The k-MSN method for the prediction of species-specific stand attributes using airborne laser scanning and aerial photographs

Various studies have been presented within the last 10 years on the possibilities for predicting forest variables such as stand volume and mean height by means of airborne laser scanning (ALS) data. These have usually considered tree stock as a whole, even though it is tree species-specific forest information that is of primary interest in Finland, for example. We will therefore concentrate here on prediction of the species-specific forest variables volume, stem number, basal area, basal area median diameter and tree height, applying the non-parametric k-MSN method to a combination of ALS data and aerial photographs in order to predict these stand attributes simultaneously for Scots pine, Norway spruce and deciduous trees as well as total characteristics as sums of the species-specific estimates. The predictor variables derived from the ALS data were based on the height distribution of vegetation hits, whereas spectral values and texture features were employed in the case of the aerial photographs. The data covered 463 sample plots in 67 stands in eastern Finland, and the results showed that this approach can be used to predict species-specific forest variables at least as accurately as from the current stand-level field inventory for Finland. The characteristics of Scots pine and Norway spruce were predicted more accurately than those of deciduous trees.     

Estimating field-plot data of forest stands using airborne laser scanning and SPOT HRG data

Airborne laser scanner systems provide detailed forest information that can be used for important improvements in forest management decisions. Planning systems under development use plot-survey data to represent forest stands in large forest holdings which enables new flexible methods to model the forest and optimize selection of silvicultural treatments. In Sweden today, only averages of forest stand variables are used, and the survey methods used do not provide plot-survey data for all stands in large forest holdings. This is a task possibly solved using airborne laser scanner data. Various measures can be derived from laser data, each describing different forest variables, such as tree height distribution, vegetation density and vertical tree crown structure. Here, imputation of field plot (10 m radius) data using measures derived from airborne laser scanner data (TopEye) and optical image data (SPOT 5 HRG satellite sensor) were evaluated as a method to provide data for new long-term management planning systems. In addition to commonly applied measures, the semivariogram of laser measurements was evaluated as a new measure to extract spatial characteristics of the forest. The study used data from 870, 10 m radius field plots (0 to 812 m³ ha^− 1) surveyed for a 1200 ha large forest estate in the south of Sweden. At the best, combining measures derived from laser scanner data and SPOT 5 data, stand mean volume was estimated with a root mean square error (RMSE) of 20% of the sample mean and stem density with 22% RMSE. Bias of stem density estimates was 5%, and stand stem volume 4%. Although these accuracies are sufficient for operational application, estimates of tree species proportions and within-stand variation were clearly not.     

Small-footprint lidar estimation of sub-canopy elevation and tree height in a tropical rain forest landscape

Meso-scale digital terrain models (DTMs) and canopy-height estimates, or digital canopy models (DCMs), are two lidar products that have immense potential for research in tropical rain forest (TRF) ecology and management. In this study, we used a small-footprint lidar sensor (airborne laser scanner, ALS) to estimate sub-canopy elevation and canopy height in an evergreen tropical rain forest. A fully automated, local-minima algorithm was developed to separate lidar ground returns from overlying vegetation returns. We then assessed inverse distance weighted (IDW) and ordinary kriging (OK) geostatistical techniques for the interpolation of a sub-canopy DTM. OK was determined to be a superior interpolation scheme because it smoothed fine-scale variance created by spurious understory heights in the ground-point dataset. The final DTM had a linear correlation of 1.00 and a root-mean-square error (RMSE) of 2.29 m when compared against 3859 well-distributed ground-survey points. In old-growth forests, RMS error on steep slopes was 0.67 m greater than on flat slopes. On flatter slopes, variation in vegetation complexity associated with land use caused highly significant differences in DTM error distribution across the landscape. The highest DTM accuracy observed in this study was 0.58-m RMSE, under flat, open-canopy areas with relatively smooth surfaces. Lidar ground retrieval was complicated by dense, multi-layered evergreen canopy in old-growth forests, causing DTM overestimation that increased RMS error to 1.95 m.A DCM was calculated from the original lidar surface and the interpolated DTM. Individual and plot-scale heights were estimated from DCM metrics and compared to field data measured using similar spatial supports and metrics. For old-growth forest emergent trees and isolated pasture trees greater than 20 m tall, individual tree heights were underestimated and had 3.67- and 2.33-m mean absolute error (MAE), respectively. Linear-regression models explained 51% (4.15-m RMSE) and 95% (2.41-m RMSE) of the variance, respectively. It was determined that improved elevation and field-height estimation in pastures explained why individual pasture trees could be estimated more accurately than old-growth trees. Mean height of tree stems in 32 young agroforestry plantation plots (0.38 to 18.53 m tall) was estimated with a mean absolute error of 0.90 m (r²=0.97; 1.08-m model RMSE) using the mean of lidar returns in the plot. As in other small-footprint lidar studies, plot mean height was underestimated; however, our plot-scale results have stronger linear models for tropical, leaf-on hardwood trees than has been previously reported for temperate-zone conifer and deciduous hardwoods.     

