基于概率神经网络的城市湖泊生态系统健康评价研究

概率神经网络(PNN)是一种结构简单、训练简捷、应用十分广泛的人工神经网络,并且在水质分类等环境领域已取得一定研究成果.本文选取广州市最大的人工湖——白云湖作为研究对象,结合其水质监测数据及生物监测数据,建立概率神经网络模型对其进行湖泊生态系统健康评价,得到不同监测时间点的湖泊生态系统健康评价结果.分析表明:1白云湖生态系统比较脆弱,目前净化水质的效果有限;2各监测点的评价结果均呈季节性变化,丰水期湖泊生态系统健康状态好于枯水期,年际变化不显著.实验结果表明,利用概率神经网络对湖泊生态系统健康状态进行评价是可行的,与传统评价方法相比,其具有训练时间短、权重确定客观、输出结果稳定等优势,可以运用到更多相关领域.     

Citizens of local jurisdictions enhance plant community preservation through ballot initiatives and voter-driven conservation efforts

Open space areas protected by local communities may augment larger scale preservation efforts and may offer overlooked benefits to biodiversity conservation provided they are in suitable ecological condition. We examine protected areas established by local communities through ballot initiatives, a form of direct democracy, in California, USA. We compare ecological conditions of wooded habitats on local ballot protected sites and on sites protected by a state-level conservation agency. Collectively, we found few differences in ecological conditions on each protected area type. Ballot sites had greater invasive understory cover and larger trees. Community dissimilarity patterns suggested ballot sites protect a complementary set of tree species to those on state lands. Overall, geographic characteristics influenced onsite conditions more than details of how sites were protected. Thus, community-driven conservation efforts contribute to protected area networks by augmenting protection of some species while providing at least some protection to others that might otherwise be missed.Electronic supplementary materialThe online version of this article (10.1007/s13280-020-01469-8) contains supplementary material, which is available to authorized users.     

Biodegradable dissolved organic carbon shapes bacterial community structures and co-occurrence patterns in large eutrophic Lake Taihu

Interactions between dissolved organic matter (DOM) and bacteria are central in the biogeochemical cycles of aquatic ecosystems; however, the relative importance of biodegradable dissolved organic carbon (BDOC) compared with other environmental variables in structuring the bacterial communities needs further investigation. Here, we investigated bacterial communities, chromophoric DOM (CDOM) characteristics and physico-chemical parameters as well as examined BDOC via bioassay incubations in large eutrophic Lake Taihu, China, to explore the importance of BDOC for shaping bacterial community structures and co-occurrence patterns. We found that the proportion of BDOC (%BDOC) correlated significantly and positively with the DOC concentration and the index of the contribution of recent produced autochthonous CDOM (BIX). %BDOC, further correlated positively with the relative abundance of the tryptophan-like component and negatively with CDOM aromaticity, indicating that autochthonous production of protein-like CDOM was an important source of BDOC. The richness of the bacterial communities correlated negatively with %BDOC, indicating an enhanced number of species in the refractory DOC environments. %BDOC was identified as a significant stronger factor than DOC in shaping bacterial community composition and the co-occurrence network, suggesting that substrate biodegradability is more significant than DOC quantity determining the bacterial communities in a eutrophic lake. Environmental factors explained a larger proportion of the variation in the conditionally rare and abundant subcommunity than for the abundant and the rare bacterial subcommunities. Our findings emphasize the importance of considering bacteria with different abundance patterns and DOC biodegradability when studying the interactions between DOM and bacteria in eutrophic lakes.     

石油污染土壤富集前后细菌群落组成和共现网络分析

为了探究石油污染土壤中细菌群落在富集过程中的演替规律,试验采用平板划线法、菌落PCR和高通量测序技术,分析了富集前后细菌群落结构、共现网络和核心菌属组成,并对富集后体系中的微生物进行分离鉴定,筛选石油降解菌.研究表明富集体系中可培养微生物隶属于34个属53个种,其中3个为潜在新种微生物,Dietzia maris OS33和Rhodococcus qingshengii OS62-1具有降解石油的能力.高通量测序结果显示,在门分类水平上,富集前后丰度较高的菌门均为Proteobacteria和Actinobacteria,富集后两菌门的丰度可达到97.98%,占据绝对优势;丰度较高菌属由Pseudomonas、Rhodococcus、Bacillus和Xanthomonas转变为Dietzia、Unspecified_Idiomarianceae和Halomonas,标志微生物转变为与石油降解有关的Dietzia.细菌群落共现网络在富集后,网络结构进一步简化且更加稳定,核心微生物转变为与石油降解有关的Pseudomonas、Lysinibacillus、Pseudochrobactrum、Agrobacterium、Lactobacillus,且非石油降解菌P.songnenensis P35可协同石油降解菌D.maris OS33降解石油.     

改性生物炭负载零价铁对土壤中三氯乙烯的去除及微生物响应

三氯乙烯是场地及地下水中广泛存在的典型有机污染物,生物炭基零价铁材料可用于去除地下水中三氯乙烯,然而其也会影响含水层土壤的微生物群落,进而改变三氯乙烯的归趋.通过限氧控温热解,NaOH和HNO₃改性处理,并采用球磨法合成了改性生物炭负载零价铁复合材料,研究了不同改性生物炭负载零价铁对模拟含水层土壤中三氯乙烯的去除及微生物群落的作用机制.结果表明,NaOH改性显著提高了复合材料的比表面积.NaOH改性和Fe/BC为1∶10的复合材料(BC＿2处理组)对三氯乙烯的去除率最高,为90.01%.除BC＿1处理组外,不同处理组均提高了土壤微生物的多样性,改变了微生物群落结构,其中芽孢杆菌属(Bacillus)、硫杆菌属(Thiobacillus)和假单胞菌属(Pseudomonas)可能是三氯乙烯的降解菌属.BC＿2处理组增加了土壤中硫杆菌属和假单胞菌属的相对丰度,有利于三氯乙烯的降解.类诺卡氏菌属(Nocardioideas)、Thermincola、溶杆菌属(Lysobacter)、Gemmatimonas、Microvirga和假单胞菌属维持了微生物群落结构的稳定.微...     

