Imputing tree-lists from aerial attributes for complex stands of south-eastern British Columbia

Abstract

The nearest neighbor, k-nearest neighbors, distance-weighted k-nearest neighbor, and class-weighted k-nearest neighbor imputation methods were compared for accuracy in estimating tree-lists (list of species and diameter for each tree) from aerial attributes for complex stands, with up to nine species and a wide range of sizes, in south-eastern British Columbia, Canada. For the four imputation methods, the most similar neighbor distance metric was used, and three neighbors were used for the k-nearest neighbor methods. Ground variables used to represent the tree-list included the number of trees per hectare by species, ranges of diameter by species, and basal area per hectare. Aerial variables included species composition, crown closure (%), elevation, biogeoclimatic ecosystem classification (BEC) zones, height, age, and site class. Sample data were divided, and the imputation methods were compared for accuracy using observed and estimated species composition, stand tables, basal area, and volume per hectare. Also, the imputed tree-list was used to predict yield using a stand level growth model, and this predicted yield was compared to the yield obtained using the actual tree-list. Of the four approaches used, the nearest neighbor was marginally better, but the methods that averaged the three nearest neighbors were somewhat better for the distribution of stems per hectare by diameter for the more sparse hardwood species. Of the three averaging methods, weighting by similarity of the species composition and the BEC zone provided better results. In using the estimated trees lists in a growth and yield model, the average volumes were reasonable at the beginning and end of the period for all methods. However, the volumes for a particular stand could be quite different than that obtained for an observed tree-list.