An official website of the United States government
Abstract Vegetation species mapping using airborne imaging spectroscopy yields accurate results and is important for advancing conservation objectives and biogeographic studies. As these data become more readily available owing to the upcoming launch of spaceborne imaging spectrometers, it is necessary to understand how these data can be used to consistently classify species across large geographic scales. However, few studies have attempted to map species across multiple ecosystems; therefore, little is known regarding the effect of intra-specific variation on the mapping of a single species across a wide range of environments and among varying backgrounds of other non-target species. To explore this effect, we developed and tested species classification models forMetrosideros polymorpha, a highly polymorphic canopy species endemic to Hawai’i, which is found in a diverse array of ecosystems. We compared the accuracies of support vector machine (SVM) and random forest models trained on canopy reflectance data from each of eight distinct ecosystems (ecosystem-specific) and a universal model trained on data from all ecosystems. When applied to ecosystem-specific test datasets, the ecosystem-specific models outperformed the universal model; however, the universal model retained high (>81%) accuracies across all ecosystems. Additionally, we found that models from ecosystems with broad variation inM. polymorphacanopy traits, as estimated using chemometric equations applied to canopy spectra, accurately predictedM. polymorphain other ecosystems. While species classifications across ecosystems can yield accurate results, these results will require sampling procedures that capture the intra-specific variation of the target species.
more »
« less
Classifying a Highly Polymorphic Tree Species across Landscapes Using Airborne Imaging Spectroscopy
Vegetation classifications on large geographic scales are necessary to inform conservation decisions and monitor keystone, invasive, and endangered species. These classifications are often effectively achieved by applying models to imaging spectroscopy, a type of remote sensing data, but such undertakings are often limited in spatial extent. Here we provide accurate, high-resolution spatial data on the keystone species Metrosideros polymorpha, a highly polymorphic tree species distributed across bioclimatic zones and environmental gradients on Hawai’i Island using airborne imaging spectroscopy and LiDAR. We compare two tree species classification techniques, the support vector machine (SVM) and spectral mixture analysis (SMA), to assess their ability to map M. polymorpha over 28,000 square kilometers where differences in topography, background vegetation, sun angle relative to the aircraft, and day of data collection, among others, challenge accurate classification. To capture spatial variability in model performance, we applied Gaussian process classification (GPC) to estimate the spatial probability density of M. polymorpha occurrence using only training sample locations. We found that while SVM and SMA models exhibit similar raw score accuracy over the test set (96.0% and 93.4%, respectively), SVM better reproduces the spatial distribution of M. polymorpha than SMA. We developed a final 2 m × 2 m M. polymorpha presence dataset and a 30 m × 30 m M. polymorpha density dataset using SVM classifications that have been made publicly available for use in conservation applications. Accurate, large-scale species classifications are achievable, but metrics for model performance assessments must account for spatial variation of model accuracy.
more »
« less
- Award ID(s):
- 2218932
- PAR ID:
- 10539468
- Publisher / Repository:
- MDPI
- Date Published:
- Journal Name:
- Remote Sensing
- Volume:
- 15
- Issue:
- 18
- ISSN:
- 2072-4292
- Page Range / eLocation ID:
- 4365
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Imaging spectroscopy is a burgeoning tool for understanding ecosystem functioning on large spatial scales, yet the application of this technology to assess intra-specific trait variation across environmental gradients has been poorly tested. Selection of specific genotypes via environmental filtering plays an important role in driving trait variation and thus functional diversity across space and time, but the relative contributions of intra-specific trait variation and species turnover are still unclear. To address this issue, we quantified the variation in reflectance spectra within and between six uniform stands of Metrosideros polymorpha across elevation and soil substrate age gradients on Hawai‘i Island. Airborne imaging spectroscopy and light detection and ranging (LiDAR) data were merged to capture and isolate sunlit portions of canopies at the six M. polymorpha-dominated sites. Both intra-site and inter-site spectral variations were quantified using several analyses. A support vector machine (SVM) model revealed that each site was spectrally distinct, while Euclidean distances between site centroids in principal components (PC) space indicated that elevation and soil substrate age drive the separation of canopy spectra between sites. Coefficients of variation among spectra, as well as the intrinsic spectral dimensionality of the data, demonstrated the hierarchical effect of soil substrate age, followed by elevation, in determining intra-site variation. Assessments based on leaf trait data estimated from canopy reflectance resulted in similar patterns of separation among sites in the PC space and distinction among sites in the SVM model. Using a highly polymorphic species, we demonstrated that canopy reflectance follows known ecological principles of community turnover and thus how spectral remote sensing addresses forest community assembly on large spatial scales.more » « less
