Tree Crown Level Research Articles

A novel linear spectral unmixing-based method for tree decline monitoring by fusing UAV-RGB and optical space-borne data

ABSTRACT Remote sensing-assisted monitoring of forest health entails methods that can provide up-to-date and accurate information on decline and mortality of individual trees, while maintaining time and cost efficiency. However, the trade-off of applying consumer-grade UAV-RGB data as the most affordable and accessible data source at the catchment level is constrained by its poor spectral information content. We developed a method based on the fusion of UAV-RGB data with space-borne Sentinel-2 Multispectral Instrument (MSI) at the level of tree crowns, with the specific target of supporting studies on semi-arid tree decline. We applied linear spectral unmixing (Spectral Unmixing-Based data Fusion method, LSUBF) by considering a limited number of endmembers and calculating the abundances (fractional covers) from the UAV data, and evaluated the results by high-resolution MSI space-borne data including SPOT-6 (1.5 m spatial resolution) and PlanetScope (3 m spatial resolution). This method suggested an increase in the coefficient of determination of the applied generalized additive model for decline severity estimation at tree crown level from 0.61 to 0.69, while it was improved from 0.70 to 0.91 when fitting a non-parametric random forest model. The results of sensitivity analysis demonstrated that the additional spectral information obtained from the proposed method results in higher accuracy in estimating decline severity. We suggest this method as a cost-effective alternative to monitor periodical tree decline, in particular across semi-arid ecosystems.

Evaluating Predictive Models of Tree Foliar Moisture Content for Application to Multispectral UAS Data: A Laboratory Study

Water supply is a critical component of tree physiological health, influencing a tree’s photosynthetic activity and resilience to disturbances. The climatic regions of the western United States are particularly at risk from increasing drought, fire, and pest interactions. Existing methods for quantifying drought stress and a tree’s relative resilience against disturbances mostly use moderate-scale (20–30 m) multispectral satellite sensor data. However, tree water status (i.e., water stress) quantification using sensors like Landsat and Sentinel are error-prone given that the spectral reflectance of pixels are a mixture of the dominant tree canopy, surface vegetation, and soil. Uncrewed aerial systems (UAS) equipped with multispectral sensors could potentially provide individual tree water status. In this study, we assess whether the simulated band equivalent reflectance (BER) of a common UAS optical multispectral sensor can accurately quantify the foliar moisture content and water stress status of individual trees. To achieve this, water was withheld from groups of Douglas-fir and western white pine saplings. Then, measurements of each sapling’s foliar moisture content (FMC) and spectral reflectance were converted to BER of a consumer-grade multispectral camera commonly used on UAS. These bands were used in two classification models and three regression models to develop a best-performing FMC model for predicting either the water status (i.e., drought-stressed or healthy) or the foliar moisture content of each sapling, respectively. Our top-performing models were a logistic regression classification and a multiple linear regression which achieved a classification accuracy of 96.55% and an r2 of 82.62, respectively. These FMC models could provide an important tool for investigating tree crown level water stress, as well as drought interactions with other disturbances, and provide land managers with a vital indicator of tree resilience.

Pollen limitation failing reproductive success in selected animal pollinated trees of tropical moist deciduous forest of north-eastern hill region, India

Abstract The aim of this study was to estimate reproductive effort and success in tropical trees and to examine the effect of pollen limitation on reproductive success. Pollen limitation was assessed through pollen supplementation experiment to contrast the open pollination treatment. The taxa selected were Bombax ceiba, Erythrina stricta (ornithophilous trees), Lagerstroemia speciosa, Mesua ferrea and Schima wallichii (entomophilous trees). Index of pollen limitation was highest in Bombax ceiba and Erythrina stricta (both self-incompatible species). The remaining three species were partially self-incompatible with favouring selfing in Lagerstroemia speciosa and Mesua ferrea and supporting outcrossing in Schima wallichii. Therefore, the high index of pollen limitation in Bombax ceiba and Erythrina stricta might be due to the effect of either lacking quality pollen or lacking bird pollinators. All five species produce a large amount of pollen at individual tree level in the order of 108 (Erythrina stricta) to 1010 (Mesua ferrea). Fruit and seed set following pollen supplementation were higher than the open pollination (as control) in all studied species. Pollen limitation in this study is likely associated with the effectiveness of pollinator and their frequency, as all the studied species had produced ample pollen at tree crown level which ultimately leads to pollinator resource limitation in tropical trees.

