Variation and directional anisotropy of reflectance at the crown scale — Implications for tree species classification in digital aerial images

Tree species classification is still solved at insufficient reliability in airborne optical data. The variation caused by directional reflectance anisotropy hampers image-based solutions. In addition, trees show considerable within-species variation in reflectance properties. We examined these phenomena at the single-tree level, using the Leica ADS40 line sensor and XPro software, which constitute the first photogrammetric large-format multispectral system to provide target reflectance images. To analyze the influence of illumination conditions in the canopy, we developed a method in which the crown shape as well as between-tree occlusions and shading were modeled, using dense LiDAR data. The precision of the ADS40 reflectance images in well-defined surfaces was 5% as coefficient of variation when 1−4-km image data were fused. The range of reflectance anisotropy was ± 30% for trees near the solar principal plane, with differences between bands and species. Because of the anisotropy differences observed, the spectral separability of the tree species in different bands is dependent on the view-illumination geometry. The within-species variation was high; the coefficient of variation was 13−31%. The contribution of tree and stand variables to anisotropy-normalized reflectance variation was examined. The effects of the species composition of adjacent trees were substantial in NIR and this variation hampers spectral classification in mixed stands. We also studied species- and band-specific intracrown brightness patterns, and we suggest their use as high-order image features in species classification. A species classification accuracy of up to 80% was obtained using 4-km data, which showed the high potential of the ADS40.     

Boosted decision tree classifications of land cover over Turkey integrating MODIS,climate and topographic data

This study investigates the impact of using different combinations of Moderate Resolution Imaging Spectroradiometer (MODIS) and ancillary datasets on overall and per-class classification accuracies for nine land cover types modified from the classification system of the International Geosphere Biosphere Programme (IGBP). Twelve land cover maps were generated for Turkey using boosted decision trees (BDTs) based on the stepwise addition of 14 explanatory variables derived from a time series of 16-day MODIS composites between 2000 and 2006 (Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI) and four spectral bands) and ancillary climate and topographic data (minimum and maximum air temperature, precipitation, potential evapotranspiration, aspect, elevation, distance to sea and slope) at 500-m resolution. Evaluation of the 12 BDTs indicated that the BDT built as a function of all the MODIS and climate variables, aspect and elevation produced the highest degree of overall classification accuracy (79.8%) and kappa statistic (0.76) followed by the BDTs that additionally included distance to sea (DtS), and both DtS and slope. Based on an independent validation dataset derived from a pre-existing national forest map and Landsat images of Turkey, the highest overall accuracy (64.7%) and kappa coefficient (0.58) among the 12 land cover maps was achieved by using MODIS-derived NDVI time series only, followed by NDVI and EVI time series combined; NDVI, EVI and four MODIS spectral bands; and the combination of all MODIS and climate data, aspect, elevation and distance to sea, respectively. The largest improvements in producer's accuracies were observed for grasslands (+50%), barrenlands (+46%) and mixed forests (+39%) and in user's accuracies for grasslands (+53%), shrublands (+30%) and mixed forests (+28%), in relation to the lowest producer's accuracy. The results of this study indicate that BDTs can increase the accuracy of land cover classifications at the national scale.     

The delineation of tree crowns in Australian mixed species forests using hyperspectral Compact Airborne Spectrographic Imager (CASI) data

In mixed-species forests of complex structure, the delineation of tree crowns is problematic because of their varying dimensions and reflectance characteristics, the existence of several layers of canopy (including understorey), and shadowing within and between crowns. To overcome this problem, an algorithm for delineating tree crowns has been developed using eCognition Expert and hyperspectral Compact Airborne Spectrographic Imager (CASI-2) data acquired over a forested landscape near Injune, central east Queensland, Australia. The algorithm has six components: 1) the differentiation of forest, non-forest and understorey; 2) initial segmentation of the forest area and allocation of segments (objects) to larger objects associated with forest spectral types (FSTs); 3) initial identification of object maxima as seeds within these larger objects and their expansion to the edges of crowns or clusters of crowns; 4) subsequent classification-based separation of the resulting objects into crown or cluster classes; 5) further iterative splitting of the cluster classes to delineate more crowns; and 6) identification and subsequent merging of oversplit objects into crowns or clusters. In forests with a high density of individuals (e.g., regrowth), objects associated with tree clusters rather than crowns are delineated and local maxima counted to approximate density. With reference to field data, the delineation process provided accuracies > ∼70% (range 48-88%) for individuals or clusters of trees of the same species with diameter at breast height (DBH) exceeding 10 cm (senescent and dead trees excluded), with lower accuracies associated with dense stands containing several canopy layers, as many trees were obscured from the view of the CASI sensor. Although developed using 1-m spatial resolution CASI data acquired over Australian forests, the algorithm has application elsewhere and is currently being considered for integration into the Definiens product portfolio for use by the wider community.     

