Modeling Diameter Distributions of Loblolly Pine Plantations in Western Gulf Coastal Plain

Abstract

Abstract Diameter distribution models are useful tools for forest management planning, in particular for even-aged plantations of important commercial species such as loblolly pine. Using data collected from loblolly pine plantations across East Texas, two diameter distribution model systems were developed, with the first being a conventional, Weibull-form statistical model system and the second being developed using gradient boosting (GB) technique. Both models were tested using an independent data set and compared with the regional model currently being used, which was developed by Lee and Coble (2006). Compared with Lee and Coble (2006), the Weibull-form model of this study had 66.7% smaller prediction bias, 27.2% lower mean absolute error (MAE), and 18.9% smaller root-mean-square error (RMSE). Compared with the Weibull-form model of this study, the GB model had 33.9% lower MAE, 39.5% smaller RMSE, and greater R2. Thus, the GB model greatly outperformed the Weibull-form model, which, in turn, was greatly improved over the Lee and Coble (2006) in prediction accuracy. By combining a regional volume or weight equation, both proposed diameter distribution models can be used to predict stand wood volume or weight by diameter class. Both models, in particular the GB model, are recommended for use in predicting stand structures and developing stand and stock tables for loblolly pine plantations in the region. Study Implications Knowing future stand tree size distributions is important for forest management planning. This study developed two quantitative tools to predict diameter distributions for loblolly pine (Pinus taeda) plantations in the Western Gulf Coastal Plain, with one based on the Weibull function (Weibull-form model) and the other developed using the gradient boosting technique (GB model). For the Weibull-form model, using current stand information, readers can manually calculate future stand trees per acre by diameter class. Importantly, the Weibull-form model provides more accurate (less bias and more precise) prediction than any currently available models for loblolly pine in the region. The GB model, which uses the same predictors as the Weibull-form model, can achieve even better (similar bias but more precise) prediction than the Weibull-form model. However, no equations and model coefficients for the GB model were provided, and use of the GB model relies on computer programming. A computer program was developed to implement the GB model. We recommend use of both models, in particular of the GB model, in managing loblolly pine in the region. The results aid our understanding in loblolly pine stand structure development and management in the region.