质量评价

城市旅游环境质量与城市旅游可持续发展之间存在着极为密切的关系，实现可持续发展的关键就是要解决好城市旅游环境质量问题。而旅游资源环境、旅游自然生态环境、旅游社会服务环境、旅游信息环境是城市旅游环境质量评价的主要因素，利用BP神经网络的方法对城市旅游环境质量进行评价是十分科学有效的。     

模糊神经网络模型在拟建项目环境质量评价中的应用

由于评价因子与环境质量标准之间的模糊关系,导致传统的评价模型结果的不确定性。本文将模糊理论和神经网络模型相结合,利用模糊理论的隶属度反映各因子的质量相对状态,从而更精确地识别模糊性。通过模糊神经网络模型对环境质量标准样本的学习和测试,得出评价等级,并与模糊综合评价方法进行对比,实验结果表明,模糊神经网络模型用于环境质量评价是可行的,且比模糊综合评价方法更为客观、合理。     

基于Matlab的神经网络在绵阳空气质量预测中的应用

以绵阳市2014～2016年空气污染指数(API)以及SO_2、NO_2、PM_(10)等污染物为研究对象,探讨了绵阳市空气污染的变化规律,并分析它们与常规观测的地面气象资料之间的关系。尝试采用多元线性回归方法及BP神经网络方法建立污染预报模型,并检验分析两种模型的可行性。结果表明基于BP神经网络的预报模型在污染预报中可行,并建立基于BP神经网络进行空气质量预测的预测模型,利用历史资料进行验证。     

基于Adaboost集成BP网络原煤生产成本预测研究

为了提高传统BP神经网络预测模型精度,避免BP网络容易陷入局部极值、收敛速度慢等问题,将BP神经网络与Ada-boost算法相结合,提出了一种Adaboost集成BP神经网络模型.结合磁县观台煤矿原煤生产成本相关数据,建立了原煤生产成本预测的Adaboost集成BP神经网络模型,将该模型用于实际的原煤成本预测.结果表明：该模型预测精度高于传统的BP神经网络,收敛速度快,具有较强的鲁棒性,预测精度能满足实际预测需要,为原煤生产成本预测提供了一种新的途径,也为原煤生产成本控制提供了重要依据.     

修正的BP神经网络森林火灾成灾面积预测研究

以1997-2012年《中国林业统计年鉴》的全国森林火灾成灾面积为依据,应用BP神经网络模型对成灾面积进行了预测,对预测方法进行了检验.在此基础上,利用残差提出了修正的BP神经网络模型,并对预测方法进行了改进.研究结果表明,修正的BP神经网络预测精度高于BP神经网络,预测相对误差平均为7.2％,可应用于森林火灾成灾面积的预测.     

基于遗传神经网络模型的大气环境质量评价方法

设计了用遗传算法训练神经网络权重的新方法，实验结果显示了遗传算法快速学习网络权重和全局搜索的能力，有效地解决了BP算法的局部收敛问题。误差反向传播的遗传——神经网络(GA—BP)模型用于大气环境质量综合评价，具有简便、准确、客观和适应性强等优点。     

几种神经网络模型在空气质量评价中的应用

人工神经网络是一种利用计算机模拟人脑神经组织的运算模型。作为一种新的研究方法。神经网络在一定程度上可以弥补传统评价方法需要构建隶属函数、无法精确描述级别区间内的变化特征以及设计过程具有一定人为偏好的不足。本文选用BP网络、径向基函数网络、LVQ网络和Elman网络这4种典型的神经网络模型进行实例研究。把国内8个城市的污染物排放数据代入训练好的网络模型，进行空气质量评价，得出的结论对提高神经网络评价结果的准确性和可靠性有一定参考作用。     

