LiDAR based prediction of forest biomass using hierarchical models with spatially varying coefficients

Remote Sensing of Environment
By: , and 

Links

Abstract

Many studies and production inventory systems have shown the utility of coupling covariates derived from Light Detection and Ranging (LiDAR) data with forest variables measured on georeferenced inventory plots through regression models. The objective of this study was to propose and assess the use of a Bayesian hierarchical modeling framework that accommodates both residual spatial dependence and non-stationarity of model covariates through the introduction of spatial random effects. We explored this objective using four forest inventory datasets that are part of the North American Carbon Program, each comprising point-referenced measures of above-ground forest biomass and discrete LiDAR. For each dataset, we considered at least five regression model specifications of varying complexity. Models were assessed based on goodness of fit criteria and predictive performance using a 10-fold cross-validation procedure. Results showed that the addition of spatial random effects to the regression model intercept improved fit and predictive performance in the presence of substantial residual spatial dependence. Additionally, in some cases, allowing either some or all regression slope parameters to vary spatially, via the addition of spatial random effects, further improved model fit and predictive performance. In other instances, models showed improved fit but decreased predictive performance—indicating over-fitting and underscoring the need for cross-validation to assess predictive ability. The proposed Bayesian modeling framework provided access to pixel-level posterior predictive distributions that were useful for uncertainty mapping, diagnosing spatial extrapolation issues, revealing missing model covariates, and discovering locally significant parameters.

Study Area

Additional publication details

Publication type Article
Publication Subtype Journal Article
Title LiDAR based prediction of forest biomass using hierarchical models with spatially varying coefficients
Series title Remote Sensing of Environment
DOI 10.1016/j.rse.2015.07.028
Volume 169
Year Published 2015
Language English
Publisher American Elsevier Pub. Co.
Publisher location New York, NY
Contributing office(s) Southwest Biological Science Center
Description 15 p.
First page 113
Last page 127
Country United States
State Colorado, Minnesota
Other Geospatial Fraser Experimental Forest, Marcell Experimental Forest, Niwot Long Term Ecological Research Site
Online Only (Y/N) N
Additional Online Files (Y/N) N