Segment-constrained regression tree estimation of forest stand height from very high spatial resolution panchromatic imagery over a boreal environment

Mean stand height is an important parameter for forest volume and biomass estimation in support of monitoring and management activities. Information on mean stand height is typically obtained through the manual interpretation of aerial photography, often supplemented by the collection of field calibration data. In remote areas where forest management practices may not be spatially exhaustive or where it is difficult to acquire aerial photography, alternate approaches for estimating stand height are required. One approach is to use very high spatial resolution (VHSR) satellite imagery (pixels sided less than 1 m) as a surrogate for air photos. In this research we demonstrate an approach for modelling mean stand height at four sites in the Yukon Territory, Canada, from QuickBird panchromatic imagery. An object-based approach was used to generate homogenous segments from the imagery (analogous to manually delineated forest stands) and an algorithm was used to automatically delineate individual tree crowns within the segments. A regression tree was used to predict mean stand height from stand-level metrics generated from the image grey-levels and within-stand objects relating individual tree crown characteristics. Heights were manually interpreted from the QuickBird imagery and divided into separate sets of calibration and validation data. The effects of calibration data set size and the input metrics used on the regression tree results were also assessed. The approach resulted in a model with a significant R² of 0.53 and an RMSE of 2.84 m. In addition, 84.6% of the stand height estimates were within the acceptable error for photo interpreted heights, as specified by the forest inventory standards of British Columbia. Furthermore, residual errors from the model were smallest for the stands that had larger mean heights (i.e., > 20 m), which aids in reducing error in subsequent estimates of biomass or volume (since stands with larger trees contribute more to overall estimates of volume or biomass). Estimated and manually interpreted heights were reclassified into 5-metre height classes (a schema frequently used for forest analysis and modelling applications) and compared; classes corresponded in 54% of stands assessed, and all stands had an estimated height class that was within ± 1 class of their actual class. This study demonstrates the capacity of VHSR panchromatic imagery (in this case QuickBird) for generating useful estimates of mean stand heights in unmonitored, remote, or inaccessible forest areas.     

Recursive diameter prediction for calculating merchantable volume of eucalyptus clones using Multilayer Perceptron

A very common problem in forestry is the realization of the forest inventory. The forest inventory is very important because it allows the trading of medium- and long-term timber to be extracted. On completion , the inventory is necessary to measure different diameters and total height to calculate their volumes. However, due to the high number of trees and their heights, these measurements are an extremely time consuming and expensive. In this work, a new approach to predict recursively diameters of eucalyptus trees by means of Multilayer Perceptron artificial neural networks is presented. By taking only three diameter measures at the base of the tree, diameters are predicted recursively until they reach the value of 4 cm, with no previous knowledge of total tree height. The training was conducted with only 10% of the total trees planted site, and the remaining 90% of total trees were used for testing. The Smalian method was used with the predicted diameters to calculate merchantable tree volumes. To check the performance of the model, all experiments were compared with the least square polynomial approximator and the diameters and volumes estimates with both methods were compared with the actual values measured. The performance of the proposed model was satisfactory when predicted diameters and volumes are compared to actual ones.     