城市旅游景观美学质量及其与景观格局的关系研究——以南京市为例

当前,城市旅游景观美学质量已经日益成为影响城市旅游竞争的一个重要因素。以江苏省南京市为例,同时采用美景度评估法对景观美景度进行评价,采用GIS、RS方法对景观空间格局进行分析,利用SPSS对美景度评价结果及其与格局指数的关系进行统计。结果表明:1评价者对开朗与闭合不同视域的景观,自然、人文与复合类不同类型的景观的审美无偏好;对闭合类景观、自然类景观审美趋于一致。2景观美景度与斑块数量、斑块密度之间呈负相关关系。3景观美景度与水域、草地所占景观面积之比为正相关关系,与交通所占景观面积之比为负相关关系。基于以上分析,建议对城市旅游景观规划应采取以下措施:适当降低斑块密度,增加水体、草地等自然类景观。     

Conversion of temperate forests into heaths: Role of ecosystem disturbance and ericaceous plants

Fire and logging in nutrient-poor temperate forests with certain ericaceous understory plants may convert the forests into heaths. The process of disturbance-induced heath formation is documented by using examples ofCalluna in western Europe,Kalmia in Newfoundland, andGaultheria (salal) in coastal British Columbia. In a cool, temperate climate, rapid vegetative growth ofCalluna, Kalmia, and salal following disturbance results in increasing organic accumulation (paludification), nutrient sequestration, soil acidification, and allelochemicals. These are thought to be the main reasons to conifer regeneration failure in disturbed habitats. If continuation in forest is a land-use objective, then temperate forests with an ericaceous understory should not be logged unless effective silvicultural methods are devised to control the ericaceous plants and restore forest regeneration. Preharvest vegetation control may be considered as an option. Failure to control the understory plants may lead to a long-term vegetation shift, from forest to heathland, particularly in nutrient-poor sites. Successful methods of controllingKalmia andGaultheria, however, have yet to be developed. While theKalmia- andGaultheria- dominated heathlands are undesirable in Canada and the Pacific Northwest, a wide range ofCalluna heathlands of western Europe are being conserved as natural and seminatural vegetation.     

BIOLOGICAL INDICATORS AND BIOLOGICAL EFFECTS OF ESTUARINE/COASTAL POLLUTION1

ABSTRACT: Sustained interest in and concern about the health status of the aquatic environment has resulted in extensive research focused on (1) effects of pollution on survival, growth, and reproduction of resource species at all life stages; (2) diseases of fish and shellfish, as they may be related to pollution and as they may serve as indicators of environmental stress; and (3) contaminant body burdens in fish and shellfish - their effects on the aquatic animals and their potential effects on humans. Effects, lethal and sublethal, of pollutants on life history stages of fish and shellfish have been documented, as have impacts on local stocks in badly degraded habitats, but as yet there has been no adequate quantitative demonstration of effects on entire aquatic species - probably because of the difficulty in sorting out relative effects of the many environmental factors that influence abundance. Sublethal effects, especially those that result in disease, have been examined intensively, and some diseases and disease syndromes have been associated statistically with pollution. Other pollution indicators (biochemical, physiological, genetic, behavioral, and ecological) have also received some attention, as have body burdens of contaminants in aquatic species. Research, especially that conducted during the past decade, has done much to clarify the many pathways and toxic effects of contaminants on aquatic animals, and has also helped to identify mechanisms for survival of fish and shellfish in the presence of environmental changes caused by human activities.     

Using Paleo Reconstructions to Improve Streamflow Forecast Lead Time in the Western United States

In water stressed regions, water managers are exploring new horizons that would help in long‐range streamflow forecasts. Oceanic‐atmospheric oscillations have been shown to influence streamflow variability. In this study, long‐lead time streamflow forecasts are made using a multiclass kernel‐based data‐driven support vector machine (SVM) model. The extended streamflow records based on tree ring reconstructions were used to provide a longer time series data. Reconstructed data were used from 1658 to 1952 and the instrumental record was used from 1953 to 2007. Reconstructions for oceanic‐atmospheric oscillations included the El Niño‐Southern Oscillation, Pacific Decadal Oscillation, Atlantic Multidecadal Oscillation, and North Atlantic Oscillation. Streamflow forecasts using all four oscillations were made with one‐year to five‐year lead times for 21 gages in the western United States. This is the first study that uses both instrumental and reconstructed data of oscillations in SVM model to improve streamflow forecast lead time. SVM model was able to provide “satisfactory” to “very good” forecasts with one‐ to five‐year lead time for the selected gages. The use of all the oscillation indices helped in achieving better predictability compared to using individual oscillations. The SVM modeling results are better when compared with multiple linear regression model forecasts. The findings are statistical in nature and are expected to be useful for long‐term water resources planning and management.     