Assessing changes of forest area and shrub encroachment in a mire ecosystem using digital surface models and CIR aerial images

This paper presents an approach to assess increase and decrease (2002–1997) of forest area and other wooded areas in a mire biotope in the Pre-alpine zone of Central Switzerland using logistic regression models and airborne remote sensing data (CIR aerial images, DSM derived from them). The present study was carried out in the framework of the Swiss Mire Protection Program, where increase and decrease of forest areas are key issues. In a first step, automatic DSMs were generated using an image matching approach from CIR aerial images of 1997 and 2002. In a second step, the DSMs were co-registered and normalized using LiDAR data. Tree layers from both years of various levels of detail were then generated combining canopy covers derived from normalized DSMs with a multi-resolution segmentation and a fuzzy classification. On the basis of these tree layers, fractional tree/shrub covers were calculated using explanatory variables derived from these DSMs only. Bias was estimated by analysing the distribution of the fractional model differences. The corrected models reveal a decrease of tree/shrub probability which indicates a decrease of forest and other wooded areas between 1997 and 2002. The models also indicate real shrub encroachment in open mire. The detection of shrub encroachment may be helpful for selective logging purposes for sustainable mire habitat management. The study stresses the importance of high-resolution and high-quality DSMs and highlights the potential of fractional covers for ecological modeling.     

Automated tree recognition in old growth conifer stands with high resolution digital imagery

Automated individual tree isolation and species determination with high resolution multispectral imagery is becoming a viable forest survey tool. Application to old growth conifer forests offer unique technical issues including high variability in tree size and dominance, strong tree shading and obscuration, and varying ages and states of health. The capabilities of individual tree analysis are examined with two acquisitions of 70-cm resolution CASI imagery over a hemlock, amabilis fir, and cedar dominated old growth site on the west coast of Canada. Trees were delineated using the valley following approach of the Individual Tree Crown (ITC) software suite, classified according to species (hemlock, amabilis fir, and cedar) using object-based spectral classification and tested on a tree-for-tree basis against data derived from ground plots.Tree-for-tree isolation and species classification accuracy assessment, although often sobering, is important for portraying the overall effectiveness of species composition mapping using single tree approaches. This accuracy considers not only how well each tree is classified, but how well each automated isolation represents a true tree and its species. Omissions and commissions need to be included in overall species accuracy assessment. A structure of rules for defining isolation accuracy is developed and used. An example is given of a new approach to accuracy analysis incorporating both isolation and classification results (automated tree recognition) and the issues this presents.The automated tree isolation performed well on those trees that could be visually identified on the imagery using ground measured stem maps (approximately 50-60% of trees had a good match between manual and automated delineations). There were few omissions. Commission errors, i.e., automated isolations not associated with a delineated ground reference tree, were a problem (25%) usually associated with spurious higher intensity areas within shaded regions, which get confused in the process of trying to isolate shaded trees. Difficulty in classifying species was caused by: variability of the spectral signatures of the old growth trees within the same species, tree health, and trees partly or fully shaded by other trees. To accommodate this variability, several signatures were used to represent each species including shaded trees. Species could not be determined for the shaded cases or for the unhealthy trees and therefore two combined classes, a shaded class and unhealthy class with all species included, were used for further analysis. Species classification accuracy of the trees for which there was a good automated isolation match was 72%, 60%, and 40% for the non-shaded healthy hemlock, balsam, and cedar trees for the 1996 data. Equivalent accuracy for the 1998 imagery was 59% for hemlock, 80% for balsam, with only a few cedar trees being well isolated. If all other matches were considered an error in classification, species classification was poor (approximately 45% for balsam and hemlock, 25% for cedar). However, species classification accuracies incorporating the good isolation matches and trees for which there was a match of an isolations and reference tree but the match was not considered good were moderate (60%, 57%, and 38% for hemlock, balsam, and cedar from the 1996 data; 62%, 61%, and 89%, respectively, for the 1998 imagery).Automated tree isolation and species classification of old growth forests is difficult, but nevertheless in this example useful results were obtained.     

