基于卷积神经网络的极光图像分类

极光是由带电粒子经磁层—电离层碰撞大气而产生的。面对形态各异、演变过程复杂的极光图像,对其合理分类为进一步探究日地电磁活动和能量耦合等空间物理问题奠定了基础。针对该问题,引入深度学习的方法,通过卷积神经网络模型自主表征极光特征并实现极光图像分类。该方法对2003年北极黄河站越冬观测的38 044幅和8 001幅典型极光图像分类正确率达93.17%和91.5%;自动识别2004—2009年观测数据的极光形态,4类极光时间分布规律与三波段激发谱能量分布基本一致。实验结果表明,基于卷积神经网络的极光表征方法,能有效实现极光图像的自动分类。     

黄河三角洲农作物种植分区的遥感研究

本文选取了一年中三个不同时相的TM影像,分别求出了三幅影像的NDVI分布图,将其合成为一幅影像图。由于不同区域种植的作物在三个时相中的NDVI变化是不同的,因此在NDVI合成图上会呈现不同的颜色区域。通过对不同颜色区域进行采样分析,可以确定桃红色区域为冬小麦、玉米(大豆)轮作区,蓝紫色区域为棉花、春玉米、杂粮种植区,亮蓝区域为水稻种植区,亮绿色区域为林地、草地。最后,根据不同颜色区域的NDVI变化特征用非监督分类和监督分类相结合的方法对影像进行了分类提取。这样便可对黄河三角洲农作物的种植情况进行宏观的了解,为农作物种植合理布局及农业可持续发展提供依据。     

Satellite image analysis using crowdsourcing data for collaborative mapping: current and opportunities

ABSTRACT

Researchers are continually finding new applications of satellite images because of the growing number of high-resolution images with wide spatial coverage. However, the cost of these images is sometimes high, and their temporal resolution is relatively coarse. Crowdsourcing is an increasingly common source of data that takes advantage of local stakeholder knowledge and that provides a higher frequency of data. The complementarity of these two data sources suggests there is great potential for mutually beneficial integration. Unfortunately, there are still important gaps in crowdsourced satellite image analysis by means of crowdsourcing in areas such as land cover classification and emergency management. In this paper, we summarize recent efforts, and discuss the challenges and prospects of satellite image analysis for geospatial applications using crowdsourcing. Crowdsourcing can be used to improve satellite image analysis and satellite images can be used to organize crowdsourced efforts for collaborative mapping.     

基于卷积神经网络的地震波形智能识别研究

随着世界上多个国家和地区的地震预警系统投入运行,误报和漏报等问题逐渐突显,特别是将标定以及强干扰波形误识别为大震事件,快速、精确地区分地震与其他波形是一个难题。针对于此,该研究提出了基于卷积神经网络地震波形智能识别方法。首先收集并处理了2012—2017年中国境内福建以及周边邻省共683个地震和478个爆破事件,并对这些样本筛选、截取和基线校正等预处理,共得到了27 500条三通道波形。在此基础上,构建了3 s波形输入的卷积神经网络模型(SW-CNN)。结果表明：模型对地震、噪声、爆破和异常波形的识别率分别为97.9、99、99.2和99.3%。相比于人工手动分类识别,该模型更省时和更稳定,为地震预警目前所面临的问题提供了一个新的解决方法。     

基于影像多种特征的决策树分类方法

阐述了决策树分类CART算法原理,将纹理信息、NDVI指数引入决策树方法对影像进行分类,并将分类结果与最大似然分类结果进行比较,研究表明决策树分类方法相对传统分类方法总体精度提高了8.9148%,Kappa系数提高了0.1074。     

A New Feature Vector Using Selected Line Spectra for Pulsar Signal Bispectrum Characteristic Analysis and Recognition

Average pulse profiles of pulsar signals are analyzed using the bispectrum tech-nique. The result shows that there are nonlinear phase couplings between the two frequency axes of the bispectrum charts, which indicate nonlinear factors in the generation and prop-agation of pulsar signals. Bispectra can be used as feature vectors of pulsar signals because of their being translation invariant. A one-dimension selected line spectrum algorithm for ex-tracting pulsar signal characteristic is proposed. Compared with selected bispectra, the pro-posed selected line spectra have the maximum interclass separability measurements from the point of view of the whole one-dimension feature vector. Recognition experiments on several pulsar signals received at several frequency bands are carried out. The result shows that the selected line spectrum algorithm is suitable for extracting pulsar signal characteristics and has a good classification performance.     

A New Retracking Technique for Brown Peaky Altimetric Waveforms

A new Brown-Peaky (BP) retracker has been developed for peaky waveforms that usually appear within ～10 km to the coastline. The main feature of the BP is that it fits peaky waveforms using the Brown model without introducing a peak function. The retracking strategy first detects the peak location and width of a waveform using an adaptive peak detection method, and then estimates retracking parameters using a weighted least squares (WLS) estimator. The WLS assigns a downsized weight to corrupted waveform gates, but an equal weight to other normal waveform gates. The BP retracker has been applied to 4-year Jason-1 waveform (2002–2006) in two Australian coastal zones. The results retracked by BP, MLE4 and ALES retrackers have been validated against tide-gauge observations located at Burnie, Lorne and Broome. The comparison results show that three retrackers have similar performance over open oceans with the correlation coefficient (～0.7) and RMSE (～13 cm) between altimetric and tide-gauge sea levels for distance >7 km offshore. The main improvement of BP retracker occurs for distance ≤7 km to the coastline, where validation results indicate that data retracked by BP are more accurate (15–21 cm) than those by ALES (16–24 cm) and MLE4 (19–37 cm).     

土地定级估价的分析研究与实践——以新疆拜城县为例

近几年来,经济发展迅速,土地级别划分及地价水平已有较大的变化,原有的基准地价体系已不能适应现时经济发展的要求,地价体系也亟需修正更新。该文结合拜城县的具体情况,并遵循所选因子与土地的相关性,确定拜城县城区土地定级因素,在分析各定级因素权重的基础上,计算各因素的分值,划分土地等级。通过对拜城县城区的土地进行定级估价作出修正和更新,将对土地的监督管理工作起到良好的促进作用。     

湖泊和水库营养灰色聚类分析

选取浮游植物初级产量、浮游植物现存量、有机物耗氧量、总氮、无机氮、总磷、活性磷等七项指标,由德尔菲法确定各指标的类别界限值和权重,用灰色系统理论的定权灰色聚类方法,借用计算机对23个湖泊和水库营养类型主要参数作灰色聚类分析,以建立一种划分我国湖泊和水库营养类型的有效方法,作为渔业生产的依据。     

基于改进BP神经网络的海底底质分类

通过采用遗传算法优化神经网络初始权值的方法,将GA算法与BP神经网络有机结合,应用于海底底质分类。基于多波束测深系统获取的反向散射强度数据,应用改进的BP神经网络分类方法,实现对海底基岩、砾石、砂、细砂和泥等底质类型的快速、准确识别。通过实验比较,GA-BP神经网络分类精度明显高于BP神经网络,证明了该方法的有效性和可靠性。