西太平洋深海海水中乙醛降解菌多样性及群落结构研究     

高波良  商谢谢  李丽  狄文婕  曾润颖 《海洋学报(英文版)》2018,37(8):54-64

As a major aldehyde pollutant widely existing in industry and our daily life, acetaldehyde is more and more harmful to human health. As characteristic habitat niche, bacteria from deep sea environments are abundant and distinctive in heredity, physiology and ecological functions. Thus, the development of acetaldehyde-degrading bacteria from deep sea provides a new method to harness acetaldehyde pollutant. Firstly, in this study,acetaldehyde-degrading bacteria in the deep sea water of the West Pacific Ocean were enriched in situ and in the laboratory respectively, and then the diversity of uncultured bacteria was studied by using 16 S r RNA genes. Then acetaldehyde-degrading strains were isolated from two samples, including enrichment in situ and enrichment in laboratory samples of deep sea water from the West Pacific Ocean using acetaldehyde as the sole carbon source,and then the ability of acetaldehyde degradation was detected. Our results showed that the main uncultured bacteria of two samples with different enrichment approaches were similar, including Proteobacteria,Actinobacteria, Firmicutes, Cyanobacteria, but the structure of bacterial community were significant different.Four subgroups, α, γ, δ and ε, were found in Proteobacteria group. The γ-Proteobacteria was dominant(63.5%clones in laboratory enriched sample, 75% clones in situ enriched sample). The species belonged to γ-Proteobacteria and their proportion was nearly identical between the two enrichment samples, and Vibrio was the predominant genus(45% in laboratory enriched sample, 48.5% in situ enriched sample), followed by Halomonas(9% in situ enriched sample) and Streptococcus(6% in laboratory enriched sample). A total of 12 acetaldehyde-degrading strains were isolated from the two samples, which belonged to Vibrio, Halomonas,Pseudoalteromonas, Pseudomonas and Bacillus of γ-Proteobacteria. Strains ACH-L-5, ACH-L-8 and ACH-S-12,belonging to Vibrio and Halomonas, have strong ability of acetaldehyde degradation, which could tolerate 1.5 g/L acetaldehyde and degrade 350 mg/L acetaldehyde within 24 hours. Our results indicated that bacteria of γ-Proteobacteria may play an important role in carbon cycle of deep sea environments, especial the bacteria belonging to Vibrio and Halomonas and these strains was suggested for their potentials in government of aldehyde pollutants.  相似文献   

基于卷积神经网络与条件随机场方法提取乡镇非正规固体废弃物     

刘懿兰  黄晓霞  李红旮  柳泽  陈崇  王新歌 《地球信息科学学报》2019,21(2):259-268

随着村镇经济建设发展,生活垃圾和工业固体废弃物造成的污染问题日益突出,已经成为制约新农村建设发展和生态文明建设的关键问题,而目前针对乡镇非正规固体废弃物的调查与统计主要依赖全国各乡镇相关部门逐级调查上报,工作量较大。本文基于高分辨率遥感影像,将深度学习模型和条件随机场模型相结合引入到乡镇固体废弃物的提取研究中,探索一种基于深度卷积神经网络的乡镇固体废弃物提取模型。由于固体废弃物在影像上表现为面积小,分布破碎等特点,为了提高工作效率,将模型特分为识别和提取2个部分：① 通过全连接卷积网络（CNN）对固体废弃物进行快速识别判断,筛选感兴趣区域影像块;② 在传统的全卷积神经网络(FCN)的基础上加入条件随机场模型(CRF)提取固体废弃物边界,提高整体分割精度。根据安徽、山西等地区相关部门上报固体废弃物堆放点以及住房与城乡建设部城乡规划管理中心进行野外检查的结果,实验最终识别精度达到86.87%以上;形状提取精度为89.84%,Kappa系数为0.7851,识别与提取精度均优于传统分类方法。同时,该方法已经逐步应用于住房和城乡建设部有关成都、兰州、河北等部分乡镇非正规固体废弃物的核查工作,取得了较为满意的结果。  相似文献   

