Why asymptotic limit of the acid dissolution capacity can lead to a sharp dissolution front in chemical dissolution of porous rocks?

The use of the asymptotic limit can greatly simplify the theoretical analysis of chemical dissolution front instabilities in fluid‐saturated rocks and therefore make it possible to obtain mathematical solutions, which often play a crucial role in understanding the propagation behavior of chemical dissolution fronts in chemical dissolution systems. However, there has been a debate in recent years that the asymptotic limit of the acid dissolution capacity (i.e., the acid dissolution capacity number approaching zero) alone cannot lead to a sharp dissolution front of the Stefan type in the acidization dissolution system, in which the dissolvable minerals of carbonate rocks are chemically dissolved by the injected acid flow. The acid dissolution capacity number is commonly defined as the ratio of the volume of the carbonate rock dissolved by an acid to that of the acid. In this paper, we use four different proof methods, including (i) direct use of the fundamental concepts; (ii) use of the mathematical governing equations of an acidization dissolution system; (iii) use of the different time scaling approach; and (iv) use of a moving coordinate system approach, to demonstrate that the asymptotic limit of the acid dissolution capacity can indeed lead to sharp dissolution fronts of the Stefan type in acidization dissolution systems on a much larger time scale (than the dissolution time scale). Our new finding is that on the reaction time scale, the condition of the conventional time derivative of porosity approaching zero alone can ensure that the acidization dissolution front has a sharp shape of the Stefan type. Copyright © 2017 John Wiley & Sons, Ltd.     

Simulation of site-scale water fluxes in desert and natural oasis ecosystems of the arid region in Northwest China

The study of water fluxes is important to better understand hydrological cycles in arid regions. Data-driven machine learning models have been recently applied to water flux simulation. Previous studies have built site-scale simulation models of water fluxes for individual sites separately, requiring a large amount of data from each site and significant computation time. For arid areas, there is no consensus as to the optimal model and variable selection method to simulate water fluxes. Using data from seven flux observation sites in the arid region of Northwest China, this study compared the performance of random forest (RF), support vector machine (SVM), back propagation neural network (BPNN), and multiple linear regression (MLR) models in simulating water fluxes. Additionally, the study investigated inter-annual and seasonal variation in water fluxes and the dominant drivers of this variation at different sites. A universal simulation model for water flux was built using the RF approach and key variables as determined by MLR, incorporating data from all sites. Model performance of the SVM algorithm (R² = 0.25–0.90) was slightly worse than that of the RF algorithm (R² = 0.41–0.91); the BPNN algorithm performed poorly in most cases (R² = 0.15–0.88). Similarly, the MLR results were limited and unreliable (R² = 0.00–0.66). Using the universal RF model, annual water fluxes were found to be much higher than the precipitation received at each site, and natural oases showed higher fluxes than desert ecosystems. Water fluxes were highest during the growing season (May–September) and lowest during the non-growing season (October–April). Furthermore, the dominant drivers of water flux variation were various among different sites, but the normalized difference vegetation index (NDVI), soil moisture and soil temperature were important at most sites. This study provides useful insights for simulating water fluxes in desert and oasis ecosystems, understanding patterns of variation and the underlying mechanisms. Besides, these results can make a contribution as the decision-making basis to the water management in desert and oasis ecosystems.     

Site characterization model using least‐square support vector machine and relevance vector machine based on corrected SPT data (Nc)

Statistical learning algorithms provide a viable framework for geotechnical engineering modeling. This paper describes two statistical learning algorithms applied for site characterization modeling based on standard penetration test (SPT) data. More than 2700 field SPT values (N) have been collected from 766 boreholes spread over an area of 220 sqkm area in Bangalore. To get N corrected value (N_c), N values have been corrected (N_c) for different parameters such as overburden stress, size of borehole, type of sampler, length of connecting rod, etc. In three‐dimensional site characterization model, the function N_c=N_c (X, Y, Z), where X, Y and Z are the coordinates of a point corresponding to N_c value, is to be approximated in which N_c value at any half‐space point in Bangalore can be determined. The first algorithm uses least‐square support vector machine (LSSVM), which is related to a ridge regression type of support vector machine. The second algorithm uses relevance vector machine (RVM), which combines the strengths of kernel‐based methods and Bayesian theory to establish the relationships between a set of input vectors and a desired output. The paper also presents the comparative study between the developed LSSVM and RVM model for site characterization. Copyright © 2009 John Wiley & Sons, Ltd.     

