Precipitation Retrieval from Himawari-8 Satellite Infrared Data Based on Dictionary Learning Method and Regular Term Constraint

In this paper,the application of an algorithm for precipitation retrieval based on Himawari-8 (H8) satellite infrared data is studied.Based on GPM precipitation data and H8 Infrared spectrum channel brightness temperature data,corresponding "precipitation field dictionary" and "channel brightness temperature dictionary" are formed.The retrieval of precipitation field based on brightness temperature data is studied through the classification rule of k-nearest neighbor domain (KNN) and regularization constraint.Firstly,the corresponding "dictionary" is constructed according to the training sample database of the matched GPM precipitation data and H8 brightness temperature data.Secondly,according to the fact that precipitation characteristics in small organizations in different storm environments are often repeated,KNN is used to identify the spectral brightness temperature signal of "precipitation" and "non-precipitation" based on "the dictionary".Finally,the precipitation field retrieval is carried out in the precipitation signal "subspace" based on the regular term constraint method.In the process of retrieval,the contribution rate of brightness temperature retrieval of different channels was determined by Bayesian model averaging (BMA) model.The preliminary experimental results based on the "quantitative" evaluation indexes show that the precipitation of H8 retrieval has a good correlation with the GPM truth value,with a small error and similar structure.

Robust elastic impedance inversion using L1-norm misfit function and constraint regularization

The classical elastic impedance(EI) inversion method,however,is based on the L2-norm misfit function and considerably sensitive to outliers,assuming the noise of the seismic data to be the Guassian-distribution.So we have developed a more robust elastic impedance inversion based on the L1-norm misfit function,and the noise is assumed to be non-Gaussian.Meanwhile,some regularization methods including the sparse constraint regularization and elastic impedance point constraint regularization are incorporated to improve the ill-posed characteristics of the seismic inversion problem.Firstly,we create the Ll-norm misfit objective function of pre-stack inversion problem based on the Bayesian scheme within the sparse constraint regularization and elastic impedance point constraint regularization.And then,we obtain more robust elastic impedances of different angles which are less sensitive to outliers in seismic data by using the IRLS strategy.Finally,we extract the P-wave and S-wave velocity and density by using the more stable parameter extraction method.Tests on synthetic data show that the P-wave and S-wave velocity and density parameters are still estimated reasonable with moderate noise.A test on the real data set shows that compared to the results of the classical elastic impedance inversion method,the estimated results using the proposed method can get better lateral continuity and more distinct show of the gas,verifying the feasibility and stability of the method.

A Note on the Guignard Constraint Qualification and the Guignard Regularity Condition in Vector Optimization

Some remarks are made on the use of the Abadie constraint qualification, the Guignard constraint qualifications and the Guignard regularity condition in obtaining weak and strong Kuhn-Tucker type optimality conditions in differentiable vector optimization problems.

高斯感知约束空间异常的相关滤波目标跟踪

针对目标在复杂场景运动过程中容易出现跟踪丢失问题,提出一种高斯感知约束空间异常的目标跟踪算法。以高斯均匀分布为分布规律建立目标特征采样点,采用卷积结构提取目标的外观模型以及权重模型;为了约束空间异常,在目标函数中构建空间正则项,同时更新目标权重模型,减小空间过拟合的产生,增强跟踪器的空间异常适应性;应用加权最小二乘法思想,获得权重响应模型中心,确定目标中心,更新跟踪位置,增强跟踪器鲁棒性。使用OTB2015和UAV20L数据集,与其他主流相关滤波算法相比,该算法在目标运动导致低分辨率、遮挡等复杂条件下,跟踪成功率以及跟踪精度较高。

基于机器学习的通信网络入侵检测系统

文章提出一种基于机器学习的创新型方法,以提高通信网络入侵检测系统的检测效果。首先,深入研究了通信网络入侵检测的基本架构,以全面理解入侵行为的多样性和复杂性。其次,将正则化约束引入循环神经网络(Recurrent Neural Networks,RNN)模型,旨在提高检测准确性和模型的泛化能力。最后,利用UNSW-NB15数据集进行实验,证明所提方法的有效性。实验采用混淆矩阵进行结果分析,并通过精确度、召回率、F1分数等指标综合评估模型性能。结果表明,文章所提方法在通信网络入侵检测任务中表现出色,具有较高的准确性和泛化能力。