A Landsat time series approach to characterize bark beetle and defoliator impacts on tree mortality and surface fuels in conifer forests

Insects are important forest disturbance agents, and mapping their effects on tree mortality and surface fuels represents a critical research challenge. Although various remote sensing approaches have been developed to monitor insect impacts, most studies have focused on single insect agents or single locations and have not related observed changes to ground-based measurements. This study presents a remote sensing framework to (1) characterize spectral trajectories associated with insect activity of varying duration and severity and (2) relate those trajectories to ground-based measurements of tree mortality and surface fuels in the Cascade Range, Oregon, USA. We leverage a Landsat time series change detection algorithm (LandTrendr), annual forest health aerial detection surveys (ADS), and field measurements to investigate two study landscapes broadly applicable to conifer forests and dominant insect agents of western North America. We distributed 38 plots across multiple forest types (ranging from mesic mixed-conifer to xeric lodgepole pine) and insect agents (defoliator [western spruce budworm] and bark beetle [mountain pine beetle]). Insect effects were evident in the Landsat time series as combinations of both short- and long-duration changes in the Normalized Burn Ratio spectral index. Western spruce budworm trajectories appeared to show a consistent temporal evolution of long-duration spectral decline (loss of vegetation) followed by recovery, whereas mountain pine beetle plots exhibited both short- and long-duration spectral declines and variable recovery rates. Although temporally variable, insect-affected stands generally conformed to four spectral trajectories: short-duration decline then recovery, short- then long-duration decline, long-duration decline, long-duration decline then recovery. When comparing remote sensing data with field measurements of insect impacts, we found that spectral changes were related to cover-based estimates (tree basal area mortality [R²_adj = 0.40, F_1,34 = 24.76, P < 0.0001] and down coarse woody detritus [R²_adj = 0.29, F_1,32 = 14.72, P = 0.0006]). In contrast, ADS changes were related to count-based estimates (e.g., ADS mortality from mountain pine beetle positively correlated with ground-based counts [R²_adj = 0.37, F_1,22 = 14.71, P = 0.0009]). Fine woody detritus and forest floor depth were not well correlated with Landsat- or aerial survey-based change metrics. By characterizing several distinct temporal manifestations of insect activity in conifer forests, this study demonstrates the utility of insect mapping methods that capture a wide range of spectral trajectories. This study also confirms the key role that satellite imagery can play in understanding the interactions among insects, fuels, and wildfire.     

安徽省利辛县平原区人工林树种分类研究

快速准确地绘制平原区人工林树种分布对研究人工林的生态水文和社会经济效益具有重要的意义。将资源3号（ZY-3）全色波段分别同ZY-3多光谱、哨兵2号多光谱进行融合,在图像分割基础上提取变量,采用分层优化变量组合的随机森林分类方法对安徽省利辛县人工林树种进行分类,并与分类回归树和随机森林相比较。结果表明：利用分层分类方法,平原区的人工林树种分类精度可以达到92%以上;基于哨兵2号和ZY-3融合的光谱特征变量分类精度比ZY-3数据本身的融合提高了2.49%～2.91%;而分别加入纹理变量后,分层分类方法大幅度提高了树种分类精度。因此,基于高分辨率遥感数据的光谱和纹理特征,采用分层分类方法,可以有效提高平原区人工林树种的分类精度。     