基于SMAP卫星雷达资料的海冰密集度反演技术研究   总被引：1，自引：0，他引：1  

闻斌  周旋  种劲松  石立坚  叶小敏 《海洋学报》2018,40(6):29-39

SMAP是美国于2015年初发射的一颗卫星，搭载了L波段的雷达。它采用圆锥扫描方式，具有固定的入射角、较大的幅宽和千米级的分辨率，在海冰监测方面具有独特的优势。本文利用SMAP卫星雷达资料分别与德国Bremen大学海冰密集度产品和美国国家冰雪数据中心（NSIDC）海冰密集度产品建立3.125 km和25 km匹配数据集，分析了L波段雷达后向散射系数、极化比和归一化极化差与海冰密集度之间相关性，建立基于人工神经网络的海冰密集度反演算法。为了验证SMAP卫星雷达资料反演海冰密集度的精度，本文选择德国Bremen大学和美国冰雪数据中心发布的海冰密集度产品分别与SMAP海冰密集度产品进行对比分析，SMAP海冰密集度与Bremen海冰密集度的偏差为0.07、均方根误差为0.14；与NSIDC海冰密集度的偏差为0.04、均方根误差为0.18，这表明SMAP海冰密集度产品与现有业务化海冰密集度产品具有很好的一致性。  相似文献   

“海上丝绸之路”沿线重要港口竞争力评价   总被引：1，自引：0，他引：1  

杨忍  牟乃夏  彭澎  刘希亮  张恒才  陆锋 《地球信息科学学报》2018,20(5):623-631

“海上丝绸之路”是促进亚欧和亚非互联互通的重要通道,对其沿线重要港口的竞争力研究,可以为海上丝绸之路的建设提供参考。本文综合考虑港口的自然条件、腹地环境、基础设施、服务水平、政府廉洁度,及其在航运网络中的地位差别等因素,运用熵权-层次分析法对沿线51个国家的99个重要港口的竞争力进行评价。结果表明,① 港口综合竞争力空间分布呈明显的区域化特征,且与国家经济发展水平显著相关,地中海地区港口竞争力普遍较强,亚洲次之,非洲最弱。② 港口的网络地位对竞争力的影响最大,竞争力强的港口多位于重要水域的战略通道,网络地位高,辐射范围广。③ 我国投资的部分沿线港口综合竞争力与成熟港口之间还存在一定差距,但是具备较大的竞争力提升空间。  相似文献   

基于神经网络模型的湛江湾水体有色溶解有机物的遥感估算     

余果  付东洋  刘大召  刘贝  廖珊  王立安  张小龙 《海洋科学》2018,42(9):73-80

有色溶解有机物(Colored Dissolved Organic Matter, CDOM)是水体中重要的水质参数之一,是水色遥感的重要研究对象,如何构建适合特定区域的近海二类水体CDOM反演模型一直是国内外研究难点。本文利用2017年5月26～29日对南海西北部海域湛江湾20个站位采集的水样和测量的光谱资料,分析归一化遥感反射率与CDOM浓度a_g(400)的相关性,发现最大负相关系数出现在586nm处,选择580、585、590、595nm这四个波段处的归一化遥感反射率与a_g(400)建立了多元线性回归模型、BP(Back-Propagation)神经网络模型和RBF(Radial-Basis Function)神经网络模型,并与其他算法模型进行对比分析。结果发现, BP和RBF神经网络模型的平均相对误差和均方根误差均远小于多元线性回归模型和其他算法模型,神经网络模型的预测值与实测值拟合效果要优于多元线性回归模型。研究表明,神经网络模型更适合于湛江湾有色溶解有机物的遥感估算。  相似文献   

地震前兆数据采集适配软件方案设计     

汤一翔  滕云田  刘高川  张旸  王晨  王喆 《震灾防御技术》2018,13(1):215-225

为解决地震前兆非标准仪器的统一接入问题，本文对地震前兆台网设备异构性进行了分析，提出一套完整的地震前兆数据采集适配软件设计方案，并从采集、存储、传输3个主要软件模块描述了关键技术设计。  相似文献   