The Use of UAV-Acquired Multiband Images for Detecting Rockfall-Induced Injuries at Tree Crown Level

In this paper, we present an identification of rockfall-injured trees based on multiband images obtained by an unmanned aerial vehicle (UAV). A survey with a multispectral camera was performed on three rockfall sites with versatile tree species (Fagus sylvatica L., Larix decidua Mill., Pinus sylvestris L., Picea abies (L.) Karsten, and Abies alba Mill.) and with different characterizations of rockfalls and rockfall-induced injuries. At one site, rockfall injuries were induced in the same year as the survey. At the second site, they were induced one year after the initial injuries, and at the third site, they were induced six years after the first injuries. At one site, surveys were performed three years in a row. Multiband images were used to extract different vegetation indices (VIs) at the tree crown level and were further studied to see which VIs can identify the injured trees and how successfully. A total of 14 VIs were considered, including individual multispectral bands (green, red, red edge, and near-infrared) by using regression models to differentiate between the injured and uninjured groups for a single year and for three consecutive years. The same model was also used for VI differentiations among the recorded injury groups and size of the injuries. The identification of injured trees based on VIs was possible at the sites where rockfall injuries were induced at least one year before the UAV survey, and they could still be identifiable six years after the initial injuries. At the site where injuries were induced only four months before the UAV survey, the identification of injured trees was not possible. VIs that could explain the largest variability (R2 > 0.3) between injured and uninjured trees were: inverse ratio index (IRVI), green–red vegetation index (GRVI), normalized difference vegetation index (NDVI), normalized ratio index (NRVI), and ratio vegetation index (RVI). RVI was the most successful, explaining 40% of the variance at two sites. R2 values only increased by a few percentages (up to 10%) when the VIs of injured trees were observed over a period of three years and mostly did not change significantly, thus not indicating if the vitality of the trees increased or decreased. Differentiation among the injured groups did not show promising results, while, on the other hand, there was a strong correlation between the VI values (RVI) and the size of the injury according to the basal area of the trees (so-called injury index). Both in the case of broadleaves and conifers at two sites, the R2 achieved a value of 0.82. The presented results indicate that the UAV-acquired multiband images at the tree crown level can be used for surveying rockfall protection forests in order to monitor their vitality, which is crucial for maintaining the protective effect through time and space.

Mapping a European Spruce Bark Beetle Outbreak Using Sentinel-2 Remote Sensing Data

Insect outbreaks affect forests, causing the deaths of trees and high economic loss. In this study, we explored the detection of European spruce bark beetle (Ips typographus, L.) outbreaks at the individual tree crown level using multispectral satellite images. Moreover, we explored the possibility of tracking the progression of the outbreak over time using multitemporal data. Sentinel-2 data acquired during the summer of 2020 over a bark beetle–infested area in the Italian Alps were used for the mapping and tracking over time, while airborne lidar data were used to automatically detect the individual tree crowns and to classify tree species. Mapping and tracking of the outbreak were carried out using a support vector machine classifier with input vegetation indices extracted from the multispectral data. The results showed that it was possible to detect two stages of the outbreak (i.e., early, and late) with an overall accuracy of 83.4%. Moreover, we showed how it is technically possible to track the evolution of the outbreak in an almost bi-weekly period at the level of the individual tree crowns. The outcomes of this paper are useful from both a management and ecological perspective: it allows forest managers to map a bark beetle outbreak at different stages with a high spatial accuracy, and the maps describing the evolution of the outbreak could be used in further studies related to the behavior of bark beetles.

Detection of heartwood rot in Norway spruce trees with lidar and multi-temporal satellite data

Norway spruce pathogenic fungi causing root, butt and stem rot represent a substantial problem for the forest sector in many countries. Early detection of rot presence is important for efficient management of the forest resources but due to its nature, which does not generate evident exterior signs, it is very difficult to detect without invasive measurements. Remote sensing has been widely used to monitor forest health status in relation to many pathogens and infestations. In particular, multi-temporal remotely sensed data have shown to be useful in detecting degenerative diseases. In this study, we explored the possibility of using multi-temporal and multi-spectral satellite data to detect rot presence in Norway spruce trees in Norway. Images with four bands were acquired by the Dove satellite constellation with a spatial resolution of 3 m, ranging over three years from June 2017 to September 2019. Field data were collected in 2019–2020 by a harvester during the logging: 16163 trees were recorded, classified in terms of species and presence of rot at the stump and automatically geo-located. The analysis was carried out at individual tree crown (ITC) level, and ITCs were delineated using lidar data. ITCs were classified as healthy, infested and other species using a weighted Support Vector Machine. The results showed an underestimation of the rot presence (balanced accuracy of 56.3%, producer’s accuracies of 64.3 and 48.4% and user’s accuracies of 81.0% and 32.7% respectively for healthy and rot ITCs). The method can be used to provide a tentative map of the rot presence to guide more detailed assessments in field and harvesting activities.

