Predicting the occurrence of large-diameter trees using airborne laser scanning

Abstract

Large-diameter trees are important for both ecological and economic reasons, but they have become increasingly rare. Thus, there is an interest in easily locating such trees, and for this purpose, the use of airborne laser scanning (ALS) seems suitable. Our objective was to assess the accuracy of area-based ALS estimation in predicting the number of large-diameter Scots pines (Pinus sylvestris L.). A sample of 856 trees with a diameter >35 cm were measured from 1109 sample plots located in eastern Norway. We fitted negative binomial and zero-inflated negative binomial models for predicting large-diameter tree counts. ALS-derived and external variables were used as predictors when fitting the models. The accuracy was assessed based on the weighted kappa coefficient and cross validation. Our best model was based on three ALS height distribution variables, one horizontal ALS variable, and plot elevation. Its overall accuracy was 65.8% and the weighted kappa was 0.55. Although there was a clear relationship between the response and the proposed predictor variables, fairly large errors in the predicted large-diameter tree counts were common.

LiDAR and multispectral imagery predict the occurrence of tree cavities suitable for a cavity‐nesting duck

“…Our final model predicting the presence–absence of suitable cavities had good overall accuracy (84%). This is similar to previous studies predicting snags (86%–88%; (Martinuzzi et al., 2009)), and somewhat better than predictions for the locations of large trees (66%; (Korhonen et al., 2016)). The model was more accurate when predicting absences than presences, though the difference was not great.…”

“…The dramatic increase in types, accessibility, and resolution of remotely sensed data over the last several decades has allowed many studies to predict wildlife habitat and habitat components at high spatial resolution and across broad landscapes (Hyde et al., 2006; Vierling et al., 2008). Multiple sensors, including light detection and ranging (LiDAR) and multispectral satellite imagery, are increasingly being used to predict attributes related to cavities such as snags (Martinuzzi et al., 2009; Pesonen et al., 2008; Wing et al., 2015), large trees (Korhonen et al., 2016), and tree species (Briechle et al., 2020). However, these attributes are not definitive indicators of the presence of cavities.…”

Discrimination between Ground Vegetation and Small Pioneer Trees in the Boreal-Alpine Ecotone Using Intensity Metrics Derived from Airborne Laser Scanner Data

“…When there is a very uneven balance between "zeros" (non-trees) and "non-zeros" (trees), one might for example consider the so-called zero-inflated models, e.g., zero-inflated Poisson models and zero-inflated negative binominal models (see e.g., [57] for an overview of these model types). Such modeling techniques were recently applied to modeling and prediction of rare trees using ALS data [58]. In such models, the "zeros" are attributed to one process, whereas "non-zeros" are attributed to another process.…”

Delineation of Geomorphological Woodland Key Habitats Using Airborne Laser Scanning

“…Remotely sensed data could be used in several ways to improve WKH inventories, for example, by performing a direct classification. In the remote sensing literature, there are documented methods for WKH related to deadwood [12][13][14], successional stages [15], special or old trees [16,17], areas with high herbaceous plant diversity [18,19] or hydrological features [20][21][22][23]. However, there are issues with the obtained accuracy, as some WKH can be modeled with small commission and omission errors, but other WKH types have significant errors of commission and omission, and thus remote sensing is less applicable.…”