Constrained Functional Regression of National Forest Inventory Data Over Time Using Reconstructed Remote Sensing Observations

• Activity Number: 409 - Bayesian Space-Time Modeling
• Type: Contributed
• Date/Time: Tuesday, July 30, 2019 : 2:00 PM to 3:50 PM
• Sponsor: Section on Bayesian Statistical Science
• Author(s): Md Kamrul Hasan Khan* and Avishek Chakraborty and Giovanni Petris and Ty Wilson
• Companies: University of Arkansas and University of Arkansas and Univ of Arkansas and USDA Forest Service
• Keywords: Spatiotemporal model; Functional predictors; Landsat time series; Live tree basal area; Conditional autoregressive prior

Abstract

The USDA Forest Service uses satellite imagery, along with a sample of national forest inventory field plots, to monitor and predict changes in forest conditions over time throughout the United States. We specifically focus on a 230,400-hectare region in north-central Wisconsin between 2003 - 2012. The satellite imagery therein contains a significant proportion of missing values due to weather conditions and system failures. To fill in these missing values, we build spatiotemporal models based on fixed effect periodic patterns, spatial random effects with conditional autoregressive prior and a first-order autoregressive temporal effect. Post-reconstruction of the complete imagery, we use them as functional predictors in a two-component mixture model to capture variation in spatial distribution of yearly average live tree basal area, an attribute of interest measured on field plots. We further modify the regression equation to accommodate a biophysical constraint on how plot-level live tree basal area can change from one year to the next. Findings from our analysis, represented with a series of maps, match known spatial patterns across the landscape.