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

2021 ◽  
Author(s):  
Xiongwei Lou ◽  
Yuhui Weng ◽  
Luming Fang ◽  
Jason Grogan
Keyword(s):  
Loblolly Pine ◽  
Pine Plantations ◽  
Diameter Distribution ◽  
Gradient Boosting ◽  
Distribution Models ◽  
Management Planning ◽  
Forest Management Planning ◽  
Precise Prediction ◽  
Form Model ◽  
Gb Model

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. Management and Policy 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.

scholarly journals A New Diameter Distribution Model for Unmanaged Loblolly Pine Plantations in East Texas

2006 ◽  
Vol 30 (1) ◽  
pp. 13-20 ◽  
Author(s):  
Young-Jin Lee ◽  
Dean W. Coble
Keyword(s):  
Loblolly Pine ◽  
Pine Plantations ◽  
Growth And Yield ◽  
Distribution Model ◽  
Diameter Distribution ◽  
Yield Prediction ◽  
East Texas ◽  
Distribution Models ◽  
Parameter Recovery ◽  
Diameter Classes

Abstract A parameter recovery procedure for the Weibull distribution function based on four percentile equations was used to develop a diameter distribution yield prediction model for unmanaged loblolly pine (Pinus taeda L.) plantations in East Texas. This model was compared with the diameter distribution models of Lenhart and Knowe, which have been used in East Texas. All three models were evaluated with independent observed data. The model developed in this study performed better than the other two models in prediction of trees per acre and cubic-foot volume per acre (wood and bark, excluding stump) across diameter classes. Lenhart’s model consistently underestimated the larger-diameter classes because it was developed originally with data mostly collected in young plantations. Knowe’s model overestimated volume in sawtimber-sized trees, which could lead to overestimations of volume in older loblolly pine plantations found in East Texas. An example also is provided to show users how to use this new yield prediction system. These results support the recommendation that forest managers should use growth and yield models designed and/or calibrated for the region in which they are implemented.South. J. Appl.For. 30(1):13–20.

Predicting Stand Attributes of Loblolly Pine in West Gulf Coastal Plain Using Gradient Boosting and Random Forests

2020 ◽  
Author(s):  
Xiongwei Lou ◽  
Yuhui Weng ◽  
Luming Fang ◽  
HL Gao ◽  
Jason Grogan ◽  
...  
Keyword(s):  
Loblolly Pine ◽  
Random Forests ◽  
Coastal Plain ◽  
Mean Squared Error ◽  
Pine Plantations ◽  
Machine Learning Techniques ◽  
Coefficient Of Determination ◽  
Gradient Boosting ◽  
Gulf Coastal Plain ◽  
Intensively Managed

Two machine-learning techniques, gradient boosting (GB) and random forests (RF), were used to predict stand mean height (HT), trees per hectare (Tree ha-1) and basal area per hectare (BA ha-1) based on datasets collected from extensively- and intensively-managed loblolly pine plantations in the West Gulf Coastal Plain region. Models were evaluated using coefficient of determination (R2), bias and root mean squared error (RMSE) by applying models to independent dataset and then compared to the model (Coble et al. 2017) currently being used in the region. For extensively-managed plantations, the GB models had less bias, larger R2 and smaller RMSE than RF and HT model was the best, followed by those of Tree ha-1 and BA ha-1. Even for BA ha-1, the GB model had R2 over 0.83. GB and RF models outperformed the Coble et al. (2017); differences were notable for HT and Tree ha-1, but significant for BA ha-1. For intensively-managed plantations, GB and RF were similarly great in predicting HT and Tree ha-1, but GB outperformed RF in predicting BA ha-1. We recommend the use of GB models to predict quantitative information required for managing loblolly pine plantations in the region.

Basal Area and Diameter Distribution Models for Loblolly Pine Plantations with Hardwood Competition in the Piedmont and Upper Coastal Plain

1992 ◽  
Vol 16 (2) ◽  
pp. 93-98 ◽  
Author(s):  
Steven A. Knowe
Keyword(s):  
Pinus Taeda ◽  
Loblolly Pine ◽  
Coastal Plain ◽  
Basal Area ◽  
Simulation Models ◽  
Diameter Distribution ◽  
Distribution Models ◽  
Pinus Taeda L ◽  
The Impact ◽  
Volume Equations

Abstract Prediction equations were developed for basal area and percentiles of diameter distributions to account for the hardwood component in site-prepared, Piedmont and Upper Coastal Plain loblolly pine (Pinus taeda L.) plantations. Unlike existing stand-level simulation models that incorporate hardwood competition, the new equations resulted in constant total basal area regardless of the amount of hardwood competition and permitted the variance of the diameter distribution to increase with increasing proportion of hardwoods. The equations presented can be used with existing dominant height, survival, and volume equations as a tool for assessing the impact of hardwoods on loblolly pine yield. South. J. Appl. For. 16(2):93-98.

