学术活动

复杂时空数据分析系列报告

作者:   来源:  时间:2018-05-27

复杂时空数据分析系列报告

时间:5月27号(周日)9:00-17:30

地点:金龙潭饭店第二会议室

(1)

报告题目 :ENSO对中国地形降水的影响(也谈资料分辨率等问题)

报告人:   黄刚  中国科学院大气物理研究所

摘要:我们可以很好的利用ENSO来预测西北太平洋副热带高压强度和位置的变化。但是为什么对西北太平洋副热带高压的预报的成功不能转化为对中国夏季降水的预报成功呢?大气所胡开明副研究员、黄刚研究员和美国海洋研究所谢尚平教授对这个问题进行反思。他们发现冬天厄尔尼诺事件后夏季西北太平洋副热带高压增强和西伸带来的西南气流能显著增强了热带海洋向中国内陆的水汽输送,并且这种水汽输送会爬越巫山山脉、巴山山脉、秦岭并达到黄土高原南坡。这些山脉都是东西走向最高海拔高度超过2000m,因此他们推测水汽爬坡必定会导致山区降水增加。由于地形导致的降水具有很强局地特征,需要高分辨率山区观测站点资料对该推测进行验证。最近国家气象局发布的高分辨率台站资料为验证这种推测提供了机会。利用高分辨率数据,他们发现前冬厄尔尼诺事件会导致夏季中国中部山区降水的确显著增强,这和他们的推测一致(图1)。利用这种关系他们构建了一个预测公式,能预测大约60%四川、湖北西部、陕西等地区的夏季降水年际变化。巫山、巴山、秦岭以及黄土高原地区人口众多、物种和生态多样,是1亿多人民和众多珍贵动植物的栖息地。由于山地地形,夏季洪涝可能会造成很多灾害如泥石流。该研究为提前几个月预测该地区旱涝气候预测提供物理基础。同时该研究还表明,气候预测和预估研究不能忽略地形的作用。

 (2)

报告题目 :Multilevel Functional Data Analysis for Temporal Point Processes with Applications in Stock Market Trading

报告人: 黄辉 中山大学数学学院

摘要: We propose a novel multilevel functional data analysis procedure for temporal point processes. The proposed procedure can be used to model repeatedly observed temporal point patterns, which have become increasingly available due to technological advancement. A nonparametric approach is developed to consistently estimate the covariance kernels of the latent component processes at all levels. To predict the functional principal component scores, we propose a consistent estimation procedure by maximizing the conditional likelihoods of super-positions of point processes. We further extend our procedure to the bivariate point process case where potential correlations between the processes can be assessed. Asymptotic properties of the proposed estimators are investigated, and the effectiveness of our procedures is illustrated by a simulation study and an application to a stock trading dataset.

 (3)

报告题目 :NLS-4DVar的新发展

报告人:  田向军  中科院大气物理研究所

摘要:在这个报告里面,我将向大家介绍我们持续10年所发展的一种融合两大主流数据同化方法(EnKF和4DVar)优势的集合四维变分同化方法NLS-4DVar:

(1)基于NLS-4DVar框架实现了En4DVar、4DEnVar及LETKF的统一的公式表达,从而提出了贯穿En4DVar与4DEnVar的NLSi-4DVar系列同化方法

(2)一种快速高效的局地化方案

(3)多重网格的NLS-4DVar同化框架

(4)基于NLS-4DVar方法的系统构建与应用

 (4)

报告题目 :基于POD的气象数据分析与气象场重构

报告人徐勤武   南京大学数学系

摘要: 在本报告中我们主要介绍风速、温度等气象要素数值预报结果的校正和气象场的重构。包括以下两个方面:

(1) 准确的风速预测对于风电场发电功率的预测、风电场管理和调度具有至关重要的作用。数值预报结果往往存在较大的偏差,我们基于POD对预报风场进行特征提取,考虑数值预报偏差与风场特征的关系,建立基于特征的局部回归模型,实验表明预报误差显著减小。

