Search Results (10)

High-resolution maps of redwood distributions could enable strategic land management to satisfy diverse conservation goals, but the currently-available maps of redwood distributions are low in spatial resolution and biotic detail. Classification of airborne imaging spectroscopy data provides a potential avenue for mapping redwoods over large areas and with high confidence. We used airborne imaging spectroscopy data collected over three redwood forests by the Carnegie Airborne Observatory, in combination with field training data and application of a gradient boosted regression tree (GBRT) machine learning algorithm, to map the distribution of redwoods at 2-m spatial resolution. Training data collected from the three sites showed that redwoods have spectral signatures distinct from the other common tree species found in redwood forests. We optimized a gradient boosted regression model for high performance and computational efficiency, and the resulting model was demonstrably accurate (81–98% true positive rate and 90–98% overall accuracy) in mapping redwoods in each of the study sites. The resulting maps showed marked variation in redwood abundance (0–70%) within a 1 square kilometer aggregation block, which match the spatial resolution of currently-available redwood distribution maps. Our resulting high-resolution mapping approach will facilitate improved research, conservation, and management of redwood trees in California. Full article

Rapid ‘Ōhi‘a Death (ROD) is a disease aggressively killing large numbers of Metrosideros polymorpha (‘ōhi‘a), a native keystone tree species on Hawaii Island. This loss threatens to deeply alter the biological make-up of this unique island ecosystem. Spatially explicit information about the present and past advancement of the disease is essential for its containment; yet, currently such data are severely lacking. To this end, we used the Carnegie Airborne Observatory to collect Laser-Guided Imaging Spectroscopy data and high-resolution digital imagery across >500,000 ha of Hawaii Island in June–July 2017. We then developed a method to map individual tree crowns matching the symptoms of both active (brown; desiccated ‘ōhi‘a crowns) and past (leafless tree crowns) ROD infection using an ensemble of two distinct machine learning approaches. Employing a very conservative classification scheme for minimizing false-positives, model sensitivity rates were 86.9 and 82.5, and precision rates were 97.4 and 95.3 for browning and leafless crowns, respectively. Across the island of Hawaii, we found 43,134 individual crowns suspected of exhibiting the active (browning) stage of ROD infection. Hotspots of potential ROD infection are apparent in the maps. The peninsula on the eastern side of Hawaii known as the Puna district, where the ROD outbreak likely originated, contained a particularly high density of brown crown detections. In comparison, leafless crown detections were much more numerous (547,666 detected leafless crowns in total) and more dispersed across the island. Mapped hotspots of likely ROD incidence across the island will enable scientists, administrators, and land managers to better understand both where and how ROD spreads and how to apply limited resources to limiting this spread. Full article

Spatial information on forest functional composition is needed to inform management and conservation efforts, yet this information is lacking, particularly in tropical regions. Canopy foliar traits underpin the functional biodiversity of forests, and have been shown to be remotely measurable using airborne 350–2510 nm imaging spectrometers. We used newly acquired imaging spectroscopy data constrained with concurrent light detection and ranging (LiDAR) measurements from the Carnegie Airborne Observatory (CAO), and field measurements, to test the performance of the Spectranomics approach for foliar trait retrieval. The method was previously developed in Neotropical forests, and was tested here in the humid tropical forests of Malaysian Borneo. Multiple foliar chemical traits, as well as leaf mass per area (LMA), were estimated with demonstrable precision and accuracy. The results were similar to those observed for Neotropical forests, suggesting a more general use of the Spectranomics approach for mapping canopy traits in tropical forests. Future mapping studies using this approach can advance scientific investigations and applications based on imaging spectroscopy. Full article

Airborne high fidelity imaging spectroscopy (HiFIS) holds great promise for bridging the gap between field studies of functional diversity, which are spatially limited, and satellite detection of ecosystem properties, which lacks resolution to understand within landscape dynamics. We use Carnegie Airborne Observatory HiFIS data combined with field collected foliar trait data to develop quantitative prediction models of foliar traits at the tree-crown level across over 1000 ha of humid tropical forest. We predicted foliar leaf mass per area (LMA) as well as foliar concentrations of nitrogen, phosphorus, calcium, magnesium and potassium for canopy emergent trees (R²: 0.45–0.67, relative RMSE: 11%–14%). Correlations between remotely sensed model coefficients for these foliar traits are similar to those found in laboratory studies, suggesting that the detection of these mineral nutrients is possible through their biochemical stoichiometry. Maps derived from HiFIS provide quantitative foliar trait information across a tropical forest landscape at fine spatial resolution, and along environmental gradients. Multi-nutrient maps implemented at the fine organismic scale will subsequently provide new insight to the functional biogeography and biological diversity of tropical forest ecosystems. Full article

High-resolution airborne imaging spectroscopy represents a promising avenue for mapping the spread of invasive tree species through native forests, but for this technology to be useful to forest managers there are two main technical challenges that must be addressed: (1) mapping a single focal species amongst a diverse array of other tree species; and (2) detecting early outbreaks of invasive plant species that are often hidden beneath the forest canopy. To address these challenges, we investigated the performance of two single-class classification frameworks—Biased Support Vector Machine (BSVM) and Mixture Tuned Matched Filtering (MTMF)—to estimate the degree of Psidium cattleianum incidence over a range of forest vertical strata (relative canopy density). We demonstrate that both BSVM and MTMF have the ability to detect relative canopy density of a single focal plant species in a vertically stratified forest, but they differ in the degree of user input required. Our results suggest BSVM as a promising method to disentangle spectrally-mixed classifications, as this approach generates decision values from a similarity function (kernel), which optimizes complex comparisons between classes using a dynamic machine learning process. Full article