Identifying species of individual trees using airborne laser scanner

Individual trees can be detected using high-density airborne laser scanner data. Also, variables characterizing the detected trees such as tree height, crown area, and crown base height can be measured. The Scandinavian boreal forest mainly consists of Norway spruce (Picea abies L. Karst.), Scots pine (Pinus sylvestris L.), and deciduous trees. It is possible to separate coniferous from deciduous trees using near-infrared images, but pine and spruce give similar spectral signals. Airborne laser scanning, measuring structure and shape of tree crowns could be used for discriminating between spruce and pine. The aim of this study was to test classification of Scots pine versus Norway spruce on an individual tree level using features extracted from airborne laser scanning data. Field measurements were used for training and validation of the classification. The position of all trees on 12 rectangular plots (50×20 m²) were measured in field and tree species was recorded. The dominating species (>80%) was Norway spruce for six of the plots and Scots pine for six plots. The field-measured trees were automatically linked to the laser-measured trees. The laser-detected trees on each plot were classified into species classes using all laser-detected trees on the other plots as training data. The portion correctly classified trees on all plots was 95%. Crown base height estimations of individual trees were also evaluated (r=0.84). The classification results in this study demonstrate the ability to discriminate between pine and spruce using laser data. This method could be applied in an operational context. In the first step, a segmentation of individual tree crowns is performed using laser data. In the second step, tree species classification is performed based on the segments. Methods could be developed in the future that combine laser data with digital near-infrared photographs for classification with the three classes: Norway spruce, Scots pine, and deciduous trees.     

Classifying species of individual trees by intensity and structure features derived from airborne laser scanner data

The objective of this study was to identify candidate features derived from airborne laser scanner (ALS) data suitable to discriminate between coniferous and deciduous tree species. Both features related to structure and intensity were considered. The study was conducted on 197 Norway spruce and 180 birch trees (leaves on conditions) in a boreal forest reserve in Norway. The ALS sensor used was capable of recording multiple echoes. The point density was 6.6 m^− 2. Laser echoes located within the vertical projection of the tree crowns, which were assumed to be circular and defined according to field measurements, were attributed to three categories: “first echoes of many”, “single echoes”, or “last echoes of many echoes”. They were denoted FIRST, SINGLE, and LAST, respectively. In tree species classification using ALS data features should be independent of tree heights. We found that many features were dependent on tree height and that this dependency influenced selection of candidate features. When we accounted for this dependency, it was revealed that FIRST and SINGLE echoes were located higher and LAST echoes lower in the birch crowns than in spruce crowns. The intensity features of the FIRST echoes differed more between species than corresponding features of the other echo categories. For the FIRST echoes the intensity values tended to be higher for birch than spruce. When using the various features for species classification, maximum overall classification accuracies of 77% and 73% were obtained for structural and intensity features, respectively. Combining candidate features related to structure and intensity resulted in an overall classification accuracy of 88%.     

Combining GF-2 and RapidEye satellite data for mapping mangrove species using ensemble machine-learning methods

ABSTRACT

Mangrove forests are important constitutions for sustainable development of coastal ecosystems, and they are often mapped and monitored with remote sensing approaches. Satellite images allow detailed studies of the distribution and composition of mangrove forests, and therefore facilitate the management and conservation of the ecosystems. The combination of multiple types of satellite images with different spatial and spectral resolutions is helpful in mangrove forests extraction and mangrove species discrimination as it reduces sampling workload and increases classification accuracies. In this study, the 1.0-m-resolution Gaofen-2 (GF-2) and the 5.0-m-resolution RapidEye-4 (RE-4) satellite images, acquired in February 2017 and November 2016 respectively, were used with ensemble machine-learning and object-oriented methods for mangroves mapping at both the community and species levels of the Qi’ao Island, Zhuhai, China. First, the mangroves on the island were segmented from the GF-2 image on a large scale, and then they were extracted combining with their digital elevation model (DEM) data. Second, the GF-2 image was further processed on a fine scale, in which object-oriented features from both the GF-2 and RE-4 images were extracted for each mangrove species. Third, it is followed by the mangrove species classification process which involves three ensemble machine-learning methods: the adaptive boosting (AdaBoost), the random forest (RF) and the rotation forest (RoF). These three methods employed a classification and regression tree (CART) as the base classifier. The results show that the overall accuracy (OA) of mangrove area extraction on the Qi’ao Island with the auxiliary data, DEM, achieves 98.76% (Kappa coefficient (κ) = 0.9289). The features extracted by the GF-2 and RE-4 images were shown to be beneficial for mangrove species discrimination. A maximum improvement in the OA of approximately 8% and a κκ of approximately 0.10 were achieved when employing RoF (OA = 92.01%, κ = 0.9016). Ensemble-learning methods can significantly improve the classification accuracy of CART, and the use of a bagging scheme (RF and RoF) is shown as a better way to map mangrove species than adaptive boosting (AdaBoost). In addition, RoF performed well in mangrove species classification but it was not as robust as the RF, whose average OA and κκ were 80.59% and 0.7608, respectively, while the RoF’s were 77.45% and 0.7214, respectively, in the 10-fold cross-validation.     

