EcoSta 2017: Start Registration
View Submission - EcoSta2017
A0547
Title: Approaches for massive spatial data and applications in remote sensing Authors:  Emily Kang - University of Cincinnati (United States) [presenting]
Abstract: With the development of new remote sensing technology, large or even massive spatial datasets from Earth observation become available. Statistical analysis of such data is challenging. We proposes a semiparametric approach to modeling and inference for massive spatial datasets. In particular, a Gaussian process with additive components is considered, with its covariance structure coming from two components: one part is flexible without assuming a specific parametric covariance function but is able to achieve dimension reduction; the second part is parametric and simultaneously induces sparsity. The inference algorithm for parameter estimation and spatial prediction is devised. The method is applied to simulated data and a massive dataset of sea surface temperature acquired from NASA's Terra satellite. The results demonstrate the computational and inferential benefits of the proposed method over competing methods and show that our method is more flexible and more robust against model misspecification. Other applications and extensions will also be discussed.