Detecting Tree Species Effects on Forest Canopy Temperatures with Thermal Remote Sensing: The Role of Spatial Resolution

Canopy temperatures are important for understanding tree physiology, ecology, and their cooling potential, which provides a valuable ecosystem service, especially in urban environments. Linkages between tree species composition in forest stands and air temperatures remain challenging to quantify, as the establishment and maintenance of onsite sensor networks is time-consuming and costly. Remotely-sensed land surface temperature (LST) observations can potentially acquire spatially distributed crown temperature data more efficiently. We analyzed how tree species modify canopy air temperature at an urban floodplain forest (Leipzig, Germany) site equipped with a detailed onsite sensor network, and explored whether mono-temporal thermal remote sensing observations (August, 2016) at different spatial scales could be used to model air temperatures at the tree crown level. Based on the sensor-network data, we found interspecific differences in summer air temperature to vary temporally and spatially, with mean differences between coldest and warmest tree species of 1 °C, and reaching maxima of up to 4 °C for the upper and lower canopy region. The detectability of species-specific differences in canopy surface temperature was found to be similarly feasible when comparing high-resolution airborne LST data to the airborne LST data aggregated to 30 m pixel size. To realize a spatial resolution of 30 m with regularly acquired data, we found the downscaling of Landsat 8 thermal data to be a valid alternative to airborne data, although detected between-species differences in surface temperature were less expressed. For the modeling of canopy air temperatures, all LST data up to the 30 m level were similarly appropriate. We thus conclude that satellite-derived LST products could be recommended for operational use to detect and monitor tree species effects on temperature regulation at the crown scale.

FUSION OF LIDAR AND HYPERSPECTRAL DATA FOR SEMANTIC SEGMENTATION OF FOREST TREE SPECIES

Abstract. Hyperspectral images (HI) and Light Detection and Ranging (LiDAR) provide high resolution radiometric and geometric information for monitoring forests at individual tree crown (ITC) level. It has many important applications for sustainable forest management, biodiversity assessment and healthy ecosystem preservation. However, the integration of different remote sensing modalities is a challenging task for tree species classification due to different artifacts such as the lighting variability, the topographic effects and the atmospheric conditions of the data acquisition. The characterization of ITC can benefit from the extraction and selection of robust feature descriptors that solve these issues. This paper aims to investigate the integration of feature descriptors from HI and LiDAR by using the intra-set and inter-set feature importance for the semantic segmentation of forest tree species. A fusion methodology is proposed between high-density LiDAR data – (20 pulses m−2) and VNIR HI – (160 bands and 0.80 m spatial resolution) acquired on French temperate forests along an altitude gradient. The proposed scheme has three inputs: the field inventory information, the HI and the LiDAR data. Our approach can be described in nine stages: polygon projection, non-overlapping pixel selection, vegetation and shadow removal, LiDAR feature extraction, height mask, robust PCA (rPCA), feature reduction and classification. The overall accuracy of tree species classification at pixel-level was 68.9% by using random forest (RF) classifier. Our approach showed that 74.0% of trees were correctly assigned overall, by having conifer species such as Norway Spruce (Picea abies) with a producer’s accuracy of 97.4%.

Individual Tree Segmentation Based on Mean Shift and Crown Shape Model for Temperate Forest

Light detection and ranging (LiDAR) provides high-resolution geometric information for monitoring forests at individual tree crown (ITC) level. An important task for ITC delineation is segmentation, and previous studies showed that the adaptive 3-D mean shift (AMS3D) algorithm provides effective results. AMS3D for ITC segmentation has three components for the kernel profile: shape, weight, and size. In this letter, we present an AMS3D approach based on the adaptation of the kernel profile size through an ellipsoid crown shape model. The algorithm parameters are estimated based on allometry equations derived from 22 forest plots in two study sites. After computing the mean shift (MS) vector, we initialize the parameters of the ellipsoid crown shape model to derive the kernel profile size, and further tested two crown shape models for adapting the size of the superellipsoid (SE) kernel profile. These schemes are compared with two other MS algorithms with and without kernel profile size adaptation. We select the best algorithm output per plot based on the maximum F1-score. The ellipsoid crown shape model with a SE kernel profile of n = 1.5 presents the highest recall and the best Jaccard index, especially for conifers.

