Eduardo González-Ferreiro

Assessing the attributes of high-density Eucalyptus globulus stands using airborne laser scanner data

This article presents an airborne Light Detection and Ranging (LiDAR)-based method to extract interesting stand attributes for forest management in high-density Eucalyptus globulus Labill. plantations. An adaptive morphological filter (AMF) for classifying terrain LiDAR points in forested areas is used to classify LiDAR points; canopy cover (CC), number of LiDAR-detected trees per hectare (N LD) and individual tree height (h tree) were calculated using the canopy height model (CHM); and several statistics and metrics extracted from the CHM and the normalized height of the LiDAR data cloud (NHD) were incorporated into the linear and multiplicative models for estimating mean height (H m), dominant height (H d), mean diameter (d m), quadratic mean diameter (d g), number of stems per hectare (N), basal area (G) and volume (V). The height accuracy results of the LiDAR-derived digital terrain model (DTM), root mean square error (RMSE) = 0.303 m, revealed that the developed filter behaved well. The values of the RMSE for CC, N LD and h tree were 13.2%, 733.3 stems ha–1 and 1.91 m, respectively. The regressions explained 78% of the variance in ground-truth values for H m (RMSE = 1.33 m); 92% for H d (RMSE = 1.18 m); 71% for d m (RMSE = 1.68 cm); 73% for d g (RMSE = 1.66 cm); 49% for N (RMSE = 667 stems ha–1); 78% for G (RMSE = 5.30 m2 ha–1); and 81% for V (RMSE = 53.6 m3 ha–1).

Modelling canopy fuel variables for Pinus radiata D. Don in NW Spain with low-density LiDAR data

Crown fire initiation and spread are key elements in gauging fire behaviour potential in conifer forests. Crown fire initiation and spread models implemented in widely used fire behaviour simulation systems such as FARSITE and FlamMap require accurate spatially explicit estimation of canopy fuel complex characteristics. In the present study, we evaluated the potential use of very low-density airborne LiDAR (light detection and ranging) data (0.5 first returns m-2) - which is freely available for most of the Spanish territory - to estimate canopy fuel characteristics in Pinus radiata D. Don stands in north-western Spain. Regression analysis indicated strong relationships (R2 = 0.82-0.98) between LiDAR-derived metrics and field-based fuel estimates for stand height, canopy fuel load, and average and effective canopy base height Average and effective canopy bulk density (R2 = 0.59-0.70) were estimated indirectly from a set of previously modelled forest variables. The LiDAR-based models developed can be used to elaborate geo-referenced raster files to describe fuel characteristics. These files can be generated periodically, whenever new freely available airborne LiDAR data are released by the Spanish National Plan of Aerial Orthophotography, and can be used as inputs in fire behaviour simulation systems.

Evolutionary feature selection to estimate forest stand variables using LiDAR

Abstract Light detection and ranging (LiDAR) has become an important tool in forestry. LiDAR-derived models are mostly developed by means of multiple linear regression (MLR) after stepwise selection of predictors. An increasing interest in machine learning and evolutionary computation has recently arisen to improve regression use in LiDAR data processing. Although evolutionary machine learning has already proven to be suitable for regression, evolutionary computation may also be applied to improve parametric models such as MLR. This paper provides a hybrid approach based on joint use of MLR and a novel genetic algorithm for the estimation of the main forest stand variables. We show a comparison between our genetic approach and other common methods of selecting predictors. The results obtained from several LiDAR datasets with different pulse densities in two areas of the Iberian Peninsula indicate that genetic algorithms perform better than the other methods statistically. Preliminary studies suggest that a lack of parametric conditions in field data and possible misuse of parametric tests may be the main reasons for the better performance of the genetic algorithm. This research confirms the findings of previous studies that outline the importance of evolutionary computation in the context of LiDAR analisys of forest data, especially when the size of fieldwork datatasets is reduced.