A hybrid integrated deep learning model for the prediction of citywide spatio-temporal flow volumes     

Yibin Ren  Huanfa Chen  Tao Cheng  Yang Zhang  Ge Chen 《International journal of geographical information science》2020,34(4):802-823

ABSTRACT

The spatio-temporal residual network (ST-ResNet) leverages the power of deep learning (DL) for predicting the volume of citywide spatio-temporal flows. However, this model, neglects the dynamic dependency of the input flows in the temporal dimension, which affects what spatio-temporal features may be captured in the result. This study introduces a long short-term memory (LSTM) neural network into the ST-ResNet to form a hybrid integrated-DL model to predict the volumes of citywide spatio-temporal flows (called HIDLST). The new model can dynamically learn the temporal dependency among flows via the feedback connection in the LSTM to improve accurate captures of spatio-temporal features in the flows. We test the HIDLST model by predicting the volumes of citywide taxi flows in Beijing, China. We tune the hyperparameters of the HIDLST model to optimize the prediction accuracy. A comparative study shows that the proposed model consistently outperforms ST-ResNet and several other typical DL-based models on prediction accuracy. Furthermore, we discuss the distribution of prediction errors and the contributions of the different spatio-temporal patterns.  相似文献   

Detecting regional dominant movement patterns in trajectory data with a convolutional neural network     

Can Yang  Győző Gidófalvi 《International journal of geographical information science》2020,34(5):996-1021

  相似文献   

MARC: a robust method for multiple-aspect trajectory classification via space,time, and semantic embeddings     

Lucas May Petry  Camila Leite Da Silva  Andrea Esuli  Chiara Renso  Vania Bogorny 《International journal of geographical information science》2020,34(7):1428-1450

ABSTRACT

The increasing popularity of Location-Based Social Networks (LBSNs) and the semantic enrichment of mobility data in several contexts in the last years has led to the generation of large volumes of trajectory data. In contrast to GPS-based trajectories, LBSN and context-aware trajectories are more complex data, having several semantic textual dimensions besides space and time, which may reveal interesting mobility patterns. For instance, people may visit different places or perform different activities depending on the weather conditions. These new semantically rich data, known as multiple-aspect trajectories, pose new challenges in trajectory classification, which is the problem that we address in this paper. Existing methods for trajectory classification cannot deal with the complexity of heterogeneous data dimensions or the sequential aspect that characterizes movement. In this paper we propose MARC, an approach based on attribute embedding and Recurrent Neural Networks (RNNs) for classifying multiple-aspect trajectories, that tackles all trajectory properties: space, time, semantics, and sequence. We highlight that MARC exhibits good performance especially when trajectories are described by several textual/categorical attributes. Experiments performed over four publicly available datasets considering the Trajectory-User Linking (TUL) problem show that MARC outperformed all competitors, with respect to accuracy, precision, recall, and F1-score.  相似文献   

地震油气储层的小样本卷积神经网络学习与预测   总被引：2，自引：0，他引：2       下载免费PDF全文

林年添  张栋  张凯  王守进  付超  张建彬  张冲 《地球物理学报》2018,61(10):4110-4125

地震储层预测是油气勘探的重要组成部分，但完成该项工作往往需要经历多个环节，而多工序或长周期的研究分析降低了勘探效率.基于油气藏分布规律及其在地震响应上所具有的特点，本文引入卷积神经网络深度学习方法，用于智能提取、分类并识别地震油气特征.卷积神经网络所具有的强适用性、强泛化能力，使之可以在小样本条件下，对未解释地震数据体进行全局优化提取特征并加以分类，即利用有限的已知含油气井段信息构建卷积核，以地震数据为驱动，借助卷积神经网络提取、识别蕴藏其中的地震油气特征.将本方案应用于模型数据及实际数据的验算，取得了预期效果.通过与实际钻井信息及基于多波地震数据机器学习所预测结果对比，本方案利用实际数据所演算结果与实际情况有较高的吻合度.表明本方案具有一定的可行性，为缩短相关环节的周期提供了一种新的途径.  相似文献