Reply to Vauhkonen: Comment on Tompalski et al. Combining Multi-Date Airborne Laser Scanning and Digital Aerial Photogrammetric Data for Forest Growth and Yield Modelling. Remote Sens. 2018, 10, 347

n/a

Integrating biophysical controls in forest growth and yield predictions with artificial intelligence technology

Growth and yield models are critically important for forest management planning. Biophysical factors such as light, temperature, soil water, and nutrient conditions are known to have major impacts on tree growth. However, it is difficult to incorporate these biophysical variables into growth and yield models due to large variation and complex nonlinear relationships between variables. In this study, artificial intelligence technology was used to develop individual-tree-based basal area (BA) and volume increment models. The models successfully account for the effects of incident solar radiation, growing degree days, and indices of soil water and nutrient availability on BA and volume increments of over 40 species at 5-year intervals. The models were developed using data from over 3000 permanent sample plots across the province of Nova Scotia, Canada. Model validation with independent field data produced model efficiencies of 0.38 and 0.60 for the predictions of BA and volume increments, respectively. The models are applicable to predict tree growth in mixed species, even- or uneven-aged forests in Nova Scotia but can easily be calibrated for other climatic and geographic regions. Artificial neural network models demonstrated better prediction accuracy than conventional regression-based approaches. Artificial intelligence techniques have considerable potential in forest growth and yield modelling.

Using JABOWA-3 for forest growth and yield predictions under diverse forest conditions of Nova Scotia, Canada

Empirical growth and yield models developed from historical data are commonly used in developing long-term strategic forest management plans. Use of these models rests on an assumption that there will be no future change in the tree growing environment. However, major impacts on forest growing conditions are expected to occur with climate change. As a result, there is a pressing need for tools capable of incorporating outcomes of climate change in their predictions of forest growth and yield. Process-based models have this capability and may, therefore, help to satisfy this requirement. In this paper, we evaluate the suitability of an ecological, individual-tree-based model (JABOWA-3) in generating forest growth and yield projections for diverse forest conditions across Nova Scotia, Canada. Model prediction accuracy was analyzed statistically by comparing modelled with observed basal area and merchantable volume changes for 35 permanent sample plots (PSPs) measured over periods of at least 25 years. Generally, modelled basal area and merchantable volume agreed fairly well with observed data, yielding coefficients of determination (r2) of 0.97 and 0.94 and model efficiencies (ME) of 0.96 and 0.93, respectively. A Chi-square test was performed to assess model accuracy with respect to changes in species composition. We found that 83% of species-growth trajectories based on measured basal area were adequately modelled with JABOWA-3 (P > 0.9). Model-prediction accuracy, however, was substantially reduced for those PSPs altered by some level of disturbance. In general, JABOWA-3 is much better at providing forest yield predictions, subject to the availability of suitable climatic and soil information.