Wood supply predictions from forest inventories involve two steps. First, it is predicted whether harvests occur on a plot in a given time period. Second, for plots on which harvests are predicted to occur, the harvested volume is predicted. This research addresses this second step. For forests with more than one species and/or forests with trees of varying dimensions, overall harvested volume predictions are not satisfactory and more detailed predictions are required. The study focuses on southwest Germany where diverse forest types are found. Predictions are conducted for plots on which harvests occurred in the 2002–2012 period. For each plot, harvest probabilities of sample trees are predicted and used to derive the harvested volume (m³ over bark in 10 years) per hectare. Random forests (RFs) have become popular prediction models as they define the interactions and relationships of variables in an automatized way. However, their suitability for predicting harvest probabilities for inventory sample trees is questionable and has not yet been examined. Generalized linear mixed models (GLMMs) are suitable in this context as they can account for the nested structure of tree-level data sets (trees nested in plots). It is unclear if RFs can cope with this data structure. This research aims to clarify this question by comparing two RFs—an RF based on conditional inference trees (CTree-RF), and an RF based on classification and regression trees (CART-RF)—with a GLMM. For this purpose, the models were fitted on training data and evaluated on an independent test set. Both RFs achieved better prediction results than the GLMM. Regarding plot-level harvested volumes per ha, they achieved higher variances explained (VEs) and significantly (p < 0.05) lower mean absolute residuals when compared to the GLMM. VEs were 0.38 (CTree-RF), 0.37 (CART-RF), and 0.31 (GLMM). Root means squared errors were 138.3, 139.9 and 145.5, respectively. The research demonstrates the suitability and advantages of RFs for predicting harvest decisions on the level of inventory sample trees. RFs can become important components within the generation of business-as-usual wood supply scenarios worldwide as they are able to learn and predict harvest decisions from NFIs in an automatized and self-adapting way. The applied approach is not restricted to specific forests or harvest regimes and delivers detailed species and dimension information for the harvested volumes.

Forest growth and wood supply projections are increasingly used to estimate the future availability of woody biomass and the correlated effects on forests and climate. This research parameterizes an inventory-based business-as-usual wood supply scenario, with a focus on southwest Germany and the period 2002-2012 with a stratified prediction. First, the Classification and Regression Trees algorithm groups the inventory plots into strata with corresponding harvest probabilities. Second, Random Forest algorithms generate individual harvest probabilities for the plots of each stratum. Third, the plots with the highest individual probabilities are selected as harvested until the harvest probability of the stratum is fulfilled. Fourth, the harvested volume of these plots is predicted with a linear regression model trained on harvested plots only. To illustrate the pros and cons of this method, it is compared to a direct harvested volume prediction with linear regression, and a combination of logistic regression and linear regression. Direct harvested volume regression predicts comparable volume figures, but generates these volumes in a way that differs from business-as-usual. The logistic model achieves higher overall classification accuracies, but results in underestimations or overestimations of harvest shares for several subsets of the data. The stratified prediction method balances this shortcoming, and can be of general use for forest growth and timber supply projections from large-scale forest inventories.

No abstract