Invasive species detection in Hawaiian rainforests using airborne imaging spectroscopy and LiDAR

Remote sensing of invasive species is a critical component of conservation and management efforts, but reliable methods for the detection of invaders have not been widely established. In Hawaiian forests, we recently found that invasive trees often have hyperspectral signatures unique from that of native trees, but mapping based on spectral reflectance properties alone is confounded by issues of canopy senescence and mortality, intra- and inter-canopy gaps and shadowing, and terrain variability. We deployed a new hybrid airborne system combining the Carnegie Airborne Observatory (CAO) small-footprint light detection and ranging (LiDAR) system with the Airborne Visible and Infrared Imaging Spectrometer (AVIRIS) to map the three-dimensional spectral and structural properties of Hawaiian forests. The CAO-AVIRIS systems and data were fully integrated using in-flight and post-flight fusion techniques, facilitating an analysis of forest canopy properties to determine the presence and abundance of three highly invasive tree species in Hawaiian rainforests.

The LiDAR sub-system was used to model forest canopy height and top-of-canopy surfaces; these structural data allowed for automated masking of forest gaps, intra- and inter-canopy shadows, and minimum vegetation height in the AVIRIS images. The remaining sunlit canopy spectra were analyzed using spatially-constrained spectral mixture analysis. The results of the combined LiDAR-spectroscopic analysis highlighted the location and fractional abundance of each invasive tree species throughout the rainforest sites. Field validation studies demonstrated < 6.8% and < 18.6% error rates in the detection of invasive tree species at  7 m² and  2 m² minimum canopy cover thresholds. Our results show that full integration of imaging spectroscopy and LiDAR measurements provides enormous flexibility and analytical potential for studies of terrestrial ecosystems and the species contained within them.     

结合LiDAR单木分割和高光谱特征提取的城市森林树种分类

基于多源遥感数据的城市森林树种分类对城市森林资源调查、森林健康状况评价及科学化管理具有重要意义。以江苏省常熟市虞山国家森林公园内的典型城市森林树种为研究对象,利用同期获取的机载激光雷达(LiDAR)和高光谱数据,针对5个典型城市森林树种进行了树种分类的研究。首先,基于点云距离判断单木分割方法进行单木位置和冠幅提取,并借助实测数据和目视解译结果进行精度验证;然后,在冠幅内提取4组高光谱特征变量,并借助随机森林模型对特征变量进行重要性分析;最后,筛选出重要性高的特征变量进行2个级别的树种分类并借助混淆矩阵进行验证评价。结果表明:基于点云距离判断分割方法的单木位置提取精度较高(探测率为85.7%,准确率为96%,总体精度为90.9%);利用全部特征变量(n=36)对5个树种进行分类,分类的总体精度达到了84%,Kappa系数为0.80;利用优选特征变量(n=9)进行分类,总体精度达83%,Kappa系数为0.79;利用全部特征变量(n=36)对两种森林类型进行分类,分类的总体精度达91.3%,Kappa系数为0.82,其中阔叶树种分类精度为95.6%,针叶树种分类精度为85%;利用优选特征变量(n=9)进行分类,分类的总体精度达90.7%,Kappa系数为0.80,其中阔叶树种分类精度为93.33%,针叶树种分类精度为86.67%。     

Prospects for quantifying structure,floristic composition and species richness of tropical forests