Urban ecological systems: scientific foundations and a decade of progress

Urban ecological studies, including focus on cities, suburbs, and exurbs, while having deep roots in the early to mid 20th century, have burgeoned in the last several decades. We use the state factor approach to highlight the role of important aspects of climate, substrate, organisms, relief, and time in differentiating urban from non-urban areas, and for determining heterogeneity within spatially extensive metropolitan areas. In addition to reviewing key findings relevant to each state factor, we note the emergence of tentative "urban syndromes" concerning soils, streams, wildlife and plants, and homogenization of certain ecosystem functions, such as soil organic carbon dynamics. We note the utility of the ecosystem approach, the human ecosystem framework, and watersheds as integrative tools to tie information about multiple state factors together. The organismal component of urban complexes includes the social organization of the human population, and we review key modes by which human populations within urban areas are differentiated, and how such differentiation affects environmentally relevant actions. Emerging syntheses in land change science and ecological urban design are also summarized. The multifaceted frameworks and the growing urban knowledge base do however identify some pressing research needs.     

Neighbourhood characteristics and urban gardens in the Toledo metropolitan area: staffing and voluntarism,food production,infrastructure, and sustainability practices

Urban gardens are important sources of sustenance for communities with limited access to food. Hence, this study focuses on food production in gardens in the Toledo metropolitan area in Northwest Ohio. We administered surveys to 150 garden managers from November 2014 to February 2015 in our attempt to better understand how neighbourhood racial composition and poverty levels are related to staffing and voluntarism, food production and distribution, the development of infrastructure, and the adoption of sustainability practices in urban gardens. The results from 30 gardens are presented in this paper. We used Geographic Information Systems to map the gardens and overlay the map with 2010 census data so that we could conduct demographic analyses of the neighbourhoods in which the gardens were located. Though the gardens were small – two acres or less – up to 46 varieties of food were grown in a single garden. Gardens also operated on small budgets. Food from the gardens was gifted or shared with friends, family, and neighbourhood residents. Gardens in predominantly minority neighbourhoods tended to have fewer institutional partners, less garden infrastructure, and had adopted fewer sustainable practices than gardens in predominantly White neighbourhoods. Nonetheless, residents of predominantly minority and high-poverty neighbourhoods participated in garden activities and influenced garden operations. Volunteering and staffing were racialised and gendered.     

Journalists' views of advertiser pressures on agricultural news

All major journalism ethical codes explicitly state that journalists should protect editorial copy from undue influence by outside sources. However, much of the previous research on agricultural information has concentrated on what information various media communicate (gatekeeping studies) or communication's role in increasing innovation adoption (diffusion studies). Few studies have concentrated specifically on organizational and structural constraints that might adversely affect agricultural journalists' ethical standards; those that have, focus largely on farm magazines. A study of newspaper reporters who cover agricultural news found that the most pressing ethical concern is the effect of advertiser (agri-business) pressure on editorial copy, and that their concerns in general parallel those of farm magazine writers and editors. The majority reported being in situations in which they might be exposed to advertiser pressure, including pressures to change or withhold editorial copy. Large minorities suggested that advertising pressures affect the overall environment in which agricultural journalists work, and more than one in ten said they allow advertiser pressures to influence editorial decisions. The newspaper reporters who cover agricultural beats showed slightly more resistance to advertiser pressure than did farm magazine editors in a parallel study.     

