回归-Elman网络在矿坝变形预测中的应用

金矿开展矿坝的变形监测工作,引入多层递阶回归分析模型,有较高的预测精度,但方法较繁琐,计算较复杂。由于变形数据可分离成趋势项与随机项,趋势项可用多元线性回归良好地拟合;随机项的预测,文中采用Elman网络建模计算,最后利用矿坝的实测高程位移数据进行验证,并与多层递阶回归进行比较。结果表明:回归-Elman网络模型比多层递阶回归的预测精度更高,效果更好,且方法简洁实用性强。     

基于遥感影像的青海省环境变化监测

本文通过对遥感影像的分析,针对土地利用及植被变化情况,利用优化的K-means算法对青海省环境变化进行检测,以此对土地的利用进行合理的规划,以期实现可持续发展。同时将试验结果与外业实际结果及当地政策规划进行比对,结果显示文中算法对土地的变化和未来走势预测准确率超过75%,从而验证了监测方法的可行性。这不仅保证了在经济发展的同时能够合理地使用土地资源,而且能对环境进行有效的保护。     

地形因子与小微地震相关度的空间异质性分析

针对传统最小二乘回归未能顾及数据的空间特性,且无法度量模型自变量与因变量相关性的空间变异特性的问题,本文提出利用地理加权回归方法分析小微地震频次与地形因子相关度的空间异质性。以四川地区的地震监测资料、DEM为实验数据,选取地形复杂度、坡度变率、坡向变率和地面曲率为自变量,地震发生频次为因变量,构建地理加权回归模型,并进行回归系数的空间变异分析。实验分析发现,地震频次与地形因子具有一定的相关性:地形复杂度与地震频次相关性最强;坡度变率、沟壑密度、剖面曲率与地震频次的相关性依次减弱;不同空间位置的地形因子和地震频次的相关性具有较明显的空间异质性。实验结果表明,地理加权回归可以有效地度量分析地震频次与地形因子相关度的空间异质性,研究结果可为地震及次生灾害的分析与预报提供辅助决策参考。     

Detecting patterns of climate change in long-term forecasts of marine environmental parameters

ABSTRACT

Forecasting environmental parameters in the distant future requires complex modelling and large computational resources. Due to the sensitivity and complexity of forecast models, long-term parameter forecasts (e.g. up to 2100) are uncommon and only produced by a few organisations, in heterogeneous formats and based on different assumptions of greenhouse gases emissions. However, data mining techniques can be used to coerce the data to a uniform time and spatial representation, which facilitates their use in many applications. In this paper, streams of big data coming from AquaMaps and NASA collections of 126 long-term forecasts of nine types of environmental parameters are processed through a cloud computing platform in order to (i) standardise and harmonise the data representations, (ii) produce intermediate scenarios and new informative parameters, and (iii) align all sets on a common time and spatial resolution. Time series cross-correlation applied to these aligned datasets reveals patterns of climate change and similarities between parameter trends in 10 marine areas. Our results highlight that (i) the Mediterranean Sea may have a standalone ‘response’ to climate change with respect to other areas, (ii) the Poles are most representative of global forecasted change, and (iii) the trends are generally alarming for most oceans.     

Conjugate ruptures and seismotectonic implications of the 2019 Mindanao earthquake sequence inferred from Sentinel-1 InSAR data

In 2019, four strong earthquakes of Mw>6.4 occurred successively in Mindanao, Philippines. Based on the reports from the USGS and PHIVOLCS, these earthquakes were dominated by strike-slip ruptures. Whether these earthquakes are temporally and spatially related remained unknown. We characterized the coseismic displacement fields during the earthquake sequence using an InSAR technique with Sentinel-1 SAR data. The InSAR deformation measurements convincingly reveal that the four earthquakes produced distinct coseismic displacement patterns. We estimated the source parameters of the earthquakes with a two-step inversion strategy. The optimal model suggests that the earthquake sequence resulted from the reactivation of a conjugate fault structure that involves two nearly vertical left-lateral strike-slip faults and two high-angle right-lateral strike-slip faults. We calculated Coulomb stress changes from the earthquake sequence, suggesting that the previous strong earthquakes had significant stress-encouraging effects on the following events. The regional velocities based on the GPS analysis suggest that the formation of this conjugate structure is mainly due to the westward movement of the subducting Philippine Sea Plate. This earthquake sequence provides a seismotectonic background for subsequent strong earthquakes and helps to better understand the formation mechanisms and seismotectonic implications of conjugate structure rupturing.     

改进的灰色模型在高铁沉降预测中的应用

针对目前灰色模型在高速铁路沉降预测中存在的不足之处,该文提出了一种通过改善原始数据序列的光滑度来提高灰色模型预测精度的方法,并结合实例,验证了改进灰色模型在高速铁路沉降预测中的可行性,为今后高速铁路的沉降预测评估提供了更多的参考和借鉴。     

基于分类K—L变换的多波段遥感图像近无损压缩方法

去除空间和谱间相关性是多波段遥感图像压缩中的重要环节，为了得到更好的去相关效果，将矢量量化方法引入多波段遥感图像压缩中，以去除对应同一地物的波段矢量间的相关性，再通过分类K－L变换去除量化误差图像的变间相关性，对K－L变换后的特征图像采用预测树的方法进一步去除谱间结构相关性和空间相关性，实验结果表明，该方法可以取得很好的压缩效果。     

基于小波分解的动态变形预报

阐述了小波变换和多分辨率分析的基本原理,简要地介绍了离线预报和在线预报两种不同的变形预报方式,并在此基础上提出了基于小波分解的动态变形预报的方法,并通过实际算例证明了这种方法的有效性。     

跨越断层埋地管线地震反应研究述评

本文论述了跨越断层埋地管线地震反应研究工作概况,包括理论研究和实验研究的进展,并介绍了不同情况下采用的研究方法和建立的相应的研究模型,通过对数据结果进行整理分析,得出跨越断层埋地管线地震反应规律。同时,本文还对埋地管线研究中的一些重要参数对研究结果的影响作了详尽的阐述,提出了需进一步研究的问题和今后可能的研究发展方向。     

空间分类在连锁超市选址中的应用研究

空间数据挖掘是一种知识决策支持技术,本文以大型综合连锁超市为例,研究了空间分类挖掘方法在连锁超市选址预测中的应用问题。结合连锁超市定位理论,对实验数据进行了选择和处理。同时进行了基于关联的分类实验,得到指导和预测选址的知识,并对预测知识的准确性和可信度进行了检验,结果显示预测准确率和可信度较高。本文制定的挖掘方案可为连...