Simulation analysis of regional surface mass anomalies inversion based on different types of constraints

Surface mass anomalies estimated by mass concentration(mascon)approach using Gravity Recovery and Climate Experiment(GRACE)observations with regularization constraints generally present higher spatial resolution than the spheric harmonic(SH)solutions.To analyze the influence of different types of constraints on the estimation of mascon solutions,we carried out a closed-loop simulation experiment to estimate surface mass anomalies over South America based on simulated GRACE intersatellite geopotential differences.Tikhonov regularization with spatial constraint(SC),uniform weighting constraint(UWC),and a prior information constraint(APC)were employed to stabilize the mascon solutions,and the corresponding optimal regularization parameters were determined based on the minimum residual root-mean-square(RMS)criterion.The results show that mascon solutions estimated under different types of constraints are consistent and equivalent when the optimal regularization parameters are selected.The spatial distributions and main characteristics of regional surface mass anomalies estimated by the three types of constraints agree well,and the values of residual RMS with different constraints are very close.But due to the smoothing effect of regularization,the signal strength of mascon solutions is a bit weaker than that of original true signal,especially in the regions with strong signals.In addition,due to the ill-conditioned problem is more serious for higher grid resolution,the relative contribution of the three types of constraints to the final mascon solutions would be stronger.The results show that the averages of relative contribution percentages of these constraints for 2°×2° mascon grids are 80%-90%,while the corresponding values for 4°×4° mascon grids are 30%-60%.However,based on the minimum residual RMS criterion,the accuracy of estimation results is not affected by the type of constraints and their relative contribution to the final mascon solutions.

New normalized LMS adaptive filter with a variable regularization factor

A new normalized least mean square(NLMS) adaptive filter is first derived from a cost function, which incorporates the conventional one of the NLMS with a minimum-disturbance(MD)constraint. A variable regularization factor(RF) is then employed to control the contribution made by the MD constraint in the cost function. Analysis results show that the RF can be taken as a combination of the step size and regularization parameter in the conventional NLMS. This implies that these parameters can be jointly controlled by simply tuning the RF as the proposed algorithm does. It also demonstrates that the RF can accelerate the convergence rate of the proposed algorithm and its optimal value can be obtained by minimizing the squared noise-free posteriori error. A method for automatically determining the value of the RF is also presented, which is free of any prior knowledge of the noise. While simulation results verify the analytical ones, it is also illustrated that the performance of the proposed algorithm is superior to the state-of-art ones in both the steady-state misalignment and the convergence rate. A novel algorithm is proposed to solve some problems. Simulation results show the effectiveness of the proposed algorithm.

基于不等式和Gramian约束的MT和重力正则化联合反演

基于Gramian约束的正则化联合反演是目前地球物理联合反演领域的研究热点。鉴于正则化项和约束项权重系数选择的困难性,有必要在正则化联合反演中引入不等式约束。本文以基于Gramian约束的大地电磁测深法(MT)和重力正则化联合反演为例,对比了惩罚函数法和转换函数法在联合反演中的应用效果,并开展了江西相山某测线的实测资料处理。模型试验表明,惩罚函数法和转换函数法可以有效地将物性参数约束在一定范围之内,惩罚函数法具有更高的灵活性但需要人为设置惩罚函数的权重系数。实测数据的处理表明,基于不等式和Gramian约束的联合反演具有较高的实用性,提高了地球物理解释的精度。

