Application of Bayesian regularized BP neural network model for analysis of aquatic ecological data—A case study of chlorophyll-a prediction in Nanzui water area of Dongting Lake

Bayesian regularized BP neural network（BRBPNN） technique was applied in the chlorophyll-α prediction of Nanzui water area in Dongting Lake. Through BP network interpolation method, the input and output samples of the network were obtained. After the selection of input variables using stepwise/multiple linear regression method in SPSS i1.0 software, the BRBPNN model was established between chlorophyll-α and environmental parameters, biological parameters. The achieved optimal network structure was 3-11-1 with the correlation coefficients and the mean square errors for the training set and the test set as 0.999 and 0.000？8426, 0.981 and 0.0216 respectively. The sum of square weights between each input neuron and the hidden layer of optimal BRBPNN models of different structures indicated that the effect of individual input parameter on chlorophyll- α declined in the order of alga amount 〉 secchi disc depth（SD） 〉 electrical conductivity （EC）. Additionally, it also demonstrated that the contributions of these three factors were the maximal for the change of chlorophyll-α concentration, total phosphorus（TP） and total nitrogen（TN） were the minimal. All the results showed that BRBPNN model was capable of automated regularization parameter selection and thus it may ensure the excellent generation ability and robustness. Thus, this study laid the foundation for the application of BRBPNN model in the analysis of aquatic ecological data（chlorophyll-α prediction） and the explanation about the effective eutrophication treatment measures for Nanzui water area in Dongting Lake.

Composition Analysis and Identification of Ancient Glass Products Based on L1 Regularization Logistic Regression

In view of the composition analysis and identification of ancient glass products, L1 regularization, K-Means cluster analysis, elbow rule and other methods were comprehensively used to build logical regression, cluster analysis, hyper-parameter test and other models, and SPSS, Python and other tools were used to obtain the classification rules of glass products under different fluxes, sub classification under different chemical compositions, hyper-parameter K value test and rationality analysis. Research can provide theoretical support for the protection and restoration of ancient glass relics.

Calculation of Activity Coefficient from Immiscible Binary Alloy Phase Diagram by Means of Modified Sub-regular Solution Model

The modified sub regular solution model was used for a calculation of the activity coefficient of immiscible binary alloy systems. The parameters needed for the calculation are the interaction parameters, λ 1 and λ 2, which are represented as a linear function of temperature, T . The molar excess Gibbs free energy, G m E, can be written in the form G m E= x A x B[( λ 11 + λ 12 T )+( λ 21 + λ 22 T ) x B ] The calculation is carried out numerically for three immiscible binary alloy systems, Al Pb, Cu Tl and In V. The agreement between the calculated and experimentally determined values of activity coefficient is excellent.

Two-dimensional regularized inversion of AMT data based on rotation invariant of Central impedance tensor

Considering the uncertainty of the electrical axis for two-dimensional audo-magnetotelluric(AMT) data processing, an AMT inversion method with the Central impedance tensor was presented. First, we present a calculation expression of the Central impedance tensor in AMT, which can be considered as the arithmetic mean of TE-polarization mode and TM-polarization mode in the twodimensional geo-electrical model. Second, a least-squares iterative inversion algorithm is established, based on a smoothnessconstrained model, and an improved L-curve method is adopted to determine the best regularization parameters. We then test the above inversion method with synthetic data and field data. The test results show that this two-dimensional AMT inversion scheme for the responses of Central impedance is effective and can reconstruct reasonable two-dimensional subsurface resistivity structures. We conclude that the Central impedance tensor is a useful tool for two-dimensional inversion of AMT data.