Effects of different sensors and leaf-on and leaf-off canopy conditions on echo distributions and individual tree properties derived from airborne laser scanning

The objectives of this study were to quantify and analyze differences in laser height and laser intensity distributions of individual trees obtained from airborne laser scanner (ALS) data for different canopy conditions (leaf-on vs. leaf-off) and sensors. It was also assessed how estimated tree height, stem diameter, and tree species were influenced by these differences. The study was based on 412 trees from a boreal forest reserve in Norway. Three different ALS acquisitions were carried out. Leaf-on and leaf-off data were acquired with the Optech ALTM 3100 sensor, and an additional leaf-on dataset was acquired using the Optech ALTM 1233 sensor. Laser echoes located within the vertical projection of the tree crowns were attributed to different echo categories (“first echoes of many”, “single echoes”, “last echoes of many”) and analyzed. The most pronounced changes in laser height distribution from leaf-on to leaf-off were found for the echo categories denoted as “single” and “last echoes of many” where the distributions were shifted towards the ground under leaf-off conditions. The most pronounced change in the intensity distribution was found for “first echoes of many” where the distribution was extremely skewed towards the lower values under leaf-off conditions compared to leaf-on. Furthermore, the echo height and intensity distributions obtained for the two different sensors also differed significantly. Individual tree properties were estimated fairly accurately in all acquisitions with RMSE ranging from 0.76 to 0.84 m for tree height and from 3.10 to 3.17 cm for stem diameter. It was revealed that tree species was an important model term in both and tree height and stem diameter models. A significantly higher overall accuracy of tree species classification was obtained using the leaf-off acquisition (90 vs. 98%) whereas classification accuracy did not differ much between sensors (90 vs. 93%).     

Using airborne laser scanning to monitor tree migration in the boreal-alpine transition zone

The boreal tree line is expected to advance upwards into the mountains and northwards into the tundra due to global warming. The major objective of this study was to find out if it is possible to use high-resolution airborne laser scanner data to detect very small trees — the pioneers that are pushing the tree line up into the mountains and out onto the tundra. The study was conducted in a sub-alpine/alpine environment in southeast Norway. A total of 342 small trees of Norway spruce, Scots pine, and downy birch with tree heights ranging from 0.11 to 5.20 m were precisely georeferenced and measured in field. Laser data were collected with a pulse density of 7.7 m^− 2. Three different terrain models were used to process the airborne laser point cloud in order to assess the effects of different pre-processing parameters on small tree detection. Greater than 91% of all trees > 1 m tall registered positive laser height values regardless of terrain model. For smaller trees (< 1 m), positive height values were found in 5-73% of the cases, depending on the terrain model considered. For this group of trees, the highest rate of trees with positive height values was found for spruce. The more smoothed the terrain model was, the larger the portion of the trees that had positive laser height values. The accuracy of tree height derived from the laser data indicated a systematic underestimation of true tree height by 0.40 to 1.01 m. The standard deviation for the differences between laser-derived and field-measured tree heights was 0.11-0.73 m. Commission errors, i.e., the detection of terrain objects — rocks, hummocks — as trees, increased significantly as terrain smoothing increased. Thus, if no classification of objects into classes like small trees and terrain objects is possible, many non-tree objects with a positive height value cannot be separated from those actually being trees. In a monitoring context, i.e., repeated measurements over time, we argue that most other objects like terrain structures, rocks, and hummocks will remain stable over time while the trees will change as they grow and new trees are established. Thus, this study indicates that, given a high laser pulse density and a certain density of newly established trees, it would be possible to detect a sufficient portion of newly established trees over a 10 years period to claim that tree migration is taking place.     

基于背包激光雷达的单木材积估测方法研究

背包式激光雷达(Backpack Laser Scanning,BLS)在森林资源调查中具有很大的应用潜力,但在复杂地表情景下,单木材积和林分蓄积量提取精度存在较大不确定性。以广西高峰林场为研究区,利用随机森林方法,基于BLS点云数据对单木材积和样地蓄积量进行估测。首先,对BLS点云进行单木分割,提取单木胸径(DBH)、树高(Htree)、冠幅直径(CD)、冠幅面积(CA)、冠幅体积(CV)、郁闭度(CC)、间隙率(GF)和叶面积指数(LAI)共8个特征参数,并计算56个分层高度指标(高度百分比、累积高度百分比、变异系数、冠层起伏率等)。然后,通过随机森林算法构建单木材积估测模型,并对比各种参数组合的预测精度。得到结果：(1)仅用8个单木结构特征参数进行建模,估测精度为：R²=0.83、RMSE=0.097 m³;(2)加入分层高度指标的模型估测精度有所提升：R²=0.87、RMSE=0.087 m³;(3)通过Boruta算法进行变量筛选,输入参数从64个减少至52个,估测精度差异不大：R     