A mixed pixel-and region-based approach for using airborne laser scanning data for individual tree crown delineation in Pinus radiata D. Don plantations

The aim of this study was to evaluate the use of high-resolution airborne laser scanner (ALS) data to detect and measure individual trees. We developed and tested a new mixed pixel- and region-based algorithm (using Definiens Developer 7.0) for locating individual tree positions and estimating their total heights. We computed a canopy height model (CHM) of pixel size 0.25 m from dense first-pulse point data (8 pulses m−2) acquired with a small-footprint discrete-return lidar sensor. We validated the results of individual tree segmentation with accurate field measurements made in 37 plots of Monterey pine (Pinus radiata D. Don) distributed over an area of 36 km2. Fieldwork consisted of labelling all of the trees in each plot and measuring their height and position, for posterior integration of the data from both sources (field and lidar). The proposed algorithm correctly detected and linked 59.8% of the trees in the 37 sample plots. We also manually located the trees by using FUSION software to visualize the raw lidar data cloud. However, because the latter method is extremely time-consuming, we only considered 10 randomly selected plots. Manual location correctly detected and linked 71.9% of the trees (in this subsample the algorithm correctly detected and measured 63.5% of the trees). The R2 values for the linear model relating field- and lidar-measured heights of the linked trees located manually and with the automatic location algorithm were 0.90 and 0.88, respectively.

Comparison of ALS based models for estimating aboveground biomass in three types of Mediterranean forest

Abstract This study aimed to develop ALS-based models for estimating stem, crown and aboveground biomass in three types of Mediterranean forest, based on low density ALS data. Two different modelling approaches were used: (i) linear models with different variable selection methods (Stepwise Selection [SS], Clustering/Exhaustive search [CE] and Genetic Algorithm [GA]), and (ii) previously Published Models (PM) applicable to diverse types of forest. Results indicated more accurate estimations of biomass components for pure Pinus pinea L. (rRMSE = 25.90-26.16%) than for the mixed (30.86-36.34%) and Quercus pyrenaica Willd. forests (32.78-34.84%). All the tested approaches were valuable, but SS and GA performed better than CE and PM in most cases.

A comparative study between two regression methods on LiDAR data: a case study

Airborne LiDAR (Light Detection and Ranging) has become an excellent tool for accurately assessing vegetation characteristics in forest environments. Previous studies showed empirical relationships between LiDAR and field-measured biophysical variables. Multiple linear regression (MLR) with stepwise feature selection is the most common method for building estimation models. Although this technique has provided very interesting results, many other data mining techniques may be applied. The overall goal of this study is to compare different methodologies for assessing biomass fractions at stand level using airborne Li-DAR data in forest settings. In order to choose the best methodology, a comparison between two different feature selection techniques (stepwise selection vs. genetic-based selection) is presented. In addition, classical MLR is also compared with regression trees (M5P). The results when each methodology is applied to estimate stand biomass fractions from an area of northern Spain show that genetically-selected M5P obtains the best results.

Classification of rural landscapes from low-density lidar data: is it theoretically possible?

Lidar technology has become an important data source in 3D terrain modelling. In Spain, the National Plan for Aerial Orthophotography will soon release public low-density lidar data (0.5–1 pulses/m2) for most of the country territory. Taking advantage of this fact, this article experimentally assesses the possibility of classifying a rural landscape into eight classes using multitemporal and multidensity lidar data and analyses the effect of point density on classification accuracy. Two statistical methods (transformed divergence and the Jeffries–Matusita distance) were used to assess the possibility of discriminating the eight classes and to determine which data layers were best suited for classification purposes. The results showed that ‘dirt road’ cannot be discriminated from ‘bare earth’ and that the possibility of discriminating ‘bare earth’, ‘pavement’, and ‘low vegetation’ decreases when using densities below 4 pulses/m2. Two non-parametric tests, the Kruskal–Wallis test and the Friedman test, were used to strengthen the results by assessing their statistical significance. According to the results of the Kruskal–Wallis test, lidar point density does not significantly affect the classification, whereas the results of the Friedman test show that bands could be considered as the only parameter affecting the possibility of discriminating some of the classes, such as ‘high vegetation’. Finally, the J48 algorithm was used to perform cross-validation in order to obtain the most familiar quantitative values in the international literature (e.g. overall accuracy). Mean overall accuracy was around 85% when the eight classes were considered and increased up to 95% when ‘dirt road’ was disregarded.