-
The role of intraspecific trait variation in functional ecology has gained traction in recent years as many papers have observed its importance in driving community diversity and ecology. Yet much of the work in this field relies on field-based trait surveys. Here, we used continuous canopy trait information derived from remote sensing data of a highly polymorphic tree species, Metrosideros polymorpha, to quantify environmental controls on intraspecific trait variation. M. polymorpha, an endemic, keystone tree species in Hawai’i, varies morphologically, chemically, and genetically across broad elevation and soil substrate age gradients, making it an ideal model organism to explore large-scale environmental drivers of intraspecific trait variation. M. polymorpha canopy reflectance (visible to shortwave infrared; 380–2510 nm) and light detection and ranging (LiDAR) data collected by the Global Airborne Observatory were modeled to canopy trait estimates of leaf mass per area, chlorophyll a and b, carotenoids, total carbon, nitrogen, phosphorus, phenols, cellulose, and top of canopy height using previously developed leaf chemometric equations. We explored how these derived traits varied across environmental gradients by extracting elevation, slope, aspect, precipitation, and soil substrate age data at canopy locations. We then obtained the feature importance values of the environmental factors in predicting each leaf trait by training random forest models to predict leaf traits individually. Of these environmental factors, elevation was the most important predictor for all canopy traits. Elevation not only affected canopy traits directly but also indirectly by influencing the relationships between soil substrate age and canopy traits as well as between nitrogen and other traits, as indicated by the change in slope between the variables at different elevation ranges. In conclusion, intraspecific variation in M. polymorpha traits derived from remote sensing adheres to known leaf economic spectrum (LES) patterns as well as interspecific LES traits previously mapped using imaging spectroscopy.more » « less
-
Abstract Imaging spectroscopy has the potential to map closely related plant taxa at landscape scales. Although spectral investigations at the leaf and canopy levels have revealed relationships between phylogeny and reflectance, understanding how spectra differ across, and are inherited from, genotypes of a single species has received less attention. We used a common-garden population of four varieties of the keystone canopy tree,Metrosideros polymorpha, from Hawaii Island and four F1-hybrid genotypes derived from controlled crosses to determine if reflectance spectra discriminate sympatric, conspecific varieties of this species and their hybrids. With a single exception, pairwise comparisons of leaf reflectance patterns successfully distinguished varieties ofM. polymorphaon Hawaii Island as well as populations of the same variety from different islands. Further, spectral variability within a single variety from Hawaii Island and the older island of Oahu was greater than that observed among the four varieties on Hawaii Island. F1 hybrids most frequently displayed leaf spectral patterns intermediate to those of their parent taxa. Spectral reflectance patterns distinguished each of two of the hybrid genotypes from one of their parent varieties, indicating that classifying hybrids may be possible, particularly if sample sizes are increased. This work quantifies a baseline in spectral variability for an endemic Hawaiian tree species and advances the use of imaging spectroscopy in biodiversity studies at the genetic level.more » « less
-
Trees in proximity to power lines can cause significant damage to utility infrastructure during storms, leading to substantial economic and societal costs. This study investigated the effectiveness of non-parametric machine learning algorithms in modeling tree-related outage risks to distribution power lines at a finer spatial scale. We used a vegetation risk model (VRM) comprising 15 predictor variables derived from roadside tree data, landscape information, vegetation management records, and utility infrastructure data. We evaluated the VRM’s performance using decision tree (DT), random forest (RF), k-Nearest Neighbor (k-NN), extreme gradient boosting (XGBoost), and support vector machine (SVM) techniques. The RF algorithm demonstrated the highest performance with an accuracy of 0.753, an AUC-ROC of 0.746, precision of 0.671, and an F1-score of 0.693. The SVM achieved the highest recall value of 0.727. Based on the overall performance, the RF emerged as the best machine learning algorithm, whereas the DT was the least suitable. The DT reported the lowest run times for both hyperparameter optimization (3.93 s) and model evaluation (0.41 s). XGBoost and the SVM exhibited the highest run times for hyperparameter tuning (9438.54 s) and model evaluation (112 s), respectively. The findings of this study are valuable for enhancing the resilience and reliability of the electric grid.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3390/rs15184365