Airborne spectral and light detection and ranging (lidar) sensors have been used to quantify biophysical characteristics of tropical forests. Lidar sensors have provided high-resolution data on forest height, canopy topography, volume, and gap size; and provided estimates on number of strata in a forest, successional status of forests, and above-ground biomass. Spectral sensors have provided data on vegetation types, foliar biochemistry content of forest canopies, tree and canopy phenology, and spectral signatures for selected tree species. A number of advances are theoretically possible with individual and combined spectral and lidar sensors for the study of forest structure, floristic composition and species richness. Delineating individual canopies of over-storey trees with small footprint lidar and discrimination of tree architectural types with waveform distributions is possible and would provide scientists with a new method to study tropical forest structure. Combined spectral and lidar data can be used to identify selected tree species and identify the successional status of tropical forest fragments in order to rank forest patches by levels of species richness. It should be possible in the near future to quantify selected patterns of tropical forests at a higher resolution than can currently be undertaken in the field or from space.     

Continuous wavelet analysis for the detection of green attack damage due to mountain pine beetle infestation

Mountain pine beetle (Dendroctonus ponderosae Hopkins) is the most destructive insect infesting mature pine forests in North America and has devastated millions of hectares of forest in western Canada. Past studies have demonstrated the use of multispectral imagery for remote identification and mapping of visible or red attack damage in forests. This study aims to detect pre-visual or green attack damage in lodgepole pine needles by means of hyperspectral measurements, particularly via continuous wavelet analysis. Field measurements of lodgepole pine stands were conducted at two sites located northwest of Edmonton, Alberta, Canada. In June and August of 2007, reflectance spectra (350-2500 nm) were collected for 16 pairs of trees. Each of the 16 tree pairs included one control tree (healthy), and one stressed tree (girdled to simulate the effects of beetle infestation). In addition, during the period of June through October 2008, spectra were collected from 15 pairs of control- and beetle-infested trees. Spectra derived from these 31 tree pairs were subjected to a continuous wavelet transform, generating a scalogram that compiles the wavelet power as a function of wavelength location and scale of decomposition. Linear relationships were then explored between the wavelet scalograms and chemical properties or class labels (control and non-control) of the sample populations in order to isolate the most useful distinguishing spectral features that related to infested or girdled trees vs. control trees.A deficit in water content is observed in infested trees while an additional deficit in chlorophyll content is seen for girdled trees. The measurable water deficit of infested and girdled tree samples was detectable from the wavelet analysis of the reflectance spectra providing a novel method for the detection of green attack. The spectral features distinguishing control and infested trees are predominantly located between 950 and 1390 nm from scales 1 to 8. Of those, five features between 1318 to 1322 nm at scale 7 are consistently found in the July and August 2008 datasets. These features are located at longer wavelengths than those investigated in previous studies (below 1100 nm) and provide new insights into the potential remote detection of green attack. Spectral features that distinguish control and girdled trees were mostly observed between 1550 and 2370 nm from scales 1 to 5. The differing response of girdled and infested trees appears to indicate that the girdling process does not provide a perfect simulation of the effects caused by beetle infestation.It remains to be determined if the location of the 1318-1322 nm features, near the edge of a strong atmospheric water absorption band, will be sufficiently separable for use in airborne detection of green attack. A plot comparing needle water content and wavelet power at 1320 nm reveals considerable overlap between data derived from both infested and control samples, though the groups are statistically separable. This obstacle may preclude a high accuracy separation of healthy and infected single individuals, but establishing threshold identification levels may provide an economical, efficient and expeditious method for discriminating between healthy and infested tree populations.     