高分一号遥感影像地质灾害信息提取方法研究

山区地质灾害发生频繁,受灾范围大,危害严重。提取地质灾害信息、估算受灾情况,对救灾工作极为重要。传统的遥感人工解译方法速度慢、效率低;计算机自动解译速度快但解译精度受影像质量影响大,大范围地区很难建立起普适性的解译模型。本文利用洮南市西部高分一号遥感数据,结合DEM生成三维影像,建立解译标志,解译基础地质信息,分析地质灾害成因;根据研究区泥石流地质灾害的主要影像特征,提取影像的分类属性,基于面向对象的分类方法,建立信息提取模型,快速提取出地质灾害敏感区域;再进行人机交互,精确提取出地质灾害的类型和范围,通过野外验证,该方法十分可靠,为大范围地质灾害信息快速提取和灾后救援提供科学依据。     

迁移学习支持下的高分影像山地滑坡灾害解译模型

无人机低空遥感是近年来新兴的一种快速获取灾情信息的手段,如何利用无人机高分影像构建滑坡灾害解译模型是实现快速自动解译滑坡的关键。针对该问题,对比了多种影像特征提取方法,将迁移学习(TL)特征和支持向量机(SVM)引入到构建滑坡灾害自动解译模型中,提出了一种TL支持下的高分影像滑坡灾害解译模型。选取5·12汶川地震及4·20芦山地震系列无人机影像构建了滑坡灾害样本库并进行了实验,TL特征方法整体分类准确度ACC为95%,ROC达到0.98,识别准确率达到97%。结果表明,所提方法可用于高分影像滑坡自动解译,同时可用于大面积高分影像中快速山地滑坡灾害定位及检测。     

高光谱影像概率分类向量机分类方法研究

从分析基于支持向量机和相关向量机的高光谱影像分类方法的优势和不足出发,将基于概率分类向量机的方法用于高光谱影像分类试验。在贝叶斯理论框架下,概率分类向量机为基函数权值引入截断Gauss先验概率分布,使得不同类别的基函数权值具有不同符号的先验分布,并利用EM算法进行参数推断,得到足够稀疏的概率模型,弥补了相关向量机选取错误类别的样本作为相关向量的不足,从而有效地提高了模型的分类精度和稳定性。OMIS和PHI影像分类试验表明,概率分类向量机能够很好地应用在高光谱影像分类。     

利用多光谱卫星遥感和深度学习方法进行青藏高原积雪判识

青藏高原积雪对全球气候变化十分重要,针对已有积雪遥感判识方法中普遍采用的可见光与红外光谱数据易受复杂地形与高海拔影响,导致青藏高原地区积雪判识精度较低的问题,提出了一种基于多光谱遥感与地理信息数据特征级融合的积雪遥感判识方法:以风云三号卫星可见光与红外多光谱遥感资料与多要素地理信息作为数据源,由地面实测雪深数据与现有积雪产品交叉筛选出样本标签,构建并训练基于层叠去噪自编码器(SDAE)的特征融合与分类网络,从而有效辨识青藏高原遥感图像中的云、积雪以及无雪地表。经地面实测雪深数据验证,该方法分类精度显著高于使用相同数据源的FY-3A/MULSS积雪产品,略高于国际主流积雪产品MOD10A1与MYD10A1,并且年均云覆盖率最低。试验结果表明该方法可有效地减少云层对积雪判识的干扰,提升分类精度。     

历史数据和强化学习相结合的低频轨迹数据匹配算法

针对低频(采样间隔大于1min)轨迹数据匹配算法精度不高的问题,提出了一种基于强化学习和历史轨迹的匹配算法HMDP-Q,首先通过增量匹配算法提取历史路径作为历史参考经验库;根据历史参考经验库、最短路径和可达性筛选候选路径集;再将地图匹配过程建模成马尔科夫决策过程,利用轨迹点偏离道路距离和历史轨迹构建回报函数;然后借助强化学习算法求解马尔科夫决策过程的最大回报值,即轨迹与道路的最优匹配结果;最后应用某市浮动车轨迹数据进行试验。结果表明:本文算法能有效提高轨迹数据与道路匹配精度;本算法在1min低频采样间隔下轨迹匹配准确率达到了89.2%;采样频率为16min时,该算法匹配精度也能达到61.4%;与IVVM算法相比,HMDP-Q算法匹配精度和求解效率均优于IVVM算法,16min采样频率时本文算法轨迹匹配精度提高了26%。     

支持向量机的车载雷达点云目标识别

为了进一步研究移动测量系统的数据处理问题,该文根据点云的基本特征,归纳了由7个特征构成的点云原始特征向量,在此基础上,结合语义环境构建了由17个特征构成的点云扩展特征向量,并采用支持向量机模型对车载LiDAR点云进行行道树点云识别的一系列实验。实验中采用粒子群优化算法和遗传算法对支持向量机进行参数寻优;采用不同特征向量和不同数目样本对点云进行学习和目标识别;分析了特征向量的学习曲线和识别精度。实验结果表明,支持向量机模型能够在行道树点云识别中取得较高的精度。     

一种裸露土壤湿度反演方法

针对目前土壤湿度反演方法研究较少且缺少实时性的现状,该文提出一种土壤湿度反演方法——最小二乘支持向量机技术。以积分方程模型为正向算法,数值模拟不同雷达参数(频率、入射角及极化)下后向散射系数随土壤含水量和地表粗糙度的变化情况。经过数据敏感性分析,选取C-波段和X-波段、小入射角下的同极化后向散射系数作为支持向量回归的训练样本信息;经过适当的训练,利用支持向量回归技术对土壤含水量进行了反演研究;并考虑通过多频率、多极化、多入射角数据的组合,消除地表粗糙度的影响,提高反演精度。模拟结果表明,该方法反演土壤湿度具有较高的精度和较好的实时性;同时,与人工神经网络方法的结果比较,证明了该方法的有效性,为土壤湿度的反演研究提供了一种方法。