Predicting individual tree attributes from airborne laser point clouds based on the random forests technique

This paper depicts an approach for predicting individual tree attributes, i.e., tree height, diameter at breast height (DBH) and stem volume, based on both physical and statistical features derived from airborne laser-scanning data utilizing a new detection method for finding individual trees together with random forests as an estimation method. The random forests (also called regression forests) technique is a nonparametric regression method consisting of a set of individual regression trees. Tests of the method were performed, using 1476 trees in a boreal forest area in southern Finland and laser data with a density of 2.6 points per m². Correlation coefficients (R) between the observed and predicted values of 0.93, 0.79 and 0.87 for individual tree height, DBH and stem volume, respectively, were achieved, based on 26 laser-derived features. The corresponding relative root-mean-squared errors (RMSEs) were 10.03%, 21.35% and 45.77% (38% in best cases), which are similar to those obtained with the linear regression method, with maximum laser heights, laser-estimated DBH or crown diameters as predictors. With random forests, however, the forest models currently used for deriving the tree attributes are not needed. Based on the results, we conclude that the method is capable of providing a stable and consistent solution for determining individual tree attributes using small-footprint laser data.     

Nudging the Impasse? Lessons From the Nationwide Online Wolf Management Forum in Finland

During the early 2010s, Finnish wolf (Canis lupus) policy reached an impasse. Unfavorable conservation status, intensifying wolf–human conflict, civil disobedience, legislative confusion, and administrative frustration characterized the situation. As part of a participatory updating process for the Finnish national wolf management plan in 2014, we organized a nationwide wolf management forum to explore how e-participation could be used to nurture deliberation for improved wolf policy. We present our interactive method and the resulting wolf territory-based solutions to the wolf problems that the participants of a nationwide online forum identified. The theoretical and practical significance of our work is that we ascribe value to the functional features of these solutions as modifications to the action environment, shared by people and wolves. In this vein, we discuss the role of e-deliberation on the path toward an institutional fit, and we consider how local decision making could help to implement promising wolf territory-level policy interventions.     

Cosmogenic Be dating of the Salpausselkä I Moraine in southwestern Finland

We determined in situ cosmogenic ¹⁰Be ages for nine boulders sampled on the Salpausselkä I (Ss I) Moraine. Previous dating of this moraine indicated that it formed during the Younger Dryas Stadial along the southern margin of the Scandinavian Ice Sheet in southern Finland. Our new exposure ages range from 10.9±1.0 to 13.5±1.2 ¹⁰Be ka, with an error-weighted mean age of 12.4±0.7 ¹⁰Be ka. Our results confirm four previous ¹⁰Be ages obtained 40 km northeast of our sample location. The combined data (n=13) indicate that retreat from the Ss I Moraine occurred at 12.5±0.7 ¹⁰Be ka, in excellent agreement with an age of 12.1 ka for retreat from the Ss I Moraine based on varve chronologies. These results identify the Ss I Moraine as among the best-dated margins associated with Late Quaternary ice sheets.