Combining high spatial resolution multi-temporal satellite data with leaf-on LiDAR to enhance tree species discrimination at the crown level

ABSTRACT

The long-standing goal of discriminating tree species at the crown-level from high spatial resolution imagery remains challenging. The aim of this study is to evaluate whether combining (a) high spatial resolution multi-temporal images from different phenological periods (spring, summer and autumn), and (b) leaf-on LiDAR height and intensity data can enhance the ability to discriminate the species of individual tree crowns of red oak (Quercus rubra), sugar maple (Acer saccharum), tulip poplar (Liriodendron tulipifera), and black cherry (Prunus serotina) in the Fernow Experimental Forest, West Virginia, USA. We used RandomForest models to measure a loss of classification accuracy caused by iteratively removing from the classification one or more groups from six groups of variables: spectral reflectance from all multispectral bands in the (1) spring, (2) summer, and (3) autumn images, (4) vegetation indices derived from the three multispectral datasets, (5) canopy height and intensity from the LiDAR imagery, and (6) texture related variables from the panchromatic and LiDAR datasets. We also used ANOVA and decision tree analyses to elucidate how the multispectral and LiDAR datasets combine to help discriminate tree species based on their unique phenological, spectral, textural, and crown architectural traits. From these results, we conclude that combing high spatial resolution multi-temporal satellite data with LiDAR datasets can enhance the ability to discriminate tree species at the crown level.     

Broadleaf species recognition with in situ hyperspectral data

Timely and accurate identification of tree species by spectral methods is crucial for forest and urban ecological management. In this study, a total of 394 reflectance spectra (between 350 and 2500 nm) from foliage branches or canopy of 11 important urban forest broadleaf species were measured in the City of Tampa, Florida, USA with a spectrometer. The 11 species include American elm (Ulmus americana), bluejack oak (Quercus incana), crape myrtle (Lagerstroemia indica), laurel oak (Q. laurifolia), live oak (Q. virginiana), southern magnolia (Magnolia grandiflora), persimmon (Diospyros virginiana), red maple (Acer rubrum), sand live oak (Q. geminata), American sycamore (Platanus occidentalis), and turkey oak (Q. laevis). A total of 46 spectral variables, including normalized spectra, derivative spectra, spectral vegetation indices, spectral position variables, and spectral absorption features were extracted and analysed from the in situ hyperspectral measurements. Two classification algorithms were used to identify the 11 broadleaf species: a nonlinear artificial neural network (ANN) and a linear discriminant analysis (LDA). An analysis of variance (ANOVA) indicates that the 30 selected spectral variables are effective to differentiate the 11 species. The 30 selected spectral variables account for water absorption features at 970, 1200, and 1750 nm and reflect characteristics of pigments and other biochemicals in tree leaves, especially variability of chlorophyll content in leaves. The experimental results indicate that both classification algorithms (ANN and LDA) have produced acceptable accuracies (overall accuracy from 86.3% to 87.8%, kappa from 0.83 to 0.87) and have a similar performance for classifying the 11 broadleaf species with input of the 30 selected spectral variables. The preliminary results of identifying the 11 species with the in situ hyperspectral data imply that with current remote sensing techniques, including high spatial and spectral resolution data, it is still difficult but possible to identify similar species to such 11 broadleaf species with an acceptable accuracy.     

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 hyperspectral remote sensing to detect and quantify southeastern pine senescence effects in red-cockaded woodpecker (Picoides borealis) habitat

Conservation of threatened and endangered species requires maintenance of critical habitat. The red-cockaded woodpecker Picoides borealis (RCW) is a threatened bird species, endemic to the mixed conifer forests of the southeastern United States. RCW nests and forages preferentially in mature longleaf pine Pinus palustris, but also uses mature loblolly pine Pinus taeda and shortleaf pine Pinus echinata forests. In the last century, the extent of mature pine forests has been greatly reduced by logging. The RCW, in contrast to other woodpeckers, excavates nest cavities in living trees and senescence symptoms (year round leaf chlorosis and leaf mortality) have been observed in mature pine stands across the southeast. Widespread mortality of the mature pine forests would threaten the long-term survival of the RCW. We used airborne hyperspectral data across a portion of Ft. Benning Military Installation, Georgia, U.S.A., to determine if senescent trees can be identified and mapped and assess the likely persistence of mature pines in the RCW habitat. Univariate analysis of variance showed good separation between asymptomatic, senesced and dead physiological conditions with asymptomatic trees having significantly higher reflectance for all bands in the wavelength range between 0.719 and 1.1676 µm, senescent trees having significantly lower reflectance for bands in the range between 1.1927 and 1.3122 µm, and dead trees having significantly higher reflectance for bands in the range between 1.8151 and 1.9471 µm. Classification and Regression Tree (CART) models achieved correct classification rates and kappa statistics above 70%. CART models selected information from wavelength regions similar to those identified from the ANOVA, which likely explains their performance. Our aggregated CART model of tree senescence estimated that 141.4 ha (3%) of the study area is affected. RCW nests occurred in areas with significantly higher tree cover, and trees within foraging and home ranges did not have significantly more senescence than areas without RCW. These results indicate that although tree senescence is widespread, mortality is yet to significantly affect RCW habitat. Results and analysis of critical habitat similar to those exemplified in this study can extend our knowledge about the stressors of these important and imperiled components of biodiversity.     

