GPS高程拟合支持向量机模型   总被引：1，自引：0，他引：1  

吕亚军  王亚军  鹿先锋  鲁建伟 《全球定位系统》2009,34(3):11-13

为了快速获取GPS高程异常值，提出了基于最小二乘支持向量机（LS—SVM）的GPS高程异常值求取模型，介绍了最小二乘支持向量机的原理与优越性。利用该模型进行了高程异常的拟合，并对已知点进行了检验。结果表明：其结果是可靠的，在有限样本情况下完全可以达到传统GPS高程拟舍的效果，且其实现起来更简单，具有一定的科学性和实用性。  相似文献   

Estimating the parameters of forest inventory using machine learning and the reduction of remote sensing features     

Tanel Tamm  Kalle Remm 《International Journal of Applied Earth Observation and Geoinformation》2009

Locally computed statistics of image texture and a case-based reasoning (CBR) system were evaluated for mapping of forest attributes. Cluster analysis was preferred to regression models, as a pre-selection method of features. The best stand-based accuracy using satellite sensor images was 74.64 m⁻³ ha⁻¹ (36%) RMSE for stand volume, 1.98 m⁻³ ha⁻¹ a⁻¹ (49%) for annual increase in stand volume, where κ = 0.23 for stand growth classes and κ = 0.41 for dominant tree species in stands. The top pixel-based accuracy using orthophotos was 76.54 m⁻³ ha⁻¹ (41%) RMSE for stand volume, 1.87 m⁻³ ha⁻¹ a⁻¹ (44%) for annual increase in stand volume, where κ = 0.24 for stand growth classes and κ = 0.38 for dominant tree species in stands. Mean saturation in 30 m radius was the most useful feature when orthophotos were used, and standard deviation of Landsat ETM 6.2 values in 80 m radius was the best when satellite sensor images were used. The most valuable feature components (radii, channels and local statistics) for orthophotos were: 30 m kernel radius, lightness and the mean of pixel values; for satellite sensor images: 80 m kernel radius, near-infrared channel (ETM 4) and the mean of pixel values. Locally computed statistics.  相似文献   

Unsupervised ore/waste classification on open-cut mine faces using close-range hyperspectral data     

《地学前缘(英文版)》2023,14(4):101562

The remote mapping of minerals and discrimination of ore and waste on surfaces are important tasks for geological applications such as those in mining. Such tasks have become possible using ground-based, close-range hyperspectral sensors which can remotely measure the reflectance properties of the environment with high spatial and spectral resolution. However, autonomous mapping of mineral spectra measured on an open-cut mine face remains a challenging problem due to the subtleness of differences in spectral absorption features between mineral and rock classes as well as variability in the illumination of the scene. An additional layer of difficulty arises when there is no annotated data available to train a supervised learning algorithm. A pipeline for unsupervised mapping of spectra on a mine face is proposed which draws from several recent advances in the hyperspectral machine learning literature. The proposed pipeline brings together unsupervised and self-supervised algorithms in a unified system to map minerals on a mine face without the need for human-annotated training data. The pipeline is evaluated with a hyperspectral image dataset of an open-cut mine face comprising mineral ore martite and non-mineralised shale. The combined system is shown to produce a superior map to its constituent algorithms, and the consistency of its mapping capability is demonstrated using data acquired at two different times of day.  相似文献   