Imputation of single-tree attributes using airborne laser scanning-based height, intensity, and alpha shape metrics

Forest inventories based on single-tree interpretation of airborne laser scanning (ALS) data often rely on an allometric estimation chain in which inaccuracies in the estimates of the diameter at breast height (DBH) propagate to other characteristics of interest such as the stem volume. Our purpose was to test nearest neighbor imputation by the k-Most Similar Neighbor (k-MSN) and the Random Forest (RF) methods for the simultaneous estimation of species, DBH, height and stem volume using ALS data. The predictors included computational alpha shape metrics and variables based on the height and intensity distributions in the ALS data. Separate data sets covering 1898 and 1249 dominant to intermediate trees in a typical Scandinavian stand structure were used for training and validation, respectively. RF proved to be a flexible method with an ability to handle 1846 predictors with no need for their reduction. Classification of Scots pine, Norway spruce and deciduous trees showed an accuracy of 78%, and the estimates of DBH, height and volume had root mean square errors of 13%, 3%, and 31%, respectively, when evaluated against the validation data. The two selection strategies implemented here reduced the number of candidate variables effectively without any substantial effect on the accuracy relative to the use of all predictors. Differences in k-MSN and RF imputations were marginal when the reduced sets of variables were used. Estimation accuracies could be maintained practically unchanged with only 12.5% of the initial reference data (237 trees), provided the distribution of the observations was similar in the reference and target data. Since we used information collected in the field for extracting the ALS point clouds for individual trees, our results represent an optimal case and should nevertheless be validated against automated tree delineation.     

Influence of terrain model smoothing and flight and sensor configurations on detection of small pioneer trees in the boreal-alpine transition zone utilizing height metrics derived from airborne scanning lasers

It has been suggested that airborne laser scanning (ALS) with high point densities could be used to monitor changes in the alpine tree line. The overall goal of this study was to assess the influence of ALS sensor and flight configurations on the ability to detect small trees in the alpine tree line and on the estimation of their heights. The study was conducted in a sub-alpine/alpine environment in southeast Norway. 342 small trees (0.11-5.20 m tall) of Norway spruce, Scots pine, and downy birch were precisely georeferenced and measured in field. ALS data acquired with two different instruments and at different flying altitudes (700-1130 m a.g.l.) with different pulse repetition frequencies (100, 125, and 166 kHz) were collected with a point density of all echoes of 7.7-11.0 m^− 2. For each acquisition, three different terrain models were used to process the ALS point clouds in order to assess the effects of different preprocessing parameters on the ability to detect small trees. Regardless of acquisition and terrain model, positive height values were found for 91% of the taller trees (> 1 m). For smaller trees (< 1 m), 29-61% of the trees displayed positive height values. For the lowest repetition frequencies (100 and 125 kHz) in particular, the portion of trees with positive laser height values increased significantly with increasing terrain smoothing. For the highest repetition frequency there were no differences between smoothing levels, likely because of large ALS measurement errors at low laser pulse energy levels causing a large portion of the laser echoes to be discarded during terrain modeling. Error analysis revealed large commission errors when detecting small trees. The commissions consisted of objects like terrain structures, rocks, and hummocks having positive height values. The magnitude of commissions ranged from 709 to 8948% of the true tree numbers and tended to increase with increasing levels of terrain smoothing and with acquisitions according to increasing point densities. The accuracy of tree height derived from the ALS data indicated a systematic underestimation of true tree height by 0.35 to 1.47 m, depending on acquisition, terrain model, and tree species. The underestimation also increased with increasing tree height. The standard deviation for the differences between laser-derived and field-measured tree heights was 0.16-0.57 m. Because there are significant effects of sensor and flight configurations on tree height estimation, field calibration of tree heights at each point of time is required when using airborne lasers for tree growth monitoring.     

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).     