Subspace Minimization Conjugate Gradient Method Based on Cubic Regularization Model for Unconstrained Optimization

Many methods have been put forward to solve unconstrained optimization problems,among which conjugate gradient method(CG)is very important.With the increasing emergence of large⁃scale problems,the subspace technology has become particularly important and widely used in the field of optimization.In this study,a new CG method was put forward,which combined subspace technology and a cubic regularization model.Besides,a special scaled norm in a cubic regularization model was analyzed.Under certain conditions,some significant characteristics of the search direction were given and the convergence of the algorithm was built.Numerical comparisons show that for the 145 test functions under the CUTEr library,the proposed method is better than two classical CG methods and two new subspaces conjugate gradient methods.

Occurrence Regularity and Prediction Model of Underground Pest Adults in Hangzhou District of China

To improve forecasting and sustained control level of underground pests, trapping quantity of underground pests （black cutworm,mole cricket and scar-ab） by lamps and their field dynamics in Hangzhou district from 2005 to 2011 were investigated in the paper. The results showed that different pests had obvious differences in population dynamic. The black cutworm （Agrotis ypsilon） had several damage peaks （late May, late June and late July） and the moth amount in early period was relatively high. The mole cricket （ Gryllotalpa africana） had two damage peaks （late May to early July, early September to mid and late October）. The scarab （Anomala corpulenta） had one damage peak （late May to late June）. There were periodic changes in total quantity of underground pests among years, and the peak period appeared in the year of 2005, 2007 to 2009 and 2011, respectively. On this basis, temperature, humidity, rainfall and light were used as forecas- ting factors, using the method of stepwise regression, 19 factors with significant correlation were screened out and prediction models for occurrence quantity and oc- currence period of the three pests were established. By using accuracy degree judge model for verification, the score values of prediction model for occurrence quan-tity and occurrence period of the three underground pests were more than 58 and 70, which indicated that the historical coincident rate and prediction accuracy of estabhshed prediction models were good.

Some Properties of a Recursive Procedure for High Dimensional Parameter Estimation in Linear Model with Regularization

Theoretical results related to properties of a regularized recursive algorithm for estimation of a high dimensional vector of parameters are presented and proved. The recursive character of the procedure is proposed to overcome the difficulties with high dimension of the observation vector in computation of a statistical regularized estimator. As to deal with high dimension of the vector of unknown parameters, the regularization is introduced by specifying a priori non-negative covariance structure for the vector of estimated parameters. Numerical example with Monte-Carlo simulation for a low-dimensional system as well as the state/parameter estimation in a very high dimensional oceanic model is presented to demonstrate the efficiency of the proposed approach.

A GAUSSIAN MIXTURE MODEL-BASED REGULARIZATION METHOD IN ADAPTIVE IMAGE RESTORATION

A GMM (Gaussian Mixture Model) based adaptive image restoration is proposed in this paper. The feature vectors of pixels are selected and extracted. Pixels are clustered into smooth,edge or detail texture region according to variance-sum criteria function of the feature vectors. Then pa-rameters of GMM are calculated by using the statistical information of these feature vectors. GMM predicts the regularization parameter for each pixel adaptively. Hopfield Neural Network (Hopfield-NN) is used to optimize the objective function of image restoration,and network weight value matrix is updated by the output of GMM. Since GMM is used,the regularization parameters share properties of different kind of regions. In addition,the regularization parameters are different from pixel to pixel. GMM-based regularization method is consistent with human visual system,and it has strong gener-alization capability. Comparing with non-adaptive and some adaptive image restoration algorithms,experimental results show that the proposed algorithm obtains more preferable restored images.

基于非凸与不可分离正则化算法的电容层析成像图像重建

搅拌器内两相混合是化工生产中常见的现象,电容层析成像(ECT)技术主要对两相分布进行可视化重构,以达到监测的目的。受稀疏贝叶斯学习的启发,提出了一种非凸与不可分离正则化(NNR)算法重建ECT图像。在稀疏先验的基础上引入矩阵低秩特性,采用最大后验估计在潜在空间中提出一个新的优化问题,利用对偶变量将潜在空间的目标函数映射到原始空间进行迭代求解,用来恢复同时稀疏与低秩的矩阵。与凸近似L1范数相比,NNR算法可获得更准确的重建图像,同时比非凸可分离方法更容易收敛到全局最优解。为验证NNR算法的重建效果,通过数值仿真与静态实验的方法分别与其他5种算法进行重建对比。结果表明:NNR算法可以有效减少重建伪影,提升中心物体的重建质量,为搅拌器内两相分布提供了高质量的重建算法。