Modelling the vertical distribution of canopy fuel load using national forest inventory and low-density airbone laser scanning data

The fuel complex variables canopy bulk density and canopy base height are often used to predict crown fire initiation and spread. Direct measurement of these variables is impractical, and they are usually estimated indirectly by modelling. Recent advances in predicting crown fire behaviour require accurate estimates of the complete vertical distribution of canopy fuels. The objectives of the present study were to model the vertical profile of available canopy fuel in pine stands by using data from the Spanish national forest inventory plus low-density airborne laser scanning (ALS) metrics. In a first step, the vertical distribution of the canopy fuel load was modelled using the Weibull probability density function. In a second step, two different systems of models were fitted to estimate the canopy variables defining the vertical distributions; the first system related these variables to stand variables obtained in a field inventory, and the second system related the canopy variables to airborne laser scanning metrics. The models of each system were fitted simultaneously to compensate the effects of the inherent cross-model correlation between the canopy variables. Heteroscedasticity was also analyzed, but no correction in the fitting process was necessary. The estimated canopy fuel load profiles from field variables explained 84% and 86% of the variation in canopy fuel load for maritime pine and radiata pine respectively; whereas the estimated canopy fuel load profiles from ALS metrics explained 52% and 49% of the variation for the same species. The proposed models can be used to assess the effectiveness of different forest management alternatives for reducing crown fire hazard.

Comparison of ALS- and UAV(SfM)-derived high-density point clouds for individual tree detection in Eucalyptus plantations

ABSTRACT Highly accurate, rapid forest inventory techniques are needed to enable forest managers to address the increasing demand for sustainable forestry. In the last two decades, Airborne Laser Scanning (ALS) and Terrestrial Laser Scanning have become internationally established as forest mapping and monitoring methods. However, recent advances in sensors and in image processing – particularly Structure from Motion (SfM) technology – have also enabled the extraction of dense point clouds from images obtained by Digital Aerial Photography (DAP). DAP is cheaper than ALS, especially when the systems are mounted on small unmanned aerial vehicles (UAVs), and the density of the point cloud can easily reach the levels yielded by ALS devices. The main objective of this study was to evaluate and compare the usefulness of ALS-derived and UAV(SfM)-derived high-density point clouds for detecting and measuring individual tree height in Eucalyptus spp. plantations established on complex terrain. A total of 325 reference trees were measured and located in 6 square plots (400 m2). The individual tree crown (ITC) delineation algorithm detected 311 from the ALS-derived data and 259 trees from the UAV(SfM)-derived data, representing accuracy levels of, respectively, 96% and 80%. The results suggest that at plot level, UAV(SfM)-generated point clouds are as good as ALS-derived point clouds for estimating individual tree height. Furthermore, analysis of the differences in digital elevation models at landscape level showed that the elevations of the UAV(SfM)-derived terrain surfaces were slightly higher than the ALS-derived surfaces (mean difference, 1.14 m and standard deviation, 1.93 m). Finally, we discuss how non-optimal UAV-image-acquisition conditions and slope terrain affect the ITC delineation process.

Evaluating the Potential of ALS Data to Increase the Efficiency of Aboveground Biomass Estimates in Tropical Peat–Swamp Forests

We are grateful to the Galician Government and European Social Fund (Official Journal of Galicia DOG n 52, 17 March 2014, p. 11343, exp: POS-A/2013/049) for financing the postdoctoral research stays of Eduardo Gonzalez-Ferreiro at different institutions