Mathematical Sciences: Multivariate Bayesian Classification Methods in Spatial Statistics

首席调查员将探索多变量贝叶斯分类方法在空间统计中的使用。他计划使用迭代贝叶斯和经验贝叶斯方法研究遥感数据的背景分类。他计划将现有的模型扩展到更广泛的背景下，并希望以各种方式改进现有的模型。将对模拟数据和实际数据进行研究。他将研究块金效应模型，各种空间相关性结构，以及使用自然共轭先验族的自适应起始值模型(同时使用迭代程序进行后验分类)。结果应适用于农业和地球物理背景下的卫星图像、图像重建和模式识别问题。

The principal investigator will explore the use of multivariate Bayesian classification methods in spatial statistics. He plans to study the contextual classification of remotely sensed data using iterative Bayesian and empirical Bayesian procedures. He plans to extend existing models to broader contexts,and hopes to improve current models in various ways. Both simulated and actual data will be studied. He will study nugget effect models, various spatial correlation structures, and adaptive starting value models using natural conjugate prior families (while using iterative procedures for posterior classification). Results should be applicable to satellite imagery in agricultural and geophysical contexts, to image reconstruction, and to problems in pattern recognition.