Non-structural carbohydrates (NSC) are products of photosynthesis, and leaf NSC concentration may be a prognostic indicator of climate-change tolerance in woody plants. However, measurement of leaf NSC is prohibitively labor intensive, especially in tropical forests, where foliage is difficult to access and where NSC concentrations vary enormously by species and across environments. Imaging spectroscopy may allow quantitative mapping of leaf NSC, but this possibility remains unproven. We tested the accuracy of NSC remote sensing at leaf, canopy and stand levels using visible-to-shortwave infrared (VSWIR) spectroscopy with partial least squares regression (PLSR) techniques. Leaf-level analyses demonstrated the high precision (R² = 0.69–0.73) and accuracy (%RMSE = 13%–14%) of NSC estimates in 6136 live samples taken from 4222 forest canopy species worldwide. The leaf spectral data were combined with a radiative transfer model to simulate the role of canopy structural variability, which led to a reduction in the precision and accuracy of leaf NSC estimation (R² = 0.56; %RMSE = 16%). Application of the approach to 79 one-hectare plots in Amazonia using the Carnegie Airborne Observatory VSWIR spectrometer indicated the good precision and accuracy of leaf NSC estimates at the forest stand level (R² = 0.49; %RMSE = 9.1%). Spectral analyses indicated strong contributions of the shortwave-IR (1300–2500 nm) region to leaf NSC determination at all scales. We conclude that leaf NSC can be remotely sensed, opening doors to monitoring forest canopy physiological responses to environmental stress and climate change. Full article

Plant species identification and mapping based on remotely-sensed spectral signatures is a challenging task with the potential to contribute enormously to ecological studies. Success in this task rests upon the appropriate collection and use of costly field-based training data, and researchers are in need of ways to improve collection efficiency based on quantitative evidence. Using imaging spectrometer data collected by the Carnegie Airborne Observatory for hundreds of field-identified tree crowns in Kruger National Park, South Africa, we developed woody plant species classification models and evaluated how classification accuracy increases with increasing numbers of training crowns. First, we show that classification accuracy must be estimated while respecting the crown as the basic unit of data; otherwise, accuracy will be overestimated and the amount of training data needed to perform successful classification will be underestimated. We found that classification accuracy and the number of training crowns needed to perform successful classification varied depending on the number and spectral separability of species in the model. We also used a modified Michaelis-Menten function to describe the empirical relationship between training crowns and model accuracy, and show how this function may be useful for predicting accuracy. This framework can assist researchers in designing field campaigns to maximize the efficiency of field data collection, and thus the amount of biodiversity information gained from remote species identification models. Full article

Airborne remote sensing has an important role to play in mapping and monitoring biodiversity over large spatial scales. Techniques for applying this technology to biodiversity mapping have focused on remote species identification of individual crowns; however, this requires collection of a large number of crowns to train a classifier, which may limit the usefulness of this approach in many study regions. Based on the premise that the spectral variation among sites is related to their ecological dissimilarity, we asked whether it is possible to estimate the beta diversity, or turnover in species composition, among sites without the use of training data. We evaluated alternative methods using simulated communities constructed from the spectra of field-identified tree and shrub crowns from an African savanna. A method based on the k-means clustering of crown spectra produced beta diversity estimates (measured as Bray-Curtis dissimilarity) among sites with an average pairwise correlation of ~0.5 with the true beta diversity, compared to an average correlation of ~0.8 obtained by a supervised species classification approach. When applied to savanna landscapes, the unsupervised clustering method produced beta diversity estimates similar to those obtained from supervised classification. The unsupervised method proposed here can be used to estimate the spatial structure of species turnover in a landscape when training data (e.g., tree crowns) are unavailable, providing top-down information for science, conservation and ecosystem management applications. Full article

Mapping the spatial distribution of plant species in savannas provides insight into the roles of competition, fire, herbivory, soils and climate in maintaining the biodiversity of these ecosystems. This study focuses on the challenges facing large-scale species mapping using a fusion of Light Detection and Ranging (LiDAR) and hyperspectral imagery. Here we build upon previous work on airborne species detection by using a two-stage support vector machine (SVM) classifier to first predict species from hyperspectral data at the pixel scale. Tree crowns are segmented from the lidar imagery such that crown-level information, such as maximum tree height, can then be combined with the pixel-level species probabilities to predict the species of each tree. An overall prediction accuracy of 76% was achieved for 15 species. We also show that bidirectional reflectance distribution (BRDF) effects caused by anisotropic scattering properties of savanna vegetation can result in flight line artifacts evident in species probability maps, yet these can be largely mitigated by applying a semi-empirical BRDF model to the hyperspectral data. We find that confronting these three challenges—reflectance anisotropy, integration of pixel- and crown-level data, and crown delineation over large areas—enables species mapping at ecosystem scales for monitoring biodiversity and ecosystem function. Full article

Our objective is to identify and map individuals of nine tree species in a Hawaiian lowland tropical forest by comparing the performance of a variety of semi-supervised classifiers. A method was adapted to process hyperspectral imagery, LiDAR intensity variables, and LiDAR-derived canopy height and use them to assess the identification accuracy. We found that semi-supervised Support Vector Machine classification using tensor summation kernel was superior to supervised classification, with demonstrable accuracy for at least eight out of nine species, and for all combinations of data types tested. We also found that the combination of hyperspectral imagery and LiDAR data usually improved species classification. Both LiDAR intensity and LiDAR canopy height proved useful for classification of certain species, but the improvements varied depending upon the species in question. Our results pave the way for target-species identification in tropical forests and other ecosystems. Full article