石英脉型钨多金属矿床的扇状成矿实例及找矿模型

石英脉型钨矿床是中国数量最多的钨矿床类型,但保有储量消耗迅速,迫切需要创新找矿模型,指导找矿突破。文章结合二十余年的找矿实践,通过详细分析扇状成矿矿床实例,构建了石英脉型钨矿床新的找矿模型。该模型强调赋矿裂隙为岩浆动力成因,在花岗岩体顶部呈扇状分布型式,岩浆期后热液恰在裂隙张开时充填其中而形成扇状成矿系统;提出“就岩找矿”、“就矿找矿”、“就矿找岩”的地质、地球化学和地球物理标志,指导矿床尺度的勘查工程部署。截至目前,该模型已在广东禾尚田钨锡矿床、广西珊瑚钨锡矿床、广西社垌钨钼矿床、江西盘古山钨铋矿床等获得了验证,找矿成效显著。

基于扩散模型和爬坡趋势分类的风电功率自适应区间预测

扩散模型基于马尔可夫链的概率性质,能够定量描述风电的随机性和不确定性。然而,传统基于扩散模型的时序预测方法以当前输入前一段样本的均值作为基准进行特征缩放,导致预测区间在高峰时段过大、低谷时段过小。因此,提出一种基于扩散模型和爬坡趋势分类的风电功率自适应区间预测方法。首先,利用基于扩散模型的区间预测框架获取初始预测区间。然后,将风电波动过程划分为6种模式,对不同模式下的预测区间采取自适应规整策略,进而获得初始改进区间。接着,针对高出力模式中非爬坡时段的区间带宽不匹配问题,建立爬坡趋势分类评估模型,并结合所属出力模式进行区间修正,获得最终的区间预测结果。最后,实验结果表明所提方法的区间预测效果更优。

基于核机器的加速失效时间模型及其应用

加速失效时间模型是一种应用广泛的生存分析模型。本文借助LASSO惩罚剔除冗余预测变量,构建基于核机器的加速失效时间模型,用以刻画预测变量与生存期间的复杂关系。此外,提出一种新的正则化Garrotized核机器估计方法,可以较好地刻画预测变量与生存期潜在的非线性关系,实现非参数分量中预测变量间交互作用的自动建模,提升模型预测精度。模拟研究表明,与已有的代表性方法相比,本文提出的方法对生存期的预测精度更高,特别是在复杂关系情形下优势更为显著。最后,将该方法应用于胃癌数据分析,利用临床信息和基因表达预测生存期和风险评分。实证结果显示,该方法能为病例基于风险分层的临床精准诊疗方案设计提供有益的参考。

基于因果正则化极限学习机的风电功率短期预测方法

随着风电并网比例的逐年提高,电力系统对风电功率预测的准确性和稳定性提出了更高要求。对于同一风电场而言,为了避免不同特征选择方法所选择的风电场特征子集不同,从因果关系的角度出发,提出了一种基于因果正则化极限学习机(causal regularized extreme learning machine, CRELM)的风电功率短期预测方法。首先将极限学习机(extreme learning machine, ELM)建模为结构因果模型(structural causal model, SCM),在此基础上计算隐藏层神经元与输出层神经元之间的平均因果效应向量。然后将该平均因果效应向量与输出层权重相结合构成因果正则化项,在最小化训练误差的同时最大化网络的因果关系,以进一步提升模型的预测准确性和预测稳定性。最后,以国内蒙西某风电场数据为例,与采用特征选择或不采用特征选择的预测模型相对比,验证了所提方法的有效性和适用性。