Prediction of species specific forest inventory attributes using a nonparametric semi-individual tree crown approach based on fused airborne laser scanning and multispectral data

While forest inventories based on airborne laser scanning data (ALS) using the area based approach (ABA) have reached operational status, methods using the individual tree crown approach (ITC) have basically remained a research issue. One of the main obstacles for operational applications of ITC is biased results often experienced due to segmentation errors. In this article, we propose a new method, called “semi-ITC” that overcomes the main problems related to ITC by imputing ground truth data within crown segments from the nearest neighboring segment. This may be none, one, or several trees. The distances between segments were derived based on a set of explanatory variables using two nonparametric methods, i.e., most similar neighbor inference (MSN) and random forest (RF). RF favored the imputation of common observations in the data set which resulted in significant biases. Main conclusions are therefore based on MSN. The explanatory variables were calculated by means of small footprint ALS and multispectral data. When testing with empirical data the new method compared favorably to the well-known ABA. Another advantage of the new method over the ABA is that it allowed for the modeling of rare tree species. The results of predicting timber volume with the semi-ITC method were unbiased and the root mean squared error (RMSE) on plot level was smaller than the standard deviation of the observed response variables. The relative RMSEs after cross validation using semi-ITC for total volume and volume of the individual species pine, spruce, birch, and aspen on plot level were 17, 38, 40, 101, and 222%, respectively. Due to the unbiasedness of the estimation, this study is a showcase for how to use crown segments resulting from ITC algorithms in a forest inventory context.     

Comparison of UAS photogrammetric products for tree detection and characterization of coniferous stands

The use of Unmanned Aerial Systems (UAS) opens a new era for remote sensing and forest management, which requires accurate and regular quantification of resources. In this study, we propose a comprehensive workflow to detect trees and assess forest attributes in the particular context of coniferous stands in transformation from even-aged to uneven-aged stands, using UAS imagery, from data acquisition to model construction. We implement a local maxima detection to identify the tree tops, based on a fixed-radius moving window in a Canopy Height Model (CHM) and images produced from UAS surveys. To compare the contribution of different photogrammetric products, we analysed the local maxima detected from the CHM, from three image types (individual rectified and ortho-rectified images and ortho-mosaic) and from a combination of both CHM and images. The local maxima detection gave promising results, with low omission and true-positive rates of up to 89.2%. A filtering process of false positives was implemented, using a supervised classification which decreased the false positives up to 2.6%. Based on the local maxima combined with an area-based approach, we constructed models to assess top height (R²: 83%, root mean square error [RMSE]: 5.7%), number of stems (R²: 71%, RMSE: 28.3%), basal area (R²: 70%, RMSE: 16.2%), volume (R²: 69%, RMSE: 20.1%), and individual tree height (R²: 70%, RMSE: 7.2%). Despite a suboptimal data acquisition, our simple and flexible method has yielded good results and shows great potential for application.     

Tree cover and height estimation in the Fennoscandian tundra-taiga transition zone using multiangular MISR data

The tundra-taiga transition zone stretches around the northern hemisphere separating boreal forest to the south from treeless tundra to the north. Tree cover and height are important variables to characterize this vegetation transition. Accurate continuous fields of tree cover and height would enable the delineation of the forest extent according to different criterion and provide useful data for change detection of this climatically sensitive ecotone. This study examined if multiangular remote sensing data has potential to improve the accuracy of the tree cover and height estimates in relation to nadir-view data. The satellite data consisted of Multi-angle Imaging SpectroRadiometer (MISR) data at 275 m and 1.1 km resolutions. The study area was located in the Fennoscandian tundra-taiga transition zone, in northernmost Finland. The continuous fields of tree cover and height were estimated using neural networks, which were trained and assessed by high-resolution biotope inventory data. The spectral-angular data together produced lower estimation errors than single band nadir, multispectral nadir or single band multiangular data alone. RMSE of the tree cover estimates reduced from 7.8% (relative RMSE 67.4%) to 6.5% (56.1%) at 275 m resolution, and from 5.4% (49.2%) to 4.1% (36.9%) at 1.1 km resolution, when multispectral nadir data were used together with multiangular data. RMSE of the tree height estimates reduced from 2.3 m (44.3%) to 2.0 m (37.6%) and from 1.8 m (35.4%) to 1.3 m (25.4%), respectively. The largest estimation errors occurred in mires and in areas of dense shrub cover, but the use of multiangular data also reduced estimation errors in these areas. The results suggest that directional information has potential to improve the tree cover and height estimates, and hence the accuracy of the land cover change detection in the tundra-taiga transition zone.     

