决策树模型在水环境监测网络中选取代表性样点的应用

地表水体中的硝酸盐污染已经成为全球关注的热点环境问题之一。现今,国内外均建立了相关的监测网络对地表水体的水质实施长期监测,但是却导致大量的监测数据累积,给后续的科学研究工作带来了不便,尤其是在庞大的监测网络中如何选取有代表性样点的研究点则成为急需解决的问题之一。以比利时弗拉芒地区地表水的长期监测物理化学指标为例,利用决策树模型评估地表水样点的硝酸盐污染来源专家分类的有效性,为点位优化提供理论依据。原有监测点位的污染源专家分类和模型输出的可匹配率为80%,优化后监测点位从原有47个点降低到30个点,提高了监测工作效率。     

基于3种时间序列模型的九龙江河流库区藻华预测

湖库富营养化和有害藻华是全球性生态环境问题,藻华预测与早期预警是保障湖库水源地供水安全的关键技术.如何基于高频水生态在线监测数据进行藻华的实时动态预测成为水生态管理领域的重大需求.本研究以福建省九龙江江东库区(水源地)为例,利用3年连续观测的逐时平均总叶绿素a浓度数据,对比研究了SARIMA、Prophet和LSTM(长短期记忆神经网络)3种时间序列模型在藻华(日平均叶绿素a大于15μg·L^-1)预测方面的效果.结果表明：(1)时间序列模型要求参数少,灵活性强,能清晰反映水质特征和未来变化趋势,可弥补传统藻类监测预警方法的局限性;(2)基于深度学习框架的LSTM模型,具有独特的迭代优化算法,对藻类非线性变化特征的识别和预测能力较强,其总叶绿素a逐日预测和7日预测效果均显著优于SARIMA模型和Prophet模型;(3)输入数据长度会在一定程度上影响模型预测效果,最优的输入数据时间长度为7 d;输入数据频率对预测效果也有影响,在预测非藻华日时,小时数据的预测效果优于日频率数据;在预测藻华日时,两种频率数据无显著差异,但日频率数据能更准确识别藻华日特征.总结起来,基于...     

Estimating the extent and structure of trade in horticultural orchids via social media

The wildlife trade is a lucrative industry involving thousands of animal and plant species. The increasing use of the internet for both legal and illegal wildlife trade is well documented, but there is evidence that trade may be emerging on new online technologies such as social media. Using the orchid trade as a case study, we conducted the first systematic survey of wildlife trade on an international social‐media website. We focused on themed forums (groups), where people with similar interests can interact by uploading images or text (posts) that are visible to other group members. We used social‐network analysis to examine the ties between 150 of these orchid‐themed groups to determine the structure of the network. We found 4 communities of closely linked groups based around shared language. Most trade occurred in a community that consisted of English‐speaking and Southeast Asian groups. In addition to the network analysis, we randomly sampled 30 groups from the whole network to assess the prevalence of trade in cultivated and wild plants. Of 55,805 posts recorded over 12 weeks, 8.9% contained plants for sale, and 22–46% of these posts pertained to wild‐collected orchids. Although total numbers of posts about trade were relatively small, the large proportion of posts advertising wild orchids for sale supports calls for better monitoring of social media for trade in wild‐collected plants.     

GIS网络服务区分析在重庆市主城区夜间施工噪声投诉处置中应用

通过对重庆市主城区夜间施工噪声投诉处置现状分析,以主城区道路交通网络、环境监察机构分布等数据专题建模,采用G IS的网络服务区功能的分析结果,提出车辆调度合理化建议方案,为环境监察部门的夜间施工噪声投诉处置车辆部署调度提供辅助技术支持。     

JUSTIFICATION FOR A REDUCTION IN THE CREST-STAGE GAGE PROGRAM IN LOUISIANA1

The crest-stage gage program in Louisiana was evaluated to determine if the data were adequate for use in developing regional flood-frequency equations and to determine if any crest-stage gage stations could be discontinued. An abundance of data at many crest-stage gage stations and a lack of data for urban areas and flat-slope areas indicated a need for a shift in the number, type, and locations of gages. Correlations and comparisons of annual peak discharges and watershed characteristics of 96 existing stations resulted in the elimination of 72 stations and the addition of one new station, reducing the total network to 25 stations that could be used for future flood-frequency analyses. The adequacy of the reduced network for development and verification of regional flood-frequency equations was tested by comparing a set of regional flood-frequency equations developed using data from the full network with a set developed using data from the reduced network. The results indicate that the crest-stage gage network can be reduced to 25 stations and still provide adequate information for future flood-frequency analyses.     

Large-scale constructed wetlands for nutrient removal from stormwater runoff: An everglades restoration project

The South Florida Water Management District (SFWMD) constructed a wetland south of Lake Okeechobee to begin the process of removing nutrients (especially phosphorus) from agricultural stormwater runoff entering the Everglades. The project, called the Everglades Nutrient Removal (ENR) project, is a prototype for larger, similarly constructed wetlands that the SFWMD will build as part of the Everglades restoration program. This innovative project is believed to be one of the largest agricultural stormwater cleanup projects in the United States, if not in the world. This publication describes the ENR project's design, construction, and proposed operation, as well as the proposed research program to be implemented over the next few years.     

计算机局域网络保密措施

随着计算机的普及 ,局域网络越来越广为利用 ,但也出现了相应的失密问题。本文从信息及实体两个方面 ,论述了局域网络的保密措施。     

基于神经网络的温度预测

室内温度与诸多影响因素之间的非线性、复杂性等关系 ,给建模、预测带来了难度 ,引入了人工神经网络 ;利用人工神经网络的非线性、并行计算和自学习特性进行建模 ,实现了对温度模拟     

煤体注水湿润半径预测的神经网络模型

合理的注水半径一直是煤体注水防尘技术中难以确定的参数。笔者基于对影响煤体注水半径因素的分析和神经网络理论的原理之上 ,设计网络模型为 3层 ,输入层为 7个节点 ,应用BP网络算法 ,建立了煤体注水湿润半径的预测模型 ,并对其参数进行了讨论。然后 ,用平顶山矿务局和水城矿务局 13个矿 19个回采工作面的统计资料对BP网络进行自适应学习 ,并取η =0 .9,α =0 .82 ,控制网络总误差E≤ 10 6。经过 2 12 34次迭代后 ,网络趋于稳定。用训练好的网络对平顶山矿务局的某矿的 3层煤的注水湿润半径进行预测 ,预测结果与实测值很接近。其误差分别为 0 .5 %,0 .6 %和 0 .7%。     

滨海平原咸水入侵动态监测网构建研究——以潍河下游地区为例

作为进行咸水入侵动态监测的基础性工作，对潍河下游地区的供需水平衡及地下水位、水质和地层电阻率在咸淡水界面上变化规律进行了研究分析；同时，探索了监测工作的地理工程技术途径，并据此构建了3个层次的监测体系：（1）宏观区域供需水平衡分析与地下水位负值区变化监测，（2）中观咸水入侵发展变化的物探监测，（3）微观地下水位、水质变化监测；最后，为了对日益增多的咸水入侵动态数据资料进行有效的管理，设计了一个基于GIS的、以数据库管理应用为核心的信息系统。