云南开远市吉德金矿地质特征及成矿模式

吉德金矿矿体主要呈似层状、透镜状产于峨眉山玄武岩与下伏灰岩岩溶不整合面、玄武质火山碎屑岩夹层及次级构造破碎带中,有红土型和岩溶角砾岩型两种类型,金以微粒自然金为主,目前矿床规模较小、地质研究程度较低。通过总结成矿规律、构建成矿模式,对矿区及外围寻找红土型和岩溶角砾岩型金矿具有指导作用。

青海省不同生境下青海云杉胸径生长模型研究

[目的]研究不同生境压力下青海云杉的林木胸径生长规律及生长模型,为有效保护、合理经营青海云杉林提供经验模型。[方法]利用青海地区青海云杉的树轮数据,计算单木胸径生长量,分析不同起源、不同坡位条件下胸径生长规律,构建单木胸径生长模型,对比与评价不同模型的拟合优度结果。随后选取基础模型,建立考虑起源和坡位的青海云杉单木胸径混合效应模型,采用全部数据对模型进行检验。[结果]总体来看,青海云杉生长到胸高位置后,单木胸径生长量随着年龄的增加呈现下降后平缓变化趋势;青海云杉天然林、人工林单木生长的速生期分别为29—44 a、29—39 a,连年生长量(CAI)和平均生长量(MAI)均在0.40 cm以上,随后天然林单木CAI和MAI的变化平缓,人工林的变化幅度较大。不同坡位的单木胸径生长趋势具有差异。生长模型结果显示,不同起源、坡位条件下各树种最优胸径生长模型的决定系数(R^(2))均在0.913以上,总体相对误差(TRE)和平均系统误差(MSE)均在±2%以内,平均预估误差(MPE)大多在5%以内,平均百分标准误差(MPSE)在35%以内。以Gompertz模型为基础模型构建的混合效应模型的R^(2)为0.702,拟合效果优于基础模型;检验指标TRE为0.03%,MSE为-0.30%,MPE为4.23%,MPSE为29.54%,较基础模型分别下降89.3%、83.5%、20.6%、15.1%。[结论]不同生境条件下青海云杉的胸径生长规律具有差异,天然林的快速生长期持续时间长;所构建的单木胸径生长混合效应模型,可以用于估算青海省不同生境条件下青海云杉的林木胸径生长量变化。

一种基于重力正演理论的海底地形反演迭代算法

重力数据反演海底地形的方法是获取全球海底地形数据的重要途径。针对传统地形反演算法需要间接引入经验参数的问题,本研究以不采用经验公式为原则,从空间域方法入手,结合重力正演公式,建立重力异常与地形之间的解析观测方程,采用最小二乘方法进行求解。为了得到观测方程最优解,建立牛顿迭代关系,引入正则化参数,增强方程组的收敛性。顾及边缘效应对正演的影响,采用双线性插值算法对原始重力异常数据进行加密处理和无约束网格扩充以削弱误差。在太平洋海域(155°E~156°E,16°N~17°N)构建了1′×1′分辨率的海底地形模型,并通过船测水深数据验证。相比于传统空间域算法——重力地质法,本研究方法的均方根误差降低了12.7%,验证了其可行性与准确性。

