Geostatistical software for merging multivariate data with various spatial supports

用于将多元数据与各种空间支持合并的地统计软件

• 批准号: 10006357
• 负责人: PIERRE E GOOVAERTS
• 金额: $ 22.49万
• 依托单位: BIOMEDWARE
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-05-15 至 2021-04-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10006357
• 关键词: Air; Air Pollution; Area; Categories; Censuses; Cities; Communities; Computer software; Data; Data Analyses; Data Set; Development; Dimensions; Environment; Environmental Epidemiology; Epidemiologist; Evaluation; Geography; Geology; Health; Health Sciences; Health Status; Imagery; Individual; Investigation; Lead; Lead levels; Linear Models; Literature; Location; Malignant Neoplasms; Measurement; Measures; Meteorology; Methods; Modeling; Monitor; Outcome; Performance; Phase; Protocols documentation; Radon; Records; Research; Sampling; Science; Services; Small Business Innovation Research Grant; Soil; Source; Space Models; Techniques; Technology; Test Result; Testing; Time; Uncertainty; United States National Institutes of Health; Validation; Variant; Visualization; Water; base; cost; density; design; improved; innovation; land use; prototype; reconstruction; remote sensing; simulation; theories; tool; usability; user-friendly

7. Project Summary/Abstract A key component in any investigation of association and/or cause-effect relationships between the environment and health outcomes is the availability of accurate models of exposure. Because the cost of collecting field data is often prohibitive, it is critical to incorporate any source of secondary information available to supplement sparse datasets. Secondary data can take many forms (e.g., continuous or categorical measurement scale), display various sampling densities (e.g., data available everywhere or at specific locations), and be recorded over different spatial supports (e.g., point observations, census tracts, rasters). Surprisingly, there is currently no commercial software for the geostatistical treatment of multivariate space- time data, including the merging of data layers measured on different spatial supports. This SBIR project is developing the first commercial software to offer tools for geostatistical multivariate ST interpolation and modeling of uncertainty. The research product will be a stand-alone module into the desktop space-time visualization core developed by BioMedware, an Esri partner. These tools will be suited for the analysis of data outside health sciences, such as in remote sensing, geochemistry or soil science, broadening significantly the commercial market for the end product. This project will accomplish three aims:  Review the main spatial coregionalization models available in the geostatistical literature (i.e., traditional vs extended, intrinsic) and compare their performances (i.e., prediction accuracy) and user-friendliness (i.e., ease of inference) for multivariate spatial interpolation through the cross-validation analysis of 4 datasets dealing with mapping of water lead levels, radon, meteorological and geochemical data. The comparison will include various cokriging types (i.e., one or several unbiasedness constraints) and other tools used by environmental epidemiologists, such as nearest monitors, inverse distance or purely spatial kriging.  Develop and test a prototype module that will guide non-expert users through the fitting of a linear model of coregionalization (LMC) and selection of an appropriate multivariate interpolation method (e.g., cokriging, kriging with an external drift, regression kriging), followed by the spatial interpolation based on BioMedware’s space-time visualization and analysis technology.  Conduct a usability study and identify additional methods and tools to consider in Phase II. These technologic, scientific and commercial innovations will enhance our ability to model geostatistically multivariate space-time phenomena and compute estimates and the associated uncertainty at the scale (e.g. point location, census-tract level) the most relevant for environmental epidemiology.

7.项目总结/摘要 在任何调查的关联和/或因果关系之间的一个关键组成部分， 环境和健康成果的关键是提供准确的接触模型。因为 收集现场数据通常是禁止的，关键是要纳入任何可用的辅助信息源 来补充稀疏数据集。辅助数据可以采取多种形式（例如，连续或分类 测量标度），显示各种采样密度（例如，数据可在任何地方或特定 位置），并且可以在不同的空间支持物上记录（例如，点观测、人口普查区域、栅格）。 令人惊讶的是，目前还没有用于多变量空间的地质统计处理的商业软件- 时间数据，包括合并在不同空间支持上测量的数据层。 该SBIR项目正在开发第一个商业软件，为地统计多变量ST提供工具 插值和不确定性建模。该研究产品将是一个独立的模块到桌面 由Esri合作伙伴BioMedware开发的时空可视化核心。这些工具将适用于 分析卫生科学以外的数据，如遥感、地球化学或土壤科学， 最终产品的商业市场。该项目将实现三个目标： 审查地统计文献中现有的主要空间协同区域化模型（即，传统vs 扩展的、内在的）并比较它们的性能（即，预测精度）和用户友好性（即， 通过4个数据集的交叉验证分析进行多变量空间插值 处理水铅含量、氡、气象和地球化学数据的绘图。比较 将包括各种协同克里格类型（即，一个或多个无偏约束）和其他工具 环境流行病学家，如最近的监测，反距离或纯粹的空间克里金法。 * 开发和测试一个原型模块，指导非专家用户拟合线性模型， 共区域化（LMC）和选择适当的多元插值方法（例如，协克里格法， 带外部漂移的克里金法、回归克里金法），然后是基于 BioMedware的时空可视化和分析技术。 进行可用性研究，并确定在第二阶段考虑的其他方法和工具。 这些技术、科学和商业上的创新将增强我们建立地质统计模型的能力 多变量时空现象和计算估计和相关的不确定性在尺度（例如， 点的位置，普查区的水平）最相关的环境流行病学。