(2)利用Gappy-POD方法针对温度场和雾霾浓度场研究气象场的重构和缺失数据处理。基于数值模拟数据利用POD建立特征基函数组,将基函数组投影到可用观测数据点,依据物理意义增加适当约束条件,将场的重构/缺失数据恢复问题转化为优化问题,通过求解优化问题得到最优恢复结果。利用实际数据进行测试,结果显示恢复结果可以很好的逼近实测数据。

 (5)

报告题目 :Spatio-Temporal Autoregressions

报告人:马莹莹  北京航空航天大学经济管理学院

摘要: We propose a new class of spatio-temporal models with unknown and banded autoregressive coefficient matrices. The setting represents a sparse structure for high-dimensional spatial panel dynamic models when panel members represent economic (or other type) individuals at many different locations. The structure is practically meaningful when the order of panel members is arranged appropriately. Note that the implied autocovariance matrices are unlikely to be banded, and therefore, the proposal is radically different from the existing literature on the inference for high-dimensional banded covariance matrices. Due to the innate endogeneity, we apply the least squares method based on a Yule-Walker equation to estimate autoregressive coefficient matrices. The estimators based on multiple Yule-Walker equations are also studied.  A ratio-based method for determining the bandwidth of autoregressive matrices is also proposed. Some asymptotic properties of the inference methods are established. The proposed methodology is further illustrated using both simulated and real data sets.

 (6)

报告题目 :Disease Mapping with Generative Models

报告人 王菲菲   中国人民大学统计学院

摘要:Disease mapping focuses on learning about areal units presenting high relative risk. Disease mapping models assume that the disease counts are distributed as Poisson random variables with the respective means typically specified as the product of the relative risk and the expected count. These models usually incorporate spatial random effects to accomplish spatial smoothing of the relative risks. Fitting of these models often computes expected disease counts via internal standardization. This places the data on both sides of the model, i.e., the counts are on the left side but they are also used to obtain the expected counts on the right side.  As a result, these internally standardized models are incoherent and not generative; probabilistically, they could not produce the data we observe. Here, we argue for adopting the direct generative model for disease counts, modeling disease incidence rates instead of relative risks, using a generalized logistic regression. Then, the relative risks are then extracted post model fitting. We first demonstrate the benefit of the generative model without incorporating spatial smoothing using simulation. Then, spatial smoothing is introduced using the customary conditionally autoregressive model. We also extend the generative model to dynamic settings. The generative models are compared with internally standardized models, again through simulated datasets but also through a well-examined lung cancer morbidity dataset in Ohio. Both models are spatial and both smooth the data similarly with regard to relative risks. However, the generative coherent models tend to provide tighter credible intervals.  Since the generative specification is coherent, is at least as good inferentially, and is no more difficult to fit, we suggest that it should be the model of choice for spatial disease mapping.

 (7)

报告题目 :Regional Air Quality Assessment that Adjusts for Meterological Confounding

报告人: 张澍一   北京大学光华管理学院

摘要:Although air pollution is caused by emission of pollutants to the atmosphere, the observed pollution levels are largely affected by meteorological conditions which determine the dispersion condition of the pollutants. Effective air quality management requires statistical measures that are immune to the meteorological confounding in order to evaluate spatial and temporal changes of the pollution concentration objectively. Motivated by a challenging task of assessing changes and trends in the underlying pollution concentration in a region near Beijing, we propose a spatial and temporal adjustment approach for the PM2.5 and other five pollutants with respect to the meteorological conditions by constructing a spatial and temporal baseline weather condition based on historic data to remove the meteorological confounding. The adjusted mean pollution concentration is shown to be able to capture changes in the underlying emission while being able to control the meteorological variation. Estimation of the adjusted average is proposed together with asymptotic and numerical analyzes. We apply the approach to conduct assessments on six pollutants in the Beijing region from Year 2013 to Year 2016, which reveal some intriguing patterns and trends that are useful for the air quality management.

(8)

报告题目 :统计过程控制方法的构建和探讨

报告人:    邹长亮  南开大学统计与数据科学学院

摘要:本报告将以若干领域热点为例,从控制统计量的构造、控制线的求解以及在线算法的设计等方面,简要介绍关于统计过程控制方法构建的一些要素。