基于U-Net深度神经网络的早期火灾烟雾自动分割方法

在火灾事件监测中,为了减少数据处理量、加快探测速度,需要先分割出疑似烟雾区域。传统的烟雾分割算法大多需要设置阈值进行处理,算法的环境适应能力还需进一步提升。在研究中,使用U-Net结构的深度神经网络进行早期火灾烟雾的自动分割,通过半自动算法人工辅助分割出烟雾区域的图像样本,基于深度神经网络对分割烟雾区域进行学习,得到原始视频帧到分割结果的映射模型,并据此模型进行烟雾区域分割。在测试集上的分割实验结果表明该方法与传统方法相比,不需要设置阈值,自动化程度更高,分割速度极快,在疑似烟雾区域分割任务中性能较好。     

不同水文情景下白洋淀水体好氧反硝化菌群对水质因子的动态响应

为探究不同水文情景下白洋淀水体好氧反硝化菌群的演变规律和驱动机制,基于水质调查和高通量测序技术,进行了水体水质因子分析、好氧反硝化菌群α多样性分析、物种组成和网络分析.结果表明,白洋淀水体呈弱碱性,丰水期水体T最高,DO最低,冰封期T最低,DO最高.白洋淀水体在枯水期、丰水期、平水期和冰封期下NH₄⁺-N、NO₂^--N、NO₃ ^--N、TN、高锰酸盐指数、Fe和Mn之间均存在显著差异（P < 0.01）,其中TP在不同水文情景下不存在显著差异（P > 0.05）.不同水文情景下水体中最大的细菌门类为Proteobacteria,相对丰度较高的属为Magnetospirillum、Aeromonas、Pseudomonas、Azospirillum和Bradyrhizobium.此外,好氧反硝化菌群的α多样性均存在显著差异（P < 0.001）,冰封期菌群丰富度最高,枯水期和冰封期菌群的多样性和均匀度最高.经RDA、Mantel分析,菌群的水质驱动因子在不同水文情景下有所差异,枯水期菌群的水质驱动因子为pH、NO₃^--N、NO₂^--N和高锰酸盐指数,丰水期菌群的驱动因子为pH、T、DO、NO₂^--N和TP,平水期的驱动因子为NO₂^--N、Fe和高锰酸盐指数,冰封期菌群的驱动因子为NO₃^--N和NO₂^--N.网络分析表明与水质驱动因子相关的物种存在时间差异,枯水期与水质驱动因子相关的属为Magnetospirillum、Aeromonas和Azoarcus,与丰水期相关的属为Magnetospirillum、Pseudomonas和Aeromonas,与平水期相关的属为Magnetospirillum、Pseudomonas和Limnohabitans,与冰封期相关的属为Magnetospirillum、Azoarcus和Pseudomonas.不同水文情景关键水质因子（主要是T、DO、NO₃^--N和高锰酸盐指数）与好氧反硝化菌群之间的关联关系,随着时间演变也在逐渐发生变化.综上,通过对不同水文情景下白洋淀水体好氧反硝化菌群演变特征及环境因子驱动机制进行研究,可为认识天然环境中好氧反硝化菌群演变机制提供依据.     

Assessing the current state of ecological connectivity in a large marine protected area system

The establishment of marine protected areas (MPAs) is a critical step in ensuring the continued persistence of marine biodiversity. Although the area protected in MPAs is growing, the movement of individuals (or larvae) among MPAs, termed connectivity, has only recently been included as an objective of many MPAs. As such, assessing connectivity is often neglected or oversimplified in the planning process. For promoting population persistence, it is important to ensure that protected areas in a system are functionally connected through dispersal or adult movement. We devised a multi-species model of larval dispersal for the Australian marine environment to evaluate how much local scale connectivity is protected in MPAs and determine whether the extensive system of MPAs truly functions as a network. We focused on non-migratory species with simplified larval behaviors (i.e., passive larval dispersal) (e.g., no explicit vertical migration) as an illustration. Of all the MPAs analyzed (approximately 2.7 million km²), outside the Great Barrier Reef and Ningaloo Reef, <50% of MPAs (46-80% of total MPA area depending on the species considered) were functionally connected. Our results suggest that Australia's MPA system cannot be referred to as a single network, but rather a collection of numerous smaller networks delineated by natural breaks in the connectivity of reef habitat. Depending on the dispersal capacity of the taxa of interest, there may be between 25 and 47 individual ecological networks distributed across the Australian marine environment. The need to first assess the underlying natural connectivity of a study system prior to implementing new MPAs represents a key research priority for strategically enlarging MPA networks. Our findings highlight the benefits of integrating multi-species connectivity into conservation planning to identify opportunities to better incorporate connectivity into the design of MPA systems and thus to increase their capacity to support long-term, sustainable biodiversity outcomes.     