Characterizing temperate forest structural and spectral diversity with Hyperion EO-1 data

Forest structural diversity can serve as an important indicator of biodiversity. The relationship between spaceborne hyperspectral remotely sensed data and several measures of forest structure was explored over a 625 km² coastal temperate forest landscape on Vancouver Island, British Columbia, Canada. Thirteen Hyperion bands were selected for analysis based on the documented and hypothesized importance of various spectral wavelengths to forest characterization. To aid in understanding spectral trends, measures of forest stand structural diversity (projected age, projected height, and stand species composition complexity) were derived from forest inventory data. The spectral distance between the stand mean and standard deviation of reflectance and related expectations from global equivalents for each of the 13 bands were used to relate measures of spectral diversity (N = 801 forest inventory stands).Canonical correlation analysis was then used to determine the independent and shared relationships between these selected measures of forest structural diversity (dependent variables) and spectral diversity (independent variables). The dependent variables that were most strongly correlated with the first canonical variate were projected age and projected height, with canonical loadings of 0.973 and 0.979, respectively. In contrast, stand species composition complexity had a weak, negative correlation with spectral diversity (canonical loading = − 0.025). The wavelengths contributing the most to the canonical function included: 681-740 nm, 551-680 nm, and 1401-2400 nm. There have been few studies that attempt to directly link spectral and species diversity in temperate forest environments. From this initial investigation, we posit that the complex spectral response of coastal temperate forests may confound efforts to directly link spectral and species diversity across a range of site conditions.Our results, which are constrained by the spectral and spatial resolution of the data used, our target environment, and the metrics selected for measuring forest structure, suggest that attributes that characterize forest structural conditions may have a more meaningful relationship with spectral diversity than measures of species diversity alone, and that future studies in coastal temperate forests that seek to link spectral diversity with biodiversity should include measures of forest structural diversity, in addition to measures of species diversity.     

Integrating Landsat TM and SRTM-DEM derived variables with decision trees for habitat classification and change detection in complex neotropical environments

Remotely sensed images and processing techniques are a primary tool for mapping changes in tropical forest types important to biodiversity and environmental assessment. Detailed land cover data are lacking for most wet tropical areas that present special challenges for data collection. For this study, we utilize decision tree (DT) classifiers to map 32 land cover types of varying ecological and economic importance over an 8000 km² study area and biological corridor in Costa Rica. We assess multivariate QUEST DTs with unbiased classification rules and linear discriminant node models for integrated vegetation mapping and change detection. Predictor variables essential to accurate land cover classification were selected using importance indices statistically derived with classification trees. A set of 35 variables from SRTM-DEM terrain variables, WorldClim grids, and Landsat TM bands were assessed.

Of the techniques examined, QUEST trees were most accurate by integrating a set of 12 spectral and geospatial predictor variables for image subsets with an overall cross-validation accuracy of 93% ± 3.3%. Accuracy with spectral variables alone was low (69% ± 3.3%). A random selection of training and test set pixels for the entire landscape yielded lower classification accuracy (81%) demonstrating a positive effect of image subsets on accuracy. A post-classification change comparison between 1986 and 2001 reveals that two lowland forest types of differing tree species composition are vulnerable to agricultural conversion. Tree plantations and successional vegetation added forest cover over the 15-year time period, but sometimes replaced native forest types, reducing floristic diversity. Decision tree classifiers, capable of combining data from multiple sources, are highly adaptable for mapping and monitoring land cover changes important to biodiversity and other ecosystem services in complex wet tropical environments.