Definition Procedures Have Little Effect on Performance of Environmental Classifications of Streams and Rivers

Mapped environmental classifications are defined using various procedures, but there has been little evaluation of the differences in their ability to discriminate variation in independent ecological characteristics. We tested the performance of environmental classifications of the streams and rivers of France that had been defined from the same environmental data using geographic regionalization and numerical classification of individual river valley segments. Test data comprised invertebrate assemblages, water chemistry, and hydrological indexes obtained from sites throughout France. Classification performance was measured by analysis of similarity (ANOSIM). Geometric regions defined by a regular grid and without regard to environmental variables and a posteriori classifications based on clustering the test datasets defined lower and upper bounds of performance for a given number of classes. Differences in classification performances were generally small. The ANOSIM statistics for the a posteriori classifications were around twice that of all environmental classifications, including geometrically defined regions. The hydro-ecoregions performed slightly better for the invertebrate data and the network classification performed slightly better for the chemistry and hydrological data. Our results indicate that environmental classifications that are defined using different procedures can be comparable in terms of their ability to discriminate variation of ecological characteristics and that alleged differences in performance arising from different classification procedures can be small relative to unexplained variation. We conclude that definition procedures might have little effect on the performance of large-scale environmental classifications and decisions over which procedures to use should be based primarily on pragmatic considerations.     

Predicting deer-vehicle collisions in an urban area

Collisions with deer and other large animals are increasing, and the resulting economic costs and risks to public safety have made mitigation measures a priority for both city and wildlife managers. We created landscape models to describe and predict deer-vehicle collision (DVCs) within the City of Edmonton, Alberta. Models based on roadside characteristics revealed that DVCs occurred frequently where roadside vegetation was both denser and more diverse, and that DVCs were more likely to occur when the groomed width of roadside right-of-ways was smaller. No DVCs occurred where the width of the vegetation-free or manicured roadside buffer was greater than 40 m. Landscape-based models showed that DVCs were more likely in more heterogeneous landscapes where road densities were lower and speed limits were higher, and where non-forested vegetation such as farmland was in closer proximity to larger tracts of forest. These models can help wildlife and transportation managers to identify locations of high collision frequency for mitigation. Modifying certain landscape and roadside habitats can be an effective way to reduce deer-vehicle collisions.     

MANGANESE CYCLE IN IMPOUNDMENT WATER

Manganese entering impounded water will undergo a cyclic transformation. Oxidation precipitates manganese from top waters. At the bottom of the lake, biological activity will render manganese soluble by both intracellular as well as extracellular activity. The study was made to demonstrate that biological reduction and transformation, organometallic complexation, together with the presence of carbon dioxide and the lowering of pH all have some effect on the solubility of manganese. Dissolved manganese may be brought back to top waters during the lake overturn and therefore deteriorates the water quality.     

Effect of Light on Biodegradation of Estrone, 17β‐Estradiol,and 17α‐Ethinylestradiol in Stream Sediment

Biodegradation of [A‐ring ¹⁴C] Estrone (E1), 17β‐estradiol (E2), and 17α‐ethinylestradiol (EE2) to ¹⁴CO₂ was investigated under light and dark conditions in microcosms containing epilithon or sediment collected from Boulder Creek, Colorado. Mineralization of the estrogen A‐ring was observed in all sediment treatments, but not epilithon treatments. No difference in net mineralization between light and dark treatments was observed for ¹⁴C‐E2. Net mineralization of ¹⁴C‐E1 and ¹⁴C‐EE2 was enhanced in light treatments. Extents of ¹⁴CO₂ accumulation and rates of mineralization were significantly greater for E2 than E1 under dark conditions, but were comparable under light conditions. These results indicate substantial differences in the uptake and metabolism of E1 and E2 in the environment and suggest biorecalcitrance of E1 relative to E2 in light‐limited environments. The extent of ¹⁴CO₂ accumulation and rate of mineralization for EE2 in dark treatments were less than half of that observed for E2 and generally lower than for E1, consistent with previous reports of EE2 biorecalcitrance. However, ¹⁴CO₂ accumulation and rates of mineralization were comparable for EE2, E2, and E1 under light conditions. These results indicate photoactivation and/or phototransformation/photodegradation processes can substantially enhance heterotrophic biodegradation of estrogens in sunlit environments and may play an important role in estrogen transport and attenuation.