基于正则约束的分层仿射图神经网络文本分类模型

文本分类是自然语言处理中一个重要的研究课题。近年来,图神经网络(graph neural network,GNN)在这一典型任务中取得了良好的效果。目前基于图结构的文本分类方法存在边噪声和节点噪声干扰、缺乏文本层次信息和位置信息等问题。为了解决这些问题,提出了一种基于正则约束的分层仿射图神经网络文本分类模型Text-HARC,该模型融合了图注意力网络(graph attention network,GAT)与门控图神经网络(gated graph neural network,GGNN),引入正则约束过滤节点与边噪声,分别使用仿射模块与相对位置编码补充词语表示。通过实验,该方法在TREC、SST1、SST2、R8四个基准数据集上的准确率提升明显,消融实验结果也验证了该方法的有效性。

基于正则化约束项的球坐标系大地电磁快速正演

随着跨大陆尺度的大地电磁(Magnetotellurics,简称MT)勘探的广泛开展,为了克服地球曲率带来的误差,有必要开展基于球坐标系下的3D MT正反演研究.该类正、反演问题的一个重要特点是所采用的频率往往比较低,在电磁场满足的偏微分方程中跟电导率有关的项几乎可以忽略.当采用数值方法进行该类电磁正演时,由于数值离散误差,正演算法无法模拟电性变化带来的电荷积累.因此在采用迭代求解器求解该类正演问题时,即使采用了传统的迭代电流散度校正技术,迭代求解器的收敛依然很慢.针对以上问题,本文显式地将散度校正项添加到原始控制方程中来对控制方程进行约束(为方便称之为正则化约束项),以保证每次迭代电流的散度为零.此方法避免了额外求解散度方程,以期显著提高球坐标系下3D MT正演效率.在正演中,采用球谐函数高阶项P10来近似MT的场源,在球坐标系下对加入了正则化约束项的正演方程进行有限差分离散.本文首先设计了一个一维层状结构模型,对本文所提算法的数值解与解析解进行了对比.然后设计了一个简单低阻模型和一个基于实测数据反演结果的Cascadia模型,测试了本文算法的数值表现.通过结果对比,验证了本文算法的正确性.数值表现测试结果显示相比于传统算法,本文算法在计算时间和迭代次数上都显著减少,而且不会随周期变化而发生显著变化.

Preconditioned Iterative Methods for Algebraic Systems from Multiplicative Half-Quadratic Regularization Image Restorations

Image restoration is often solved by minimizing an energy function consisting of a data-fidelity term and a regularization term. A regularized convex term can usually preserve the image edges well in the restored image. In this paper, we consider a class of convex and edge-preserving regularization functions, I.e., multiplicative half-quadratic regularizations, and we use the Newton method to solve the correspondingly reduced systems of nonlinear equations. At each Newton iterate, the preconditioned conjugate gradient method, incorporated with a constraint preconditioner, is employed to solve the structured Newton equation that has a symmetric positive definite coefficient matrix.The igenvalue bounds of the preconditioned matrix are deliberately derived, which can be used to estimate the convergence speed of the preconditioned conjugate gradient method. We use experimental results to demonstrate that this new approach is efficient,and the effect of image restoration is r0easonably well.

基于正则化理论的时频分析方法及应用

时频分析方法在地震勘探中有广泛的应用,因而获得具有良好时频分辨率的时频分析算法至关重要。传统的时频分析方法存在着一定的局限性,为克服这些局限性,提出了基于正则化理论的时频分析方法。该方法认为,短时窗信号是不同频率谐波的叠加,应从求解反问题的角度考察时频分析问题。在此视角下,时频分析问题具有不适定性,为得到有意义的时频谱,需要在正则化理论框架下进行时频分析。考察了正则化理论中常用的L_(1)范数约束、L_(2)范数约束以及最小支撑约束条件下的求解方法,并将3种约束函数的求解方法统一到同一个求解框架中。通过数值分析表明,最小支撑约束的时频分析方法具有较高的时频分辨率。将方法系统应用于一个特定研究区的实际资料,获得了具有较高时频分辨率的时频数据体,并利用单频数据体清晰刻画了储层的平面展布范围,展示了方法良好的应用前景。

自适应邻居和图正则的表示学习

在传统基于图表示的聚类算法中,表示矩阵计算和聚类通常分开进行,导致最后获取的表示矩阵可能不能代表最优的聚类结构.为解决此问题,本文提出一种新的聚类模型,它能在学习数据表示矩阵的同时获取合适的聚类结构.首先,基于局部距离度量,通过为每个数据点自适应地分配最优近邻学习数据表示矩阵.然后,通过在模型中施加约束项,降低噪声和离群点的影响,学习更优的表示矩阵.最后,对已学习到的数据表示矩阵的拉普拉斯矩阵施加秩约束,使得最终学习到的表示矩阵中的连通分量个数与簇个数相同,得到能够表征聚类结构的表示矩阵.实验将所提出的方法与11个算法在7个数据集上进行了比较,结果验证了该算法的有效性.

