Nearest neighbor imputation of logwood volumes using bi-temporal ALS, multispectral ALS and aerial images

Abstract

We examine the nearest neighbor (NN) imputation of species-specific logwood volumes using airborne laser scanning (ALS) data and aerial images. We compare different remote sensing (RS) data combinations as predictor variables in an area-based prediction of logwood volumes using separate training and validation data. We include multispectral leaf-on ALS data, bi-temporal leaf-off ALS data and aerial images in the analyses. Two response configurations were used in the NN imputations: (1) simultaneous imputation in which species-specific logwood volumes are response variables, and (2) separate imputation by tree species in which the attributes of one tree species at a time are response variables. Although an unrealistic alternative in practical implementation, the combination of leaf-on and leaf-off ALS metrics as predictors proved to be the most successful RS data combination, according to the RMSE values associated with the predicted species-specific and dominant logwood volumes. The results show that older leaf-off ALS data performed well in combination with leaf-on ALS data. In general, predictive performance was better with simultaneous imputation than with separate imputation by tree species. Our finding promotes an awareness of how best to utilize various RS data in future forest inventories.

Single sensor airborne data sources for forest inventories by tree species

“…To the best of this author's knowledge, only two studies, in addition to this thesis, have applied ABA in the prediction of boreal tree species attributes using M-ALS. Räty et al (2019) found that M-ALS features slightly decreased the prediction errors associated with logwood volumes compared to features calculated from U-ALS data. Dalponte et al (2018) predicted the Shannon diversity index of tree species.…”

“…The intensities of M-ALS are considered beneficial in the classification of tree species, both using ABA (Dalponte et al 2018;Räty et al 2019) and ITD (Yu et al 2017;Axelsson et al 2018;Budei et al 2018). Although prediction errors or classification accuracies are not directly comparable between ITD and ABA, we can examine whether similar features were important predictors.…”

“…The SDI was predicted with the lowest error rate by calculating the predictor variables, considering all echoes across all channels. In contrast, Räty et al (2019) reported that a combination of LiDAR and aerial images were superior to M-ALS data in the prediction of tree species-specific logwood volumes in Finland.…”

“…Budei et al (2018) found that the combined features from all three channels provided the highest classification accuracy (75 %) in the classification of 10 manually delineated tree species. The only experiments to date where M-ALS data has been applied using ABA were published by Dalponte et al (2018) and Räty et al (2019). Dalponte et al (2018) found that M-ALS data provided better results than conventional ALS data in predicting a variety of forest characteristics, including the Shannon diversity index (SDI) of tree species.…”

Horvitz‐Thompson–like estimation with distance‐based detection probabilities for circular plot sampling of forests

“…Tree locations were determined using a variant of the triangulation method proposed by Korpela et al (2007). Field measurements are documented in detail in Räty et al (2019). The central 10 × 10 m 2 of every plot was covered with a triangular grid where the distance between points was at least 1 m. Every grid point was used as a center for a simulated circular sampling plot with radius 10 m. If a tree stem covered the center point, it was removed.…”