Bayesian Spatial Analysis of Hardwood Tree Counts in Forests via MCMC

TL;DR

This paper applies Bayesian spatial modeling with MCMC to analyze and predict hardwood tree counts in Ontario forests, comparing spatial and non-spatial models and exploring data sampling strategies for improved accuracy.

Contribution

It introduces a Bayesian geostatistical model for forest data and evaluates the impact of data reduction and sampling methods on prediction quality.

Findings

Spatial models outperform non-spatial models in prediction accuracy.

Reducing training data decreases prediction quality, but stratified sampling mitigates this effect.

Bayesian inference provides a flexible framework for spatial ecological data analysis.

Abstract

In this paper, we perform Bayesian Inference to analyze spatial tree count data from the Timiskaming and Abitibi River forests in Ontario, Canada. We consider a Bayesian Generalized Linear Geostatistical Model and implement a Markov Chain Monte Carlo algorithm to sample from its posterior distribution. How spatial predictions for new sites in the forests change as the amount of training data is reduced is studied and compared with a Logistic Regression model without a spatial effect. Finally, we discuss a stratified sampling approach for selecting subsets of data that allows for potential better predictions.