Individual tree detection and species classification of Amazonian palms using UAV images and deep learning

Information regarding the spatial distribution of palm trees in tropical forests is crucial for commercial exploitation and management. However, spatially continuous knowledge of palms occurrence is scarce and difficult to obtain with conventional approaches such as field inventories. Here, we developed a new method to map Amazonian palm species at the individual tree crown (ITC) level using RGB images acquired by a low-cost unmanned aerial vehicle (UAV). Our approach is based on morphological operations performed in the score maps of palm species derived from a fully convolutional neural network model. We first constructed a labeled dataset by dividing the study area (135 ha within an old-growth Amazon forest) into 28 plots of 250 m × 150 m. Then, we manually outlined all palm trees seen in RGB images with 4 cm pixels. We identified three palm species: Attalea butyracea, Euterpe precatoria and Iriartea deltoidea. We randomly selected 22 plots (80%) for training and six plots (20%) for testing. We changed the plots for training and testing to evaluate the variability in the classification accuracy and assess model generalization. Our method outperformed the average producer’s accuracy of conventional patch-wise semantic segmentation (CSS) in 4.7%. Moreover, our method correctly identified, on average, 34.7 percentage points more ITCs than CSS, which tended to merge trees that are close to each other. The producer’s accuracy of A. butyracea, E. precatoria and I. deltoidea was 78.6 ± 5.5%, 98.6 ± 1.4% and 96.6 ± 3.4%, respectively. Fortunately, one of the most exploited and commercialized palm species in the Amazon (E. precatoria, a.k.a, Açaí) was mapped with the highest classification accuracy. Maps of E. precatoria derived from low-cost UAV systems can support management projects and community-based forest monitoring programs in the Amazon.

Street tree health from space? An evaluation using WorldView-3 data and the Washington D.C. Street Tree Spatial Database

Spatially accurate and timely information on tree health is an essential component of maintaining sustainability in a species-rich urban setting. Our objective was to evaluate the potential of WorldView-3 (WV-3) satellite images from June 11th, July 30th and August 30th, 2017 to detect field-measured health condition classes of 2308 trees within the District of Columbia Department of Transportation’s Street Tree Spatial Database. For each street tree in each image, we measured six vegetation indices (VIs), and find that NDVI1 (defined as the normalized ratio of the red and the first of the near infrared bands) on the July image shows the strongest statistical difference among the VI values of trees classified in the field during 2017 as in good, fair, or poor health condition. This result confirms that high spatial resolution remote sensing images provided the opportunity for a timely tree health assessment at individual tree crown level. Notably, the variability in VI attributable to health condition classes is smaller than the large declines in VIs between the June and August image dates. This greendown phenological pattern occurs similarly for trees in all health condition classes, and is thus an essential consideration when comparing VIs from different years or months for tree health assessment. The tree health condition discrimination was overwhelmed by this greendown phenology and the spectral variability in these species-rich urban settings. Based on these findings, we propose useful strategies of using these high-resolution WV-3 data for street tree health management in other cities.

Application of aerial remote sensing technology for detection of fire blight infected pear trees

Over the last few decades, Fire Blight (FB) has recognized as the most dangerous diseases of apple and pear trees in the world. Timely diagnosis is very important for the detection of this disease. Visual assessment and scouting are usually used for FB detection while these methods are time-consuming and labor-intensive. Remote sensing technology can be an alternative method for visual assessment of plant diseases. So, in this research, the capability of multispectral remote sensing was evaluated for FB disease diagnosis of pear orchards in leaf and tree crown levels. Ground multispectral imaging was carried out of healthy leaves (HEL) from healthy trees and non-symptomatic diseased leaves (NSL) and symptomatic diseased leaves (SDL. Aerial multispectral imagery of trees crown was carried out by unmanned aerial vehicle. Then preprocessing and processing of ground and aerial images were performed. Some vegetation indices were calculated to detect infected leaves. Among the studied indices, SIPI, RDVI, MCARI1, MCARI2, TVI, MTVI1, MTVI2, TCARI, PSRI and ARI indices were appropriate for early detection of FB in leaf level. Support vector machine (SVM) method was used for the detection of infected trees. The overall accuracy of the classification obtained 95.0%. Based on the results, it could be concluded that multispectral imaging in leaf and tree crown levels is a reliable method for the detection of FB infected pear trees spatially in the early stage.