大数据与数学地球科学研究进展——大数据与数学地球科学专题代序   总被引：12，自引：9，他引：3  

周永章  陈铄  张旗  肖凡  王树功  刘艳鹏  焦守涛 《岩石学报》2018,34(2):255-263

大数据与数学地球科学的核心应用技术包括高维数据降维、图像数据处理、无限数据流挖掘、机器学习、关联规则算法与推荐系统算法等。人工智能地质学,包括大数据-智能矿床成因模型与找矿模型的构建,是具有重要价值的研究方向。高维数据降维旨在从初始高维特征集合中选出低维特征集合,有效地消除无关和冗余特征,增强学习结果的易理解性。哈希算法、聚类分析、主成分分析等是较常用的数学降维工具。机器学习是人工智能的核心,是使计算机具有智能的根本途径。机器学习与人工智能各种基础问题的统一性观点正在形成。深度学习的训练模型往往需要海量数据作为支撑,因此迁移学习方法日益受到重视。图像模式识别是大数据挖掘的重要技术。网络中的社区结构识别对理解整个网络的结构和功能有重要价值,可帮助分析、预测网络各元素间的交互关系。沉浸式虚拟现实技术是实现大数据可视化的重要方向,对具有多元、异构、时空性、非线性、多尺度地质矿产勘查数据的展示要求有特别的价值。引入VR技术进行矿产地质大数据的可视化,可实现大数据时代矿产勘查数据的新认知。无限数据流在地质、地球化学、地球物理监测中大量存在,甚至可以持续自动产生。对数据流数据的计算包括对点查询、范围查询、内积查询、分位数计算、频繁项计算等。关联规则和推荐系统算法是大数据挖掘中的重要算法,其应用范围越来越广泛。贝叶斯原理在大数据时代有独特的价值,贝叶斯网络是成因建模的一个革命性工具。智能地质学研究刚刚起步,构建大数据-智能矿床成因模型与找矿模型是智能地质学研究的重要内容。矿床模型研究方式的变革,将出现于互联网、云计算技术环境下全球各地的矿床研究团队的共同参与。  相似文献   

基于特征筛选与差分进化算法优化的滑坡危险性评估方法     

周侯伯  肖桂荣  林炫歆  尹玉环 《地球信息科学学报》2022,24(12):2373-2388

突发性地质灾害危险性评估对灾害防治与风险管理具有重要意义。由于不同地区影响灾害发生的因子各不相同,实际评估过程中难以全面客观地选取适宜的评估因子。机器学习对处理灾害系统的高维非线性问题独具优势,但因模型难以调优而评估效果有限。本文尝试提出一种双向优化的滑坡危险性评估方法：在构建因子敏感性指数开展定量敏感性分析的基础上,结合重要性分析、相关性分析、共线性分析构建四维(Four-Dimensional, 4D)特征筛选法用于评估因子综合优选;为克服模型难以调优的问题,引入差分进化(Differential Evolution, DE)算法优化支持向量机(Support Vector Machine, SVM)与多层感知机(Multi-Layer Perceptron, MLP) 2种推广能力较强的机器学习模型。最后,以福建省滑坡为例,开展评估方法研究。研究表明：4D特征筛选法能更加客观全面地选取适宜性更高的危险性评估因子,从而降低数据维度、减少信息冗余以提升评估模型性能;DE算法对SVM与MLP具有显著的优化效果,有益于增强模型滑坡危险性的评估准确度,DE-SVM、DE-MLP相较于未优化前模型的AUC值分别提升了4.43%与4.37%;基于双向优化的滑坡危险性评估结果表明,降雨与土地利用类型对福建省滑坡发生具有重要影响作用,福建省滑坡极高危险区普遍年均降雨较高、地形复杂多变,极低危险区主要位于东南沿海一带及闽江流域两侧。本研究为滑坡危险性评估中的影响因子客观选取与机器学习模型调优提供了一定思路。  相似文献   

Identifying tropical dry forests extent and succession via the use of machine learning techniques     

《International Journal of Applied Earth Observation and Geoinformation》2017

Information on ecosystem services as a function of the successional stage for secondary tropical dry forests (TDFs) is scarce and limited. Secondary TDFs succession is defined as regrowth following a complete forest clearance for cattle growth or agriculture activities. In the context of large conservation initiatives, the identification of the extent, structure and composition of secondary TDFs can serve as key elements to estimate the effectiveness of such activities. As such, in this study we evaluate the use of a Hyperspectral MAPper (HyMap) dataset and a waveform LIDAR dataset for characterization of different levels of intra-secondary forests stages at the Santa Rosa National Park (SRNP) Environmental Monitoring Super Site located in Costa Rica. Specifically, a multi-task learning based machine learning classifier (MLC-MTL) is employed on the first shortwave infrared (SWIR1) of HyMap in order to identify the variability of aboveground biomass of secondary TDFs along a successional gradient. Our paper recognizes that the process of ecological succession is not deterministic but a combination of transitional forests types along a stochastic path that depends on ecological, edaphic, land use, and micro-meteorological conditions, and our results provide a new way to obtain the spatial distribution of three main types of TDFs successional stages.  相似文献   