Separating the ground and airborne laser sampling phases to estimate tropical forest basal area, volume, and biomass

Airborne laser profiling data were used to estimate the basal area, volume, and biomass of primary tropical forests. A procedure was developed and tested to divorce the laser and ground data collection efforts using three distinct data sets acquired in and over the tropical forests of Costa Rica. Fixed-area ground plot data were used to simulate the height characteristics of the tropical forest canopy and to simulate laser measurements of that canopy. On two of the three study sites, the airborne laser estimates of basal area, volume, and biomass grossly misrepresented ground estimates of same. On the third study site, where the widest ground plots were utilized, airborne and ground estimates agreed within 24%. Basal area, volume, and biomass prediction inaccuracies in the first two study areas were tied directly to disagreements between simulated laser estimates and the corresponding airborne measurements of average canopy height, height variability, and canopy density. A number of sampling issues were investigated; the following results were noted in the analyses of the three study areas. 1) Of the four ground segment lengths considered (25 m, 50 m, 75 m, and 100 m), the 25 m segment length introduced a level of variability which may severely degrade prediction accuracy in these Costa Rican primary tropical forests. This effect was more pronounced as plot width decreased. A minimum segment length was on the order of 50 m. 2) The decision to transform or not to transform the dependent variable (e.g., biomass) was by far the most important factor of those considered in this experiment. The natural log transformation of the dependent variable increased prediction error, and error increased dramatically at the shorter segment lengths. The most accurate models were multiple linear models with forced zero intercept and an untransformed dependent variable. 3) General linear models were developed to predict basal area, volume, and biomass using airborne laser height measurements. Useful laser measurements include average canopy height, all pulses ( _a), average canopy height, canopy hits ( _c) and the coefficients of variation of these terms (c_a and c_c). Coefficients of determination range from 0.4 to 0.6. Based on this research, airborne laser and ground sampling procedures are proposed for use for reconnaissance level surveys of inaccessible forested regions.     

Modeling forest canopy heights: The effects of canopy shape

Three-dimensional models that represent the top-of-canopy forest height structure were developed to simulate airborne laser profiling responses along forested transects. The simulator which produced these 3-D models constructed individual tree crowns according to a tree's total height, height to first branch, crown diameter, and crown shape (cone, parabola, ellipse, sphere, or a random assortment of these shapes), and then inserted these crowns into a fixed-area plot using mapped stand (x,y) coordinates. This two-dimensional array of forest canopy heights was randomly transected to simulate measurements made by an airborne ranging laser. These simulated laser measurements were regressed with ground reference measures to develop predictive linear relationships. The assumed crown shape had a significant impact on 1) simulated laser measurements of height and 2) estimates of basal area, woody volume, and above-ground dry biomass derived via simulation. As canopy shape progressed from a conic form to a more spheric structure, average canopy height, canopy profile area, and canopy volume increased, canopy height variation decreased, and coefficients of variability were stable or decreased. In Costa Rican tropical forests, simulated laser measurements of average height, canopy profile area, and canopy volume increased 8–10% when a parabolic rather than a conic shape was assumed. An elliptic canopy was 16–18% taller, on average, than a conic canopy, and a spheric canopy was 23–25% taller. The effect of these height increases and height variability changes can profoundly affect basal area, volume, and biomass estimates, but the degree to which these estimates are affected is study-area-dependent. Since canopy shape may significantly affect such estimates, canopy shapes should be noted when field data are collected for purposes of height simulation. If canopy shapes are not noted and are unknown, an assumption of an elliptical shape is suggested in order to mitigate potentially large errors which may be incurred using a generic assumption of a cone or sphere.     

Estimation of tropical forest structure from SPOT-5 satellite images

Predictions of tropical forest structure at the landscape level still present relatively high levels of uncertainty. In this study we explore the capabilities of high-resolution Satellite Pour l'Observation de la Terre (SPOT)-5 XS images to estimate basal area, tree volume and tree biomass of a tropical rainforest region in Chiapas, Mexico. SPOT-5 satellite images and forest inventory data from 87 sites were used to establish a multiple linear regression model. The 87 0.1-ha plots covered a wide range of forest structures, including mature forest, with values from 74.7 to 607.1 t ha^?1. Spectral bands, image transformations and texture variables were explored as independent variables of a multiple linear regression model. The R²s of the final models were 0.58 for basal area, 0.70 for canopy height, 0.73 for bole volume, and 0.71 for biomass. A leave-one-out cross-validation produced a root mean square. error (RMSE) of 5.02 m² ha^?1 (relative RMSE of 22.8%) for basal area; 3.22 m (16.1%) for canopy height; 69.08 m³ ha^?1 (30.7%) for timber volume, and 59.3 t ha^?1 (21.2%) for biomass. In particular, the texture variable ‘variance of near-infrared’ turned out to be an excellent predictor for forest structure variables.     