A Weighted SVM-Based Approach to Tree Species Classification at Individual Tree Crown Level Using LiDAR Data

Tree species classification at individual tree crowns (ITCs) level, using remote-sensing data, requires the availability of a sufficient number of reliable reference samples (i.e., training samples) to be used in the learning phase of the classifier. The classification performance of the tree species is mainly affected by two main issues: (i) an imbalanced distribution of the tree species classes, and (ii) the presence of unreliable samples due to field collection errors, coordinate misalignments, and ITCs delineation errors. To address these problems, in this paper, we present a weighted Support Vector Machine (wSVM)-based approach for the detection of tree species at ITC level. The proposed approach initially extracts (i) different weights associated to different classes of tree species, to mitigate the effect of the imbalanced distribution of the classes; and (ii) different weights associated to different training samples according to their importance for the classification problem, to reduce the effect of unreliable samples. Then, in order to exploit different weights in the learning phase of the classifier a wSVM algorithm is used. The features to characterize the tree species at ITC level are extracted from both the elevation and intensity of airborne light detection and ranging (LiDAR) data. Experimental results obtained on two study areas located in the Italian Alps show the effectiveness of the proposed approach.

Prediction of stem diameter and biomass at individual tree crown level with advanced machine learning techniques

Knowledge about the aboveground biomass (AGB) and the diameters at breast height (DBH) distribution can lead to a precise estimation of carbon density and forest structure which can be very important for ecology studies especially for those concerning climate change. In this study, we propose to predict DBH and AGB of individual trees using tree height (H) and crown diameter (CD), and other metrics extracted from airborne laser scanning (ALS) data as input. In the proposed approach, regression methods, such us support vector machine for regression (SVR) and random forests (RF), were used to find a transformation or a transfer function that links the input parameters (H, CD, and other ALS metrics) with the output (DBH and AGB). The developed approach was tested on two datasets collected in southern Norway comprising 3970 and 9467 recorded trees, respectively. The results demonstrate that the developed approach provides better results compared to a state-of-the-art work (based on a linear model with the standard least-squares method) with RMSE equal to 81.4 kg and 92.0 kg, respectively (compared to 94.2 kg and 110.0 kg) for the prediction of AGB, and 5.16 cm and 4.93 cm, respectively (compared to 5.49 cm and 5.30 cm) for DBH.

High spatial resolution monitoring land surface energy, water and CO2 fluxes from an Unmanned Aerial System

High spatial resolution maps of land surface energy, water and CO2 fluxes, e.g. evapotranspiration (ET) and gross primary productivity (GPP), are important for agricultural monitoring, ecosystem and water resources management. However, it is not clear which is the optimal (e.g. coarsest possible) spatial resolution to capture those fluxes accurately. Unmanned Aerial Systems (UAS) can address this by collecting very high spatial resolution (<1 m, VHR) imagery. The objective of this study is to model ET and GPP dynamics using VHR optical and thermal imagery and quantify the influence of the spatial heterogeneity in the flux simulations and validations. The study was conducted at a deciduous willow bioenergy eddy covariance (EC) flux site in Denmark. Flight campaigns were conducted during the growing seasons of 2016 and 2017 with a hexacopter equipped with RGB, multispectral and thermal infrared cameras. A ‘top-down’ modeling approach consisting of the Priestley–Taylor Jet Propulsion Laboratory model and a light use efficiency model sharing the same canopy biophysical constraints was used to estimate ET and GPP. Model outputs were benchmarked by EC flux observations with the source weighted footprint. Our results indicate that our model can well estimate the instantaneous net radiation, ET, GPP, evaporative fraction, light use efficiency and water use efficiency with root-mean-square deviations (RMSD) of 31.6 W·m−2, 41.2 W·m−2, 3.12 μmol·C·m−2·s−1, 0.08, 0.16 g·C·MJ−1 and 0.35 g·C·kg−1, respectively. Further, it is found that using a footprint model to sample different areas of VHR imagery can be a tool to provide better diurnal estimates to benchmark with EC data. Moreover, these VHR maps (0.3 m) allowed us to quantify metrics of spatial heterogeneity by using semivariogram analysis and by aggregating model inputs into different spatial resolutions. For instance, we find that in this site, the aggregation of simulated GPP using the source weighted mean of the EC footprint was about 30% lower in RMSD than using the arithmetic mean of the footprint. This demonstrates the accuracy of the modeled VHR spatial patterns. Nevertheless, we also find that imagery resolution consistent with the canopy size (around 1.5 m in our study) is sufficient to capture the spatial heterogeneity of the fluxes as transpiration and canopy assimilation of CO2 are processes regulated at the tree crown level. Our results highlight the importance of considering the land surface heterogeneity for flux modeling and the source contribution within the EC footprint for model benchmarking at appropriate spatial resolutions.

