Comparison of Data Grouping Strategies on Prediction Accuracy of Tree-Stem Taper for Six Common Species in the Southeastern US

Abstract

Clustering data into similar characteristic groups is a commonly-used strategy in model development. However, the impact of data grouping strategies on modeling stem taper has not been well quantified. The objective of this study was to compare the prediction accuracy of different data grouping strategies. Specifically, a population-level model was compared to the models fitted with grouped data based on taxonomic rank, tree form and size. A total of 3678 trees were used in the analyses, which included six common species in upland hardwood forests of the southeastern U.S. Results showed that overall predictions are more accurate when building stem taper models at the species, species group or division level rather than at the population level. The prediction accuracy was not considerably improved between species-specific functions and models fitted with species-related groups for the four hardwood species examined. Grouping data by taxonomic rank provided more reliable predictions than height-to-diameter ratio (H–D ratio) or diameter at breast height (DBH). The form/size-related grouping methods (i.e., data grouped by H–D ratio or DBH) generally did not improve the prediction precision compared to a population-level model. In this study, the effect of sample size in model fitting showed a minimal impact on prediction accuracy. The methodology presented in this study provides a modeling strategy for mixed-species data, which will be of practical importance when data grouping is needed for developing stem taper models.

Stochastic stem bucking using mixture density neural networks

“…First, many traditional taper equations were created for forest inventory purposes and do not condition their predictions on multiple measurements along the stem, reducing their performance when they are used for stem bucking as including additional diameter measurements was shown to improve the predictions [19]. One strategy to alleviate this problem was to develop taper equations for smaller subsets of stems that have similar characteristics [20] [21]. While doing so can improve the performance of the predictions, it is still not equivalent to conditioning the predictions on the previous stem measurements as it is done by harvesters.…”