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   

突发地震灾害中无人驾驶救援车伺服控制系统研究          下载免费PDF全文

岳光  潘玉田 《地震工程学报》2018,40(6):1366-1371

针对当前采用PID控制器控制无人驾驶救援车伺服系统时存在的轨迹跟踪精度不高，误差控制性能较差，灵活性、平稳性和安全性能不佳等问题，提出并设计基于BP神经网络整定PID控制器的无人驾驶救援车伺服控制系统，建立突发地震灾害中无人驾驶救援车伺服控制系统驱动模型，并以此模型作为被控对象；根据系统期望输出值与实际输出值构成的控制偏差获得PID控制规律，并通过调节PID控制器控制参数实现系统控制，在此基础上，采用BP神经网络通过对无人驾驶救援车伺服控制系统性能的学习，构建基于BP神经网络整定的PID控制器，并采用梯度下降法修正控制器加权系数，通过在线调整BP神经网络加权系数即可实现控制器的自适应调整，控制突发地震灾害中无人驾驶救援车实施救援。实验结果表明，设计的基于BP神经网络整定PID控制器的无人驾驶救援车伺服系统可有效提高轨迹跟踪精度，具有较好的灵活性，且能够保证驾驶员的安全和车辆平稳行驶。  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   

Coordinative similitude law considering fluid‐structure interaction for underwater shaking table tests     

Zhong‐Xian Li  Kun Wu  Yundong Shi  Ning Li  Yang Ding 《地震工程与结构动力学》2018,47(11):2315-2332

Generally, when a model is made of the same material as the prototype in shaking table tests, the equivalent material density of the scaled model is greater than that of the prototype because mass is added to the model to satisfy similitude criteria. When the water environment is modeled in underwater shaking table tests, however, it is difficult to change the density of water. The differences in the density similitude ratios of specimen materials and water can affect the similitude ratios of the hydrodynamic and wave forces with those of other forces. To solve this problem, a coordinative similitude law is proposed for underwater shaking table tests by adjusting the width of the upstream face of the model or the wave height in the model test to match the similitude ratios of hydrodynamic and wave forces with those of other forces. The designs of the similitude relations were investigated for earthquake excitation, wave excitation, and combined earthquake and wave excitation conditions. Series of numerical simulations and underwater shaking table tests were performed to validate the proposed coordinative similitude law through a comparison of coordinative model and conventional model designed based on the coordinative similitude law and traditional artificial mass simulation, respectively. The results show that the relative error was less than 10% for the coordinative model, whereas it reached 80% for the conventional model. The coordinative similitude law can better reproduce the dynamic responses of the prototype, and thus, this similitude law can be used in underwater shaking table tests.  相似文献   

车辆荷载作用下山西路基重塑黄土的动力特性研究   总被引：2，自引：0，他引：2       下载免费PDF全文

马林  张军  刘亚明 《地震工程学报》2018,40(1):101-104

针对车辆荷载对山西高速公路路基土体影响研究不足的现状,从试验角度出发,研究车辆荷载水平、波形、干密度和围压对路基土体的动力特性响应。研究表明:路基土体的体变随波形比的增大而增大,随车辆荷载的增大而增大;路基土体的动弹性模量随干密度的增大而增大,随围压的增大而增大,阻尼比随围压的增大而减小。  相似文献   

Extracting drainage networks and their connectivity using LiDAR data          下载免费PDF全文

Jennifer Roelens  Ine Rosier  Stefaan Dondeyne  Jos Van Orshoven  Jan Diels 《水文研究》2018,32(8):1026-1037

Policies, measures, and models geared towards flood prevention and managing surface waters benefit from high quality data on the presence and characteristics of drainage ditches. As a cost and labour effective alternative for acquiring such data through field surveys, we propose a method (a) to extract vector data representing ditch drainage networks based on local morphologic features derived from high resolution digital elevation models (DEM) and (b) to identify possible connections in the ditch network by calculating a probability of the connectivity using a logistic regression where the predictor variables are characteristics of the ditch centre lines or derived from the DEM. Using Light Detection and Ranging (LiDAR) derived DEMs with a 1 m resolution, the method was developed and tested for a mixed agricultural residential area in north‐eastern Belgium. The derived ditch segments had an error of omission of 8% and an error of commission of 5%. The original positional accuracy of the centre lines of the extracted ditches was 0.6 m and could be improved to 0.4 m by shifting each vertex to the position of the lowest LiDAR point located within a radius equal to the spatial resolution of the used DEM. About 69% of the false disconnections in the network were identified and corrected leading to a reduction of the unconnected parts of the ditch network by 71%. The extracted and connected network approximated the reference ditch network fairly well.  相似文献   

The information system of the French Peatland Observation Service: Service National d'Observation Tourbières – A valuable tool to assess the impact of global changes on the hydrology and biogeochemistry of temperate peatlands through long term monitoring     

Sébastien Gogo  Jean-Baptiste Paroissien  Fatima Laggoun-Défarge  Jean-Marc Antoine  Léonard Bernard-Jannin  Guillaume Bertrand  Philippe Binet  Stéphane Binet  Guillaume Bouger  Yohann Brossard  Thierry Camboulive  Jean-Pierre Caudal  Stéphane Chevrier  Geneviève Chiapiuso  Benoît D'Angelo  Pilar Durantez  Chris Flechard  André-Jean Francez  Didier Galop  Laure Gandois  Daniel Gilbert  Christophe Guimbaud  Louis Hinault  Adrien Jacotot  Franck Le Moing  Emilie Lerigoleur  Gaël Le Roux  Fabien Leroy  Alexandre Lhosmot  Qian Li  Elodie Machado Da Silva  Jean-Sébastien Moquet  Juanita Mora-Gomez  Laurent Perdereau  Thomas Rosset  Marie-Laure Toussaint 《水文研究》2021,35(6):e14244

Mitigating and adapting to global changes requires a better understanding of the response of the Biosphere to these environmental variations. Human disturbances and their effects act in the long term (decades to centuries) and consequently, a similar time frame is needed to fully understand the hydrological and biogeochemical functioning of a natural system. To this end, the ‘Centre National de la Recherche Scientifique’ (CNRS) promotes and certifies long-term monitoring tools called national observation services or ‘Service National d'Observation’ (SNO) in a large range of hydrological and biogeochemical systems (e.g., cryosphere, catchments, aquifers). The SNO investigating peatlands, the SNO ‘Tourbières’, was certified in 2011 ( https://www.sno-tourbieres.cnrs.fr/ ). Peatlands are mostly found in the high latitudes of the northern hemisphere and French peatlands are located in the southern part of this area. Thus, they are located in environmental conditions that will occur in northern peatlands in coming decades or centuries and can be considered as sentinels. The SNO Tourbières is composed of four peatlands: La Guette (lowland central France), Landemarais (lowland oceanic western France), Frasne (upland continental eastern France) and Bernadouze (upland southern France). Thirty target variables are monitored to study the hydrological and biogeochemical functioning of the sites. They are grouped into four datasets: hydrology, fluvial export of organic matter, greenhouse gas fluxes and meteorology/soil physics. The data from all sites follow a common processing chain from the sensors to the public repository. The raw data are stored on an FTP server. After operator or automatic processing, data are stored in a database, from which a web application extracts the data to make them available ( https://data-snot.cnrs.fr/data-access/ ). Each year at least, an archive of each dataset is stored in Zenodo, with a digital object identifier (DOI) attribution ( https://zenodo.org/communities/sno_tourbieres_data/ ).  相似文献