scholarly journals A Comparison of Loblolly Pine Plantation Growth and Yield Models for Inventory Updating

1996 ◽  
Vol 20 (1) ◽  
pp. 15-22 ◽  
Author(s):  
James S. Shortt ◽  
Harold E. Burkhart
Keyword(s):  
Loblolly Pine ◽  
Growth And Yield ◽  
Diameter Distribution ◽  
Distribution Models ◽  
Tree Model ◽  
Individual Tree ◽  
Parameter Recovery ◽  
Individual Tree Model ◽  
The Individual ◽  
Growth And Yield Models

Abstract Four different loblolly pine growth and yield models were evaluated for the purpose of updating forest inventory data. The types of growth and yield models examined were: a whole stand, a diameter distribution-parameter prediction, a diameter distribution-parameter recovery, and an individual tree model. Three different approaches were used to create fitting and validation data sets from permanent plot remeasurement data; each of the four growth and yield models was evaluated at varying projection periods. The periods used were 0, 3, 6, and 9 yr. Evaluations were based solely on the capability of each model to predict merchantable volume. In terms of root mean square error of prediction, the individual tree and whole stand models performed better than the diameter distribution models. At shorter projection periods, the individual tree model performed better than the whole stand model, but the whole stand approach was superior at the 9 yr period. Of the diameter distribution models, the parameter recovery model performed better for shorter periods than the parameter prediction model, but this difference diminished with longer periods. South. J. Appl. For. 20(1):15-22.

scholarly journals A New Diameter Distribution Model for Unmanaged Slash Pine Plantations in East Texas

2008 ◽  
Vol 32 (2) ◽  
pp. 89-94 ◽  
Author(s):  
Dean W. Coble ◽  
Young-Jin Lee
Keyword(s):  
Loblolly Pine ◽  
Pinus Elliottii ◽  
Slash Pine ◽  
Pine Plantations ◽  
Distribution Model ◽  
Diameter Distribution ◽  
Yield Prediction ◽  
Prediction System ◽  
East Texas ◽  
New Model

Abstract A parameter recovery procedure for the Weibull distribution function based on four percentile equations was used to develop a new diameter distribution yield prediction model for unmanaged slash pine (Pinus elliottii Engelm.) plantations in East Texas. This new model was similar in structure to the model of Lee and Coble (Lee, Y.J., and D.W. Coble. 2006. A new diameter distribution model for unmanaged loblolly pine plantations in east Texas. South. J. Appl. For. 30(1):13–20) in their work with East Texas loblolly pine plantations. The new model was compared with the diameter distribution model of Lenhart (Lenhart, J.D. 1988. Diameter distribution yield prediction system for unthinned loblolly and slash pine plantations on non-old-fields in east Texas. South. J. Appl. For. 12(4):239–242. 1988), which was developed for slash pine plantations in East Texas, as well as to two other models developed using iterative techniques suggested and inspired by Cao (Cao, Q. 2004. Predicting parameters of a Weibull function for modeling diameter distribution. For. Sci. 50(5):682–685). The model developed in this study was preferred over Lenhart (Lenhart 1988) and the other two models in prediction of total trees per acre, basal area per acre, quadratic mean diameter, and cubic-foot volume per acre (wood and bark, excluding stump). An example also is provided to show users how to use this new yield prediction system. We recommend that the model developed in this study be used to estimate growth and yield of East Texas slash pine plantations.

scholarly journals Predicting Dominant Height from Plantation Age and the Diameter Distributions—Site-Prepared Loblolly Pine

1996 ◽  
Vol 20 (3) ◽  
pp. 148-150
Author(s):  
R. L. Bailey ◽  
Stacey W. Martin
Keyword(s):  
Loblolly Pine ◽  
Site Index ◽  
Pine Plantations ◽  
Diameter Distribution ◽  
Stand Age ◽  
Average Height ◽  
Regression Equations ◽  
Distribution Characteristics ◽  
Dominant Height ◽  
Plantation Age

Abstract With over 1,300 observations from plots in mechanically site-prepared loblolly pine plantations, regression equations are fitted that predict average height of dominant and codominant trees (i.e., site index trees)from stand age and diameter distribution characteristics. The equations can be used to avoid measuring heights and thus reduce costs of volume inventories in loblolly pine plantations. South. J. Appl. For. 20(3):148-150.

Harvester Productivity for Row Thinning Loblolly Pine Plantations

1980 ◽  
Author(s):  
James E. Granskog ◽  
Walter C. Anderson
Keyword(s):  
Loblolly Pine ◽  
Pine Plantations
Sign in / Sign up

Export Citation Format

Share Document