Mapping forest vegetation using Landsat TM imagery and a canopy reflectance model

Estimates of mean tree size and cover for each forest stand from an invertible forest canopy reflectance model are part of a new forest vegetation mapping system. Image segmentation defines stands which are sorted into general growth forms using per-pixel image classifications. Ecological models based on terrain relations predict species associations for the conifer, hardwood, and brush growth forms. The combination of the model-based estimates of tree size and cover with species associations yields general-purpose vegetation maps useful for a variety of land management needs. Results of timber inventories in the Tahoe and Stanislaus National Forests indicate the vegetation maps form a useful basis for stratification. Patterns in timber volumes for the strata reveal that the cover estimates are more reliable than the tree size estimates. A map accuracy assessment of the Stanislaus National Forest shows high overall map accuracy and also illustrates the problems in estimating tree size.     

Single tree detection in heterogeneous boreal forests using airborne laser scanning and area-based stem number estimates

Adaptive single tree detection methods using airborne laser scanning (ALS) data were investigated and validated on 40 large plots sampled from a structurally heterogeneous boreal forest dominated by Norway spruce and Scots pine. Under the working assumption of having uniformly distributed tree locations, area-based stem number estimates were used to guide tree crown delineation from rasterized laser data in two ways: (1) by controlling the amount of smoothing of the canopy height model and (2) by obtaining an appropriate spatial resolution for representing the forest canopy. Single tree crowns were delineated from the canopy height models (CHMs) using a marker-based watershed algorithm, and the delineation results were assessed using a simple tree crown delineation algorithm as a reference method (‘RefMeth’). Using the proposed methods, approximately 46–50% of the total number of trees were detected, while approximately 5–6% false positives were found. The detection rate was, in general, higher for Scots pine than for Norway spruce. The accuracy of individual tree variables (total height and crown width) extracted from the laser data was compared with field-measured data. The individual tree heights were better estimated for deciduous tree species than for the coniferous species Norway spruce and Scots pine. The estimation of crown diameters for Scots pine and deciduous species achieved comparable accuracy, being better than for Norway spruce. The proposed methodology has the potential for easy integration with operational laser scanner-based stand inventories.     

Forest attribute imputation using machine-learning methods and ASTER data: comparison of k-NN,SVR and random forest regression algorithms

In a small case study of mixed hardwood Hyrcanian forests of Iran, three non-parametric methods, namely k-nearest neighbour (k-NN), support vector machine regression (SVR) and tree regression based on random forest (RF), were used in plot-level estimation of volume/ha, basal area/ha and stems/ha using field inventory and Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) data. Relevant pre-processing and processing steps were applied to the ASTER data for geometric and atmospheric correction and for enhancing quantitative forest parameters. After collecting terrestrial information on trees in the 101 samples, the volume, basal area and tree number per hectare were calculated in each plot. In the k-NN implementation using different distance measures and k, the cross-validation method was used to find the best distance measure and optimal k. In SVR, the best regularized parameters of four kernel types were obtained using leave-one-out cross-validation. RF was implemented using a bootstrap learning method with regularized parameters for decision tree model and stopping. The validity of performances was examined using unused test samples by absolute and relative root mean square error (RMSE) and bias metrics. In volume/ha estimation, the results showed that all the three algorithms had similar performances. However, SVR and RF produced better results than k-NN with relative RMSE values of 28.54, 25.86 and 26.86 (m³ ha^–1), respectively, using k-NN, SVR and RF algorithms, but RF could generate unbiased estimation. In basal area/ha and stems/ha estimation, the implementation results of RF showed that RF was slightly superior in relative RMSE (18.39, 20.64) to SVR (19.35, 22.09) and k-NN (20.20, 21.53), but k-NN could generate unbiased estimation compared with the other two algorithms used.