Individual Tree Crown Segmentation and Classification of 13 Tree Species Using Airborne Hyperspectral Data

Knowledge of the distribution of tree species within a forest is key for multiple economic and ecological applications. This information is traditionally acquired through time-consuming and thereby expensive field work. Our study evaluates the suitability of a visible to near-infrared (VNIR) hyperspectral dataset with a spatial resolution of 0.4 m for the classification of 13 tree species (8 broadleaf, 5 coniferous) on an individual tree crown level in the UNESCO Biosphere Reserve ‘Wienerwald’, a temperate Austrian forest. The study also assesses the automation potential for the delineation of tree crowns using a mean shift segmentation algorithm in order to permit model application over large areas. Object-based Random Forest classification was carried out on variables that were derived from 699 manually delineated as well as automatically segmented reference trees. The models were trained separately for two strata: small and/or conifer stands and high broadleaf forests. The two strata were delineated beforehand using CHM-based tree height and NDVI. The predictor variables encompassed spectral reflectance, vegetation indices, textural metrics and principal components. After feature selection, the overall classification accuracy (OA) of the classification based on manual delineations of the 13 tree species was 91.7% (Cohen’s kappa (κ) = 0.909). The highest user’s and producer’s accuracies were most frequently obtained for Weymouth pine and Scots Pine, while European ash was most often associated with the lowest accuracies. The classification that was based on mean shift segmentation yielded similarly good results (OA = 89.4% κ = 0.883). Based on the automatically segmented trees, the Random Forest models were also applied to the whole study site (1050 ha). The resulting tree map of the study area confirmed a high abundance of European beech (58%) with smaller amounts of oak (6%) and Scots pine (5%). We conclude that highly accurate tree species classifications can be obtained from hyperspectral data covering the visible and near-infrared parts of the electromagnetic spectrum. Our results also indicate a high automation potential of the method, as the results from the automatically segmented tree crowns were similar to those that were obtained for the manually delineated tree crowns.

Drivers of spatial variability in greendown within an oak-hickory forest landscape

Declining near-infrared (NIR) surface reflectance between early and late summer, here termed greendown, is a common, yet poorly understood phenomena in remote sensing time series of temperate deciduous forests. As revealed by phenology analysis of Landsat satellite data, there are strong spatial patterns in the rate of greendown across temperate deciduous forest landscapes, and analyzing these patterns could help advance our understanding of surface reflectance drivers. Within an oak-hickory (Quercus spp. – Carya spp.) forest landscape in western Maryland, USA, we tested how spatial patterns in greendown related to potential drivers at the landscape-, tree crown- and leaf-levels. We found that 50% of the spatial variability in greendown was explained by landscape variables, with greendown particularly higher in locations with higher maximum greenness, more southerly aspects, or locations with greater abundance of white oak (Quercus alba). The importance of species composition as a driver of greendown was supported at the tree crown level, where, relative to three other tree species, white oak exhibited the most consistent trend toward more vertical leaf angles later in the season. At the leaf level, NIR reflectance decreased in productive sites where %N increased, and δ13C decreased, through the season. However, among all sites, there were no consistent seasonal trends in foliar NIR reflectance, and we found no correlation among leaf-level NIR reflectance and satellite-observed greendown. Collectively, these results suggest that the spatial variability of greendown in this oak-hickory forest is most strongly controlled by an interaction of topographic and species compositional drivers operating at the landscape and tree crown levels. We found spatial analysis of greendown to be a useful approach to explore landscape-, tree crown-, and leaf-level controls on surface reflectance, and thereby help translate land surface phenology data into predictions of ecosystem structure and functioning.