不同羽系拜城油鸡生长发育规律及生长曲线拟合分析

【目的】研究不同羽系拜城油鸡生长发育规律,为拜城油鸡的科学饲养管理和品种改良提供理论依据。【方法】分别选择0日龄健康的黑麻羽系、黄麻羽系和银灰羽系拜城油鸡雏鸡各200只(公母各半),测定并记录0~22周龄的体重,采用Logistic、Gompertz和Von Bertalanffy生长模型对拜城油鸡公、母鸡的体重进行生长曲线拟合分析。【结果】10、14周龄黑麻羽系公鸡的体重显著高于银灰羽系公鸡的体重(P<0.05),12周龄黑麻羽系公鸡的体重显著高于黄麻羽系和银灰羽系公鸡的体重(P<0.05),16周龄黑麻羽系和黄麻羽系公鸡的体重极显著高于银灰羽系公鸡的体重(P<0.01),20、22周龄黑麻羽系和黄麻羽系公鸡的体重显著高于银灰羽系公鸡的体重(P<0.05);母鸡中,黄麻羽系母鸡的初生重分别显著或极显著高于黑麻羽系和银灰羽系母鸡(P<0.05或P<0.01),6、8周龄黑麻羽系母鸡的体重显著高于银灰羽系母鸡的体重(P<0.05),20、22周龄龄黄麻羽系母鸡的体重显著高于银灰羽系母鸡的体重(P<0.05);3个羽系拜城油鸡的生长曲线均呈现“S”型;3个羽系公鸡均在第10周达到生长高峰,母鸡在第12周达到生长高峰;3种生长模型的拟合曲线与实际曲线基本吻合,Von Bertalanffy模型对公、母鸡的拟合效果最佳(R 2>0.998),黑麻羽系、黄麻羽系和银灰羽系公鸡的拐点周龄分别为8.629、9.389、8.947,拐点体重分别为858.207、911.107、842.681 g;母鸡的拐点周龄分别为7.946、8.619、7.936,拐点体重分别为635.543、679.577、609.097 g。【结论】不同羽系拜城油鸡的生长发育存在差异,3个羽系拜城油鸡公、母鸡的最优生长模型均为Von Bertalanffy模型。

考虑截面规则性的柱状节理岩体变形及强度特性研究

柱状节理岩体的复杂结构使其现场力学参数的确定存在困难,可靠地估计柱状节理岩体强度及变形特性对工程安全至关重要。结合Voronoi图形及3D打印技术制作不规则柱状节理岩体光敏树脂模具,并制备了具有不同倾角的规则及不规则柱状节理岩体试样。基于开展的单轴压缩试验结果,分析不同截面柱状节理岩体的变形及强度特性差异。根据试样最终破坏形态,揭示柱状节理岩体破坏模式及机制。结合已有研究结果,描述节理面材料对柱状节理岩体破坏形态及强度的影响。基于传统节理系数方法,提出了更能反映柱状节理岩体柱体结构特征的修正节理系数方法。采用修正节理系数法建立规则及不规则柱状节理岩体试验结果与现场变形及强度参数间的经验关系,将所提出计算公式应用于白鹤滩水电站工程,预测结果与现场实测值及RMR法(RMR为岩石质量评分指标)、Q法(Q为岩体质量指标)的预测值进行比较。结果表明,对于现场变形和强度参数,所提出的修正节理系数法的预测结果与现场实测结果较为吻合。

起伏地形下基于非结构网格模型降维的重力三维密度反演

复杂起伏地形以及剖分方式对重力反演解释具有重要影响.目前重力密度反演研究主要基于直立长方体模型,这显著降低了对起伏地形和复杂地质体的拟合程度,对重力反演解释易产生较大影响.四面体非结构网格能够更加精细地模拟起伏地形及复杂地质体,为此本文研究了起伏地形条件下基于四面体非结构网格剖分的重力三维密度反演.首先基于Delaunay方法将地下区域剖分为四面体非结构网格,引入垂向导数和相关系数两种方法进行模型降维技术从而减小解的空间,通过添加最小长度约束,深度加权约束,物性范围约束构建目标函数,并采用预条件共轭梯度法求解.为了提高反演效率在计算过程引入OpenMP并行算法.并研究了各项约束以及两种模型降维方法在四面体非结构网格正则化反演中的效果.通过不同深度直立长方体模型以及起伏地形下组合模型试验,基于四面体非结构网格的重力密度反演可以清晰地反映异常体位置.将本文提出的方法应用于美国密苏里州东南部的氧化铁矿床,反演结果与已知岩体具有较好的一致性,进一步证明该方法的正确性和有效性.