Bayesian Multispecies Ecological Models for Paleoclimate Reconstruction Using Inverse Prediction

• Activity Number: 83 - Your Invited Poster Evening Entertainment: No Longer Board
• Type: Invited
• Date/Time: Sunday, July 30, 2017 : 8:30 PM to 10:30 PM
• Sponsor: Section on Statistics and the Environment
• Author(s): John Tipton* and Mevin Hooten
• Companies: Colorado State University and Colorado State University
• Keywords: Inverse Prediction ; Multispecies Modeling ; Gaussian Process ; Paleoclimate

Abstract

Gaussian processes provide a flexible framework for modeling functional responses without assuming a parametric form. Many scientific disciplines use Gaussian process approximations to improve prediction and make inference on latent processes and parameters. When prediction is desired on unobserved covariates given realizations of the response variable, this is called inverse prediction. Because inverse prediction is often mathematically and computationally challenging, predicting unobserved covariates often requires fitting models that are different from the hypothesized generative model. We present a novel computational framework that allows for efficient estimation of a Gaussian process approximation to generative models. Our framework enables scientific learning about how the latent processes co-vary with respect to covariates while simultaneously providing predictions to the inverse problem. The proposed framework is capable of exploring the high dimensional, multi-modal latent spaces that arise in the inverse problem efficiently. To demonstrate flexibility, we apply our method to a generalized linear model to predict latent climate states given multivariate count data.