Predicting stem diameters and aboveground biomass of individual trees using remote sensing data

Airborne laser scanner (ALS) data and hyperspectral (HS) data have become standard data sources in studies related to forest ecology and environmental mapping. Nowadays it is possible to have combined acquisitions of ALS and HS data, and also to have very high point density ALS data that allows us to study forests at individual tree level. In this paper, a study on the combination of HS and ALS data with models for diameter at breast height (DBH) and aboveground biomass (AGB) prediction at individual tree crown (ITC) level is presented. ALS data were used to delineate ITCs and to estimate height and crown diameter of each ITC, whereas HS data were used to identify the tree species. The proposed approach consists in developing DBH and AGB models using field data of an area and to apply these models to areas with similar characteristics. Two datasets were considered: the first dataset is located in boreal forests and it is composed by three separate study areas (Aurskog-Høland, Hadeland, and Våler); the second dataset is located in temperate forests and it is composed by two separate study areas (Val di Sella, and Pellizzano). Aurskog-Høland and Val di Sella study areas were used only to develop species-specific and non-species specific models for DBH and AGB in the two biomes, while the other study areas were used for validation at plot level with remote sensing data. Local models were also developed using field data and ALS and HS data, and they were compared to the ones developed on Aurskog-Høland and Val di Sella study areas. The results show that the proposed approach provides high accuracies in both biomes, even if problems related to underestimation exists. Predictions with a general non-species specific model developed on one study area did not differ significantly from predictions obtained by using local models

Classification of Tree Species in a Diverse African Agroforestry Landscape Using Imaging Spectroscopy and Laser Scanning

Airborne imaging spectroscopy (IS) and laser scanning (ALS) have been explored widely for tree species classification during the past decades. However, African agroforestry areas, where a few exotic tree species are dominant and many native species occur less frequently, have not yet been studied. Obtaining maps of tree species would provide useful information for the characterization of agroforestry systems and detecting invasive species. Our objective was to study tree species classification in a diverse tropical landscape using IS and ALS data at the tree crown level, with primary interest in the exotic tree species. We performed multiple analyses based on different IS and ALS feature sets, identified important features using feature selection, and evaluated the impact of combining the two data sources. Given that a high number of tree species with limited sample size (499 samples for 31 species) was expected to limit the classification accuracy, we tested different approaches to group the species based on the frequency of their occurrence and Jeffries–Matusita (JM) distance. Surface reflectance at wavelengths between 400–450 nm and 750–800 nm, and height to crown width ratio, were identified as important features. Nonetheless, a selection of minimum noise fraction (MNF) transformed reflectance bands showed superior performance. Support vector machine classifier performed slightly better than the random forest classifier, but the improvement was not statistically significant for the best performing feature set. The highest F1-scores were achieved when each of the species was classified separately against a mixed group of all other species, which makes this approach suitable for invasive species detection. Our results are valuable for organizations working on biodiversity conservation and improving agroforestry practices, as we showed how the non-native Eucalyptus spp., Acacia mearnsii and Grevillea robusta (mean F1-scores 76%, 79% and 89%, respectively) trees can be mapped with good accuracy. We also found a group of six fruit bearing trees using JM distance, which was classified with mean F1-score of 65%. This was a useful finding, as these species could not be classified with acceptable accuracy individually, while they all share common economic and ecological importance.

Assessing the potential of multi-seasonal WorldView-2 imagery for mapping West African agroforestry tree species

High resolution satellite systems enable efficient and detailed mapping of tree cover, with high potential to support both natural resource monitoring and ecological research. This study investigates the capability of multi-seasonal WorldView-2 imagery to map five dominant tree species at the individual tree crown level in a parkland landscape in central Burkina Faso. The Random Forest algorithm is used for object based tree species classification and for assessing the relative importance of WorldView-2 predictors. The classification accuracies from using wet season, dry season and multi-seasonal datasets are compared to gain insights about the optimal timing for image acquisition. The multi-seasonal dataset produced the most accurate classifications, with an overall accuracy (OA) of 83.4%. For classifications based on single date imagery, the dry season (OA=78.4%) proved to be more suitable than the wet season (OA=68.1%). The predictors that contributed most to the classification success were based on the red edge band and visible wavelengths, in particular green and yellow. It was therefore concluded that WorldView-2, with its unique band configuration, represents a suitable data source for tree species mapping in West African parklands. These results are particularly promising when considering the recently launched WorldView-3, which provides data both at higher spatial and spectral resolution, including shortwave infrared bands.