三维初至波旅行时层析速度反演算法优化

通过机器学习拾取初至波、建立微测井约束的初始速度场、多模板快速推进算法与窄带延拓算法求取全局旅行时、射线追踪技术求取射线传播路径、视慢度与正则化对目标反演方程进行约束等方法对三维初至波旅行时层析速度反演算法进行了优化。研究结果表明:(1)采用基于图像分割的机器学习算法,将地震记录分成初至前、初至后、包含初至窄带等3类,并赋予不同权重,对576 000道地震数据进行初至拾取,拾取精度超过99%,拾取效率较人工逐道拾取提升了80余倍。(2)采用多模板快速推进算法,6个差分模板可覆盖网格周围26个节点的旅行时计算,可提升网格对角方向的旅行时计算精度;三维窄带延拓技术可完成全局网格节点正演旅行时计算;基于Runge-Kutta算法的三维射线追踪技术可完成射线路径的求取。(3)使用微测井信息构建初始速度场,同时使用视慢度信息与正则化方法对层析反演方程进行约束,可有效提高地下1 000 m以内的速度反演精度。(4)采用优化后的层析反演技术对塔里木油田甫沙4线束与英买某区块的实际资料进行处理,消除了“牛眼”假象与边界伪影假象,且井点反演速度曲线与实际测井数据高度吻合。

信号自适应识别吸收补偿方法

地下介质的吸收衰减效应严重降低了地震信号的探测深度,限制了高分辨率地震勘探的发展。反Q滤波技术是补偿地层吸收衰减、提高地震分辨率的重要手段。然而,传统的反Q滤波方法本身并不具备信号识别能力,在补偿地震信号的同时会放大噪声干扰。为此,文中提出一种信号自适应识别的多道吸收补偿方法,其核心思想是利用地震信号的空间构造特征提升吸收补偿算法的稳定性和精度。该方法主要实施流程包括四步:首先,利用空间预测算子对反射信号的空间构造特征进行数学表达;再根据信号预测算子构造空间反射结构约束项;然后,将反射结构约束项加入多道吸收补偿目标函数,得到吸收补偿反演系统;最后,求解多道反演目标函数,得到吸收补偿结果。模型数据测试和实际资料应用结果表明:所提方法不仅能提高地震资料的分辨率,还可保护补偿结果的空间构造特征和信噪比,具有较强的稳定性和一定的实用性。

不同模型约束的SOTEM稳定性反演

短偏移距瞬变电磁法(简称SOTEM)理论上探测精度较高,但由于地下电性结构复杂多样,目前所采用的单一模型约束反演策略具有局限性.本文提出了一种不同模型约束的SOTEM稳定性反演方案,能够快速获得具有光滑型、聚焦型、突变型结构特点的反演结果.该方案引入了光滑泛函、总变分泛函、最小梯度支撑泛函进行不同正则化,将不同稳定泛函重新构造,在统一反演框架下获得不同模型约束反演问题的解,并对正演、迭代过程、雅可比矩阵计算、正则化参数设置等多个细节进行了优化,以提高SOTEM反演的稳定性和效率.通过不同地电模型的大量样本,考察了本文所提的多种优化方案对反演的稳定性和效率的提升效果,对比了采用不同模型约束进行正则化的反演效果,从而验证了所提SOTEM反演方案的稳定性与快速有效性.

