& Key message We examine how the configurations in nearest neighbor imputation affect the performance of predicted species-specific diameter distributions. The simultaneous nearest neighbor imputation for all tree species and separate imputation by tree species are evaluated with total volume calibration as a prediction method for diameter distributions. & Context This study considers the predictions of species-specific diameter distributions in Finnish boreal forests by means of airborne laser scanning (ALS) data and aerial images. & Aims The aim was to investigate different configurations in non-parametric nearest neighbor (NN) imputation and to determine how changes in configurations affect prediction error rates for timber assortment volumes and the error indices of the diameter distributions. & Methods Non-parametric NN imputation was used as a modeling method and was applied in two different ways: (1) diameter distributions were predicted at the same time for all tree species by simultaneous NN imputation, and (2) diameter distributions were predicted for one tree species at a time by separate NN imputation. Calibration to a regression-based total volume prediction was applied in both cases. & Results The results indicated that significant changes in the volume prediction error rates for timber assortment and for error indices can be achieved by the selection of responses, calibration to total volume, and separate NN imputation by tree species. & Conclusion Overall, the selection of response variables in NN imputation and calibration to total volume improved the predicted diameter distribution error rates. The most successful prediction performance of diameter distribution was achieved by separate NN imputation by tree species.
Background: Tree species recognition is the main bottleneck in remote sensing based inventories aiming to produce an input for species-specific growth and yield models. We hypothesized that a stratification of the target data according to the dominant species could improve the subsequent predictions of species-specific attributes in particular in study areas strongly dominated by certain species. Methods: We tested this hypothesis and an operational potential to improve the predictions of timber volumes, stratified to Scots pine, Norway spruce and deciduous trees, in a conifer forest dominated by the pine species. We derived predictor features from airborne laser scanning (ALS) data and used Most Similar Neighbor (MSN) and Seemingly Unrelated Regression (SUR) as examples of non-parametric and parametric prediction methods, respectively. Results: The relationships between the ALS features and the volumes of the aforementioned species were considerably different depending on the dominant species. Incorporating the observed dominant species inthe predictions improved the root mean squared errors by 13.3-16.4 % and 12.6-28.9 % based on MSN and SUR, respectively, depending on the species. Predicting the dominant species based on a linear discriminant analysis had an overall accuracy of only 76 % at best, which degraded the accuracies of the predicted volumes. Consequently, the predictions that did not consider the dominant species were more accurate than those refined with the predicted species. The MSN method gave slightly better results than models fitted with SUR. Conclusions: According to our results, incorporating information on the dominant species has a clear potential to improve the subsequent predictions of species-specific forest attributes. Determining the dominant species based solely on ALS data is deemed challenging, but important in particular in areas where the species composition is otherwise seemingly homogeneous except being dominated by certain species.
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.
An area-based approach (ABA) is the most common method used to predict forest attributes with airborne laser scanning (ALS) data. Individual-tree detection (ITD) offers an alternative to ABA; however, few studies have examined the selection of these two alternatives for the prediction of diameter distributions. We predicted diameter distributions by applying ABA and ITD in coniferous-dominated boreal forests using ALS data and examined their predictive performance based on the shapes of the diameter distributions (Gaussian, bimodal, and reverse-J). We proposed an ABA–ITD fusion for diameter distribution prediction. Firstly, the fusion was optimized and its potential was evaluated using an error index. Secondly, we offer two alternatives to incorporate the fusion into ALS-based forest inventories. Our results indicate that ITD is more prone to errors than ABA and that the predictive performance of ITD is more sensitive than ABA to the shape of the diameter distribution. The results show that ITD outperforms ABA with Gaussian diameter distributions. In contrast, ABA was seen as preferable to ITD with bimodal- or reverse-J-shaped diameter distributions. The findings indicate that ABA–ITD fusion has potential for predicting diameter distributions, although the predictive capability of ITD is limited compared with that of ABA.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.