A method for simplifying the analysis of traffic accidents injury severity on two-lane highways using Bayesian networks

Introduction

This study describes a method for reducing the number of variables frequently considered in modeling the severity of traffic accidents. The method's efficiency is assessed by constructing Bayesian networks (BN).

Method

It is based on a two stage selection process. Several variable selection algorithms, commonly used in data mining, are applied in order to select subsets of variables. BNs are built using the selected subsets and their performance is compared with the original BN (with all the variables) using five indicators. The BNs that improve the indicators’ values are further analyzed for identifying the most significant variables (accident type, age, atmospheric factors, gender, lighting, number of injured, and occupant involved). A new BN is built using these variables, where the results of the indicators indicate, in most of the cases, a statistically significant improvement with respect to the original BN.

Conclusions

It is possible to reduce the number of variables used to model traffic accidents injury severity through BNs without reducing the performance of the model.

Impact on Industry

The study provides the safety analysts a methodology that could be used to minimize the number of variables used in order to determine efficiently the injury severity of traffic accidents without reducing the performance of the model.     

基于PSR与贝叶斯网络的非常规突发事件情景分析

基于情景分析在非常规突发事件应急决策中的重要性,为了提高情景分析的有效性、全面性,在非常规突发事件"情景"界定和演变规律分析的基础上,基于PSR模型构建非常规突发事件的"压力-状态-响应"网络表达方式;利用贝叶斯网络理论,构建非常规突发事件的情景演变分析模型;以简化后的大连输油管道爆炸事件为例,示范基于PSR模型与贝叶斯网络的非常规突发事件情景分析方法的具体流程,并对推理结果进行分析。分析结果与现实情况基本一致,证明方法的可行性和有效性。实际应用中可针对具体的事件进行"多响应"、"多路径"的推理分析,以全面、系统地分析事件情景的演变情况。     

机动车闯红灯判别模型及评价研究

为了提高机动车闯红灯警示系统判别准确率,提出适用于该系统的机动车闯红灯判别模型并进行评价。首先综述闯红灯警示系统的产生与发展现状,根据系统服务需求与工作流程,提出使用Logistic回归与神经网络方法建立判别模型预测机动车停止-通过行为,通过城市交通实测数据对模型进行评价。数据采集自上海城市道路交叉口进口道,通过Autoscope视频检测系统提取机动车运行数据。评价结果表明,Logistic回归与神经网络模型正确判别率均达到90%以上,神经网络具有更好的判别准确率。相对于速度,当前检测地点与上游地点30 m处车速差或速度比更宜作为模型中的判别参数。     

Disaster coordination preparedness of soft-target organisations

This paper introduces a network‐enabled model to examine the disaster coordination preparedness of soft‐target organisations (STOs). Little attention is devoted to this matter in recent research. This study places emphasis on such organisations and the proposed model tests hypotheses related to network relation and coordination preparedness. It analyses the data set entitled ‘Preparedness of large retail malls to prevent and respond to terrorist attack, 2004′, which contains 120 completed surveys of security directors of retail malls in the United States. ¹ 1 See http://www.icpsr.umich.edu/icpsrweb/TPDRC/studies/21140 .
The following questions form the basis of this study: ‘What do STOs need to be better prepared to respond to a disaster?’; ‘How does network relationship between STOs and emergency agencies affect the coordination preparedness of STOs for disaster recovery?’; and ‘Which centrality measure needs to be followed to measure network variables in order to analyse coordination preparedness?’ The results show that STOs with a high level of connectedness and strong ties to other emergency agencies are better prepared for disaster response.     

A novel method for mapping reefs and subtidal rocky habitats using artificial neural networks

Reefs and subtidal rocky habitats are sites of high biodiversity and productivity which harbour commercially important species of fish and invertebrates. Although the conservation management of reef associated species has been informed using species distribution models (SDM) and community based approaches, to date their use has been constrained to specific regions where the locality and spatial extent of reefs is well known. Much of the world's subtidal habitats remain either undiscovered or unmapped, including coasts of intense human use. Consequently, to facilitate a stronger understanding of species-environmental relationships there is an urgent need for a cost and time effective standard method to map reefs at fine spatial resolutions across broad geographical extents. We used bathymetric data (∼250 m resolution) to calculate the local slope and curvature of the seabed. We then constructed artificial neural networks (ANNs) to forecast the probability of reef occurrence within grid cells as a function of bathymetric and slope variables. Testing over an independent data set not used in training showed that ANNs were able to accurately predict the location of reefs for 86% of all grid cells (Kappa = 0.63) without over fitting. The ANN with greatest support, combining bathymetric values of the target grid cell with the slope of adjacent grid cells, was used to map inshore reef locations around the Southern Australian coastline (∼250 m resolution). Broadly, our results show that reefs are identifiable from coarse-scale bathymetry data of the seabed. We anticipate that our research technique will strengthen systematic conservation planning tools in many regions of the world, by enabling the identification of rocky substratum and mapping in localities that remain poorly surveyed due to logistics or monetary constraints.