A completely design-based data-driven inference for mapping forest resources

What is it about?

A completely data-driven, design-based sampling strategy is proposed for mapping a forest attribute within the spatial units tessellating a survey region. Based on sample data, a model is selected, and model parameters are estimated using least-squares criteria for predicting the attribute of interest within units as a linear function of a set of auxiliary variables. The spatial interpolation of residuals arising from model predictions is performed by inverse distance weighting. The leave-one-out cross validation procedure is adopted for selecting the smoothing parameter used for interpolation. The densities of the attributes of interest within units are estimated by summing predictions and interpolated residuals. Finally, density estimates are rescaled tomatch the total estimate over the survey region obtained by the traditional regression estimator with the total estimate obtained from the map as the sum of the density estimates within units.

Featured Image

Why is it important?

This study has developed and tested a new design-based, completely data-driven mapping with remotely sensed data exploited as auxiliary variables: from the initial choice of the assisting model, through model selection, exploitation of selected auxiliary variables for predictions, choice of distance function for IDWinterpolation of residuals, harmonization with traditional estimates of totals and bootstrap resampling from the estimated map, the proposed strategy leads to the final map of interest attribute and to the estimation of its precision.