乡村振兴背景下社区居民旅游创业意愿研究——基于分布式认识理论

在乡村振兴背景下,选择兰州市榆中县浪街村社区为研究对象,依托分布式认知理论,构建了居民旅游创业意愿和影响因素模型。结果发现:(1)个人力因素不是形成创业意愿的决定性因素。(2)在地域力方面,大部分居民参与旅游创业的资源条件有限。(3)在文化力方面,领导和以领导为核心的社会关系网是旅游创业意愿形成和转变的决定性因素,并且能够将这种创业意愿转化为创业行为。在研究基础上,提出对策建议:注意培育旅游创业主体,增强现存社区创业能力,争取外部专家与辅助者的支持,以增强乡村旅游发展的可持续性。     

基于贝叶斯网络的基本农田划定方法

基本农田划定是落实耕地保护、保证粮食安全的关键问题。目前,基本农田划定的相关研究多基于对耕地适宜性条件的评价,而未涉及对耕地历史变化过程的考虑,因而不能保证划定结果适应实际区域的耕地变化趋势,导致基本农田易被占用,补划与调整频繁。论文综合考虑耕地适宜性条件与历史动态变化状况,提出了一种基于贝叶斯网络模型的基本农田划定方法。以湖北省大冶市这一典型资源型城市为实验区进行了实例研究,划定结果表明,该划定方法能在保证基本农田划定数量与质量的同时,提高其农业用途的稳定性,促进基本农田保护与经济建设、生态保护间协调发展,是一种有效的划定模型。     

基于空间拟合和神经网络的机场噪声预测集成模型

将集成学习方法引入到机场噪声预测中,提出一种基于空间拟合和神经网络的机场噪声预测集成模型.该模型采用空间拟合算法和BP神经网络算法构建基学习器,然后通过所提出的基于观察学习的异构集成算法将基学习器集成起来,获得集成的机场噪声预测结果.该模型通过集成多个异构机场噪声预测基学习器,能够有效提升预测准确率.实验结果表明,本文所提出的基于观察学习的异构集成算法,较之其他异构集成算法,在解决机场噪声预测问题上准确性更高、容错性更强.     

人工神经网络在矿井多水源识别中的应用

以焦作矿区水化数据为例,选用Na++K+、Ca2+、Mg2+、Cl-、SO2-4、HCO-36种水化离子浓度作为识别矿井水源的依据,运用Matlab软件分别建立BP神经网络与Elman神经网络的矿井多水源识别模型。应用结果表明:与静态的BP神经网络相比,在结构上增加承接层的Elman神经网络在训练和仿真中拟合能力更强,识别精度更高和泛化能力更好;矿井地下水随着地下开采与扰动具有动态性,将具有非线性动态特征的Elman神经网络应用于矿井多水源的识别,对准确判断突水来源和分析地下水运移规律具有一定的辅助和指导意义。     

Bibliometric analysis of ecosystem monitoring-related research in Africa: implications for ecological stewardship and scientific collaboration

Regional ecosystem monitoring is a central form of knowledge sharing and collaboration amongst scientists and decision makers on environmental health, land use change, and science-policy development. Despite the proliferation of such research networks on long-term monitoring on many continents, little has been achieved in Africa. This study aims to assess and examine the spatiotemporal trend and categorical patterns in ecosystem monitoring-related research in Africa for the benefits of conserving biodiversity and sustaining natural resource sectors for well-being and livelihood security, environmental planning, and ecological stewardship. A systematic review was conducted using bibliometric tools. Based on a set of search terms and peer-reviewed publications retrieved from various ecosystem monitoring networks and journal databases, further analysis was conducted using social network approaches, mapping tools, and content analysis. About 1442 scientific publications on ecosystem monitoring and related research were documented from 1987 to 2014 mostly published in English. The number of publication increased progressively since 1992 after the Convention on Biodiversity was signed and this trend peaked till 2008. South African Journal of Science was the most leading journal and Nature the most cited. Internationally coauthored and collaborative articles represented majority of the findings with the United Kingdom at the central position in the research network due to colonial relationships. Regional collaboration amongst countries is limited owing to language barriers and other institutional constraints such as funding and short-term projects. These findings have implication for prioritizing national and regional policies toward biodiversity science and its contribution to human well-being, food security, and global change responses.     

Exploration of spatial morphometry and socioeconomic variables in modelling urban land use change

The incorporation of land use (LU) data with socioeconomic data is a main issue in modelling. This is as a result of difference in data model and scale. This study proposed and tested the change–pattern approach, which allows the incorporation of these data sets in modelling LU change. Focusing on LU dynamics for a selected part of the Thames Gateway within the City of London, the approach tested two different methods of input selection for the modelling operations. Variables selected from these two methods serve as inputs into several neural networks tested in order to identify the direction of change for each of the LU types within the study area. The result shows that direction of LU change across the study area could be identified when spatial morphology of the area and socioeconomic variables are considered. Some classes of change could be identified fairly accurately using landscape metrics indicating level of fragmentation, extent of LU patches, shape complexity of LU patches in combination with some socioeconomic variables.     

基于自适应遗传小波神经网络的水质评价建模

水环境污染过程的非确定性和非线性,使得传统的水质评价方法存在局限性。为了提高水质评价的准确性,提出了一种基于改进小波神经网络(wavelet neural network,WNN)的水质评价模型。采用自适应遗传算法(adaptive genetic algorithm,AGA)对小波神经网络的初始权值进行优化,再通过小波神经网络算法对网络进行训练,最后对训练好的网络展开测试。仿真结果表明,自适应遗传算法和小波神经网络的结合提高了网络的训练效率,该方法可以用于水质评价建模,并且评价结果具有较高的精度和准确性。