基于光照不变正则约束的稳健性桥梁病害识别

桥梁表观病害识别是桥梁运营养护的关键技术之一。近年来,卷积神经网络(Convolutional Neural Networks,CNN)被广泛应用于桥梁表观病害识别。然而在光照不足条件下,卷积神经网络对于桥梁表观病害识别的稳健性通常不足。针对上述问题,提出一种基于光照不变正则约束的稳健性桥梁病害识别方法。该方法利用不变正则约束,同时约束CNN的特征提取模块和分类器模块,实现光照不足条件下的不变特征学习和分类器学习,进而增强CNN模型对于桥梁病害识别的光照稳健性。运用该方法基于桥梁表观病害数据集进行实验验证。实验结果表明:所提方法在光照不足条件下的桥梁病害的平均识别准确率高于对比方法;该方法在正常光照图像和光照变化图像上提取的特征矢量的欧氏距离为7.57,较对比方法提取的特征矢量具有更高的相似度。基于光照不变正则约束的稳健性桥梁病害识别方法在光照不足条件下提取的特征具有较强的不变特性,使得模型具有较强的病害识别稳健性,具有良好的工程应用价值,能够为桥梁的运营养护提供更准确的决策支持。

带约束的一维时频电磁联合反演研究

利用时频电磁资料可同时获取时间域及频率域电磁信息。相比单一时间域或频率域电磁信号,综合利用时频电磁信息可明显提高电性反演精度。为获得精细地电模型,基于正则化反演方法,融合数据约束、模型约束及步长约束,提出一种一维自适应时频电磁联合反演算法。该算法对时间域和频率域数据平衡因子及正则化因子采用自适应调整方案,同时将模型参数搜索范围约束与WOLFE准则相结合,在限制参数搜索范围的同时约束迭代步长,确保反演的稳定性和精度。使用经典层状模型、含噪声的页岩气地电模型及实测数据对该反演方法进行测试与分析,结果表明带约束的时频电磁联合反演方法可有效提高复杂模型电阻率反演的分辨率,对提高时频电磁方法油气藏识别精度具有实际意义。

基于约束图正则的块稀疏对称非负矩阵分解

现有的基于对称非负矩阵因式分解(Symmetric Nonnegative matrix Factorization, SymNMF)算法大都仅依赖初始数据构造亲和矩阵,并且一定程度上忽视了样本有限的成对约束信息,无法有效区分不同类别的相似样本以及学习样本的几何特征。针对以上问题,提出了基于约束图正则的块稀疏对称非负矩阵分解(Block Sparse Symmetric Nonnegative Matrix Factorization Based on Constrained Graph Regularization, CGBS-SymNMF)。首先,通过先验信息构造约束图矩阵,用于指导类别指示矩阵区分高相似度的不同类别样本;然后,引入PCP-SDP(Pairwise Constraint Propagation by Semi-definite Programming)方法,利用成对约束学习一个新的样本图映射矩阵;最后,利用“勿连”约束构造不相似矩阵,用于引导一个块稀疏正则项,以增强模型抗噪能力。实验结果表明,所提算法具有更高的聚类精确度和稳定性。

基于群稀疏正则化的高光谱图像去噪

高光谱图像(HSI)具有良好的光谱识别能力,但在采集过程中易受到混合噪声的污染,严重影响了后续任务的精度,因此HSI去噪是重要的预处理过程。针对现有去噪方法对空间-光谱先验信息利用不足、条纹噪声建模不合理的问题,提出一种新的基于群稀疏正则化的高光谱图像去噪算法。该算法将干净HSI的空间-光谱低秩特性和各波段上条纹噪声的低秩结构融入一个新框架,实现了干净HSI与高强度结构化条纹噪声的分离;同时为了有效保持图像的边缘信息,在去噪模型中引入新的群稀疏正则化,即基于L_(2,1)范数的增强型三维全变分正则化(enhanced 3D total variation, E3DTV),充分挖掘HSI差分图像的稀疏先验信息,进一步提升了图像的分段平滑性。采用交替方向乘子法对变量优化求解,在仿真和真实数据集上进行数值实验表明,所提模型具有更好的去噪和去条纹性能,在视觉效果和定量评价结果上都明显优于其他对比算法。