A Novel Modelling Approach for Predicting Forest Growth and Yield under Climate Change

摘要: Global climate is changing due to increasing anthropogenic emissions of greenhouse gases. Forest managers need growth and yield models that can be used predict future forest dynamics during the transition period present-day forests under a climatic regime. In this study, we developed model individual-tree current projected conditions. The was constructed by integrating historical tree records with predictions from an ecological process-based using neural networks. new predicts basal area (BA) volume for individual trees in pure or mixed species forests. For development, tree-growth data conditions were obtained over 3000 permanent sample plots Province Nova Scotia, Canada. Data reflect regime JABOWA-3 (an model). Model validation designated produced efficiencies 0.82 0.89 predicting BA growth. efficiency relative index performance, where 1 indicates ideal fit, while values lower than zero means are no better average observations. Overall mean prediction error (BIAS) nominal (i.e., BA: -0.0177 cm2 5-year-1 volume: 0.0008 m3 5-year-1). variability described root squared (RMSE) 40.53 0.0393 prediction. modelling approach has potential reduce uncertainties different change scenarios. This novel provides avenue generate required information management transitional periods change. Artificial intelligence technology substantial modelling.