Combining machine learning and ontological data handling for multi-source classification of nature conservation areas     

《International Journal of Applied Earth Observation and Geoinformation》2017

Manual field surveys for nature conservation management are expensive and time-consuming and could be supplemented and streamlined by using Remote Sensing (RS). RS is critical to meet requirements of existing laws such as the EU Habitats Directive (HabDir) and more importantly to meet future challenges. The full potential of RS has yet to be harnessed as different nomenclatures and procedures hinder interoperability, comparison and provenance. Therefore, automated tools are needed to use RS data to produce comparable, empirical data outputs that lend themselves to data discovery and provenance. These issues are addressed by a novel, semi-automatic ontology-based classification method that uses machine learning algorithms and Web Ontology Language (OWL) ontologies that yields traceable, interoperable and observation-based classification outputs. The method was tested on European Union Nature Information System (EUNIS) grasslands in Rheinland-Palatinate, Germany. The developed methodology is a first step in developing observation-based ontologies in the field of nature conservation. The tests show promising results for the determination of the grassland indicators wetness and alkalinity with an overall accuracy of 85% for alkalinity and 76% for wetness.  相似文献   

Measuring visual enclosure for street walkability: Using machine learning algorithms and Google Street View imagery     

《Applied geography (Sevenoaks, England)》2016

One major limitation currently with studying street level urban design qualities for walkability is the often inconsistent and unreliable measures of streetscape features across different field surveyors even with costly training due to lack of more objective processes, which also make large scale study difficult. The recent advances in sensor technologies and digitization have produced a wealth of data to help research activities by facilitating improved measurements and conducting large scale analysis. This paper explores the potential of big data and big data analytics in the light of current approaches to measuring streetscape features. By applying machine learning algorithms on Google Street View imagery, we generated objectively three measures on visual enclosure. The results showed that sky areas were identified fairly well for the calculation of proportion of sky. The three visual enclosure measures were found to be correlated with pedestrian volume and Walk Score. This method allows large scale and consistent objective measures of visual enclosure that can be done reproducibly and universally applicable with readily available Google Street View imagery in many countries around the world to help test their association with walking behaviors.  相似文献   

Slope stability analysis: a support vector machine approach   总被引：5，自引：0，他引：5  

Pijush Samui 《Environmental Geology》2008,56(2):255-267

Artificial Neural Network (ANN) such as backpropagation learning algorithm has been successfully used in slope stability problem. However, generalization ability of conventional ANN has some limitations. For this reason, Support Vector Machine (SVM) which is firmly based on the theory of statistical learning has been used in slope stability problem. An interesting property of this approach is that it is an approximate implementation of a structural risk minimization (SRM) induction principle that aims at minimizing a bound on the generalization error of a model, rather than minimizing only the mean square error over the data set. In this study, SVM predicts the factor of safety that has been modeled as a regression problem and stability status that has been modeled as a classification problem. For factor of safety prediction, SVM model gives better result than previously published result of ANN model. In case of stability status, SVM gives an accuracy of 85.71%.  相似文献   

支持向量机在泥石流危险度评价中的应用研究   总被引：4，自引：0，他引：4  

原立峰  周启刚  马泽忠 《中国地质灾害与防治学报》2007,18(4):29-33,39

为改善传统泥石流危险度评价方法存在的缺陷,提出了基于支持向量机的泥石流危险度评价方法,并建立了支持向量机评价模型。研究选取泥石流一次(可能)最大冲出量(L1)、泥石流发生频率(L2)、流域面积(S1)、主沟长度(S2)、流域最大相对高差(S3)、流域切割密度(S6)和泥沙补给段长度比(S9)7个因子作为泥石流沟谷危险度评价因子,运用支持向量机理论,选用径向基(RBF)核函数,采取"试错法"进行参数优选;确定参数C=8,γ=2。以云南省37条泥石流沟的259个基础数据为样本进行学习训练和测试,建立了泥石流危险度评价的支持向量机模型。并将该模型应用于黄河积石峡水电站库区的泥石流危险性评价中进行验证。将模型评判结果和模糊数学方法的评价结果进行对比分析,结果的一致性达到73.33%。研究认为支持向量机方法能够成功地应用到泥石流危险度评价中,且具有较高的精度及很强的泛化能力,应用前景广阔。  相似文献