Limits...
Operational Tree Species Mapping in a Diverse Tropical Forest with Airborne Imaging Spectroscopy.

Baldeck CA, Asner GP, Martin RE, Anderson CB, Knapp DE, Kellner JR, Wright SJ - PLoS ONE (2015)

Bottom Line: First, we compared two leading single-class classification methods--binary support vector machine (SVM) and biased SVM--for their performance in identifying pixels of a single focal species.From this comparison we determined that biased SVM was more precise and created a multi-species classification model by combining the three biased SVM models.We attribute the success of our model to recent classification and mapping techniques adapted to species detection in diverse closed-canopy forests, which can pave the way for remote species mapping in a wider variety of ecosystems.

View Article: PubMed Central - PubMed

Affiliation: Department of Global Ecology, Carnegie Institution for Science, Stanford, CA, United States of America.

ABSTRACT
Remote identification and mapping of canopy tree species can contribute valuable information towards our understanding of ecosystem biodiversity and function over large spatial scales. However, the extreme challenges posed by highly diverse, closed-canopy tropical forests have prevented automated remote species mapping of non-flowering tree crowns in these ecosystems. We set out to identify individuals of three focal canopy tree species amongst a diverse background of tree and liana species on Barro Colorado Island, Panama, using airborne imaging spectroscopy data. First, we compared two leading single-class classification methods--binary support vector machine (SVM) and biased SVM--for their performance in identifying pixels of a single focal species. From this comparison we determined that biased SVM was more precise and created a multi-species classification model by combining the three biased SVM models. This model was applied to the imagery to identify pixels belonging to the three focal species and the prediction results were then processed to create a map of focal species crown objects. Crown-level cross-validation of the training data indicated that the multi-species classification model had pixel-level producer's accuracies of 94-97% for the three focal species, and field validation of the predicted crown objects indicated that these had user's accuracies of 94-100%. Our results demonstrate the ability of high spatial and spectral resolution remote sensing to accurately detect non-flowering crowns of focal species within a diverse tropical forest. We attribute the success of our model to recent classification and mapping techniques adapted to species detection in diverse closed-canopy forests, which can pave the way for remote species mapping in a wider variety of ecosystems.

No MeSH data available.


Related in: MedlinePlus

Mapped prediction results of binary and biased SVM models for the three focal species.The true-color representation of the raw imagery is on the left-hand side, results from the binary SVM models are in the center, and results from the biased SVM models are on the right-hand side. The three spectral bands used to display the true-color image are R = 640 nm, G = 550 nm, and B = 460 nm.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4496029&req=5

pone.0118403.g004: Mapped prediction results of binary and biased SVM models for the three focal species.The true-color representation of the raw imagery is on the left-hand side, results from the binary SVM models are in the center, and results from the biased SVM models are on the right-hand side. The three spectral bands used to display the true-color image are R = 640 nm, G = 550 nm, and B = 460 nm.

Mentions: In general, binary SVM had higher sensitivity but lower specificity than biased SVM for the same focal species (Fig 3). The average model sensitivity for binary SVM was 0.036–0.057 higher across species than that of biased SVM. The difference was smaller for specificity, which was 0.004–0.012 higher across species for biased SVM compared to binary SVM. The maps produced from these models were consistent with this general result as more pixels were assigned to the focal class by the binary SVM models (Fig 4). However, the contrast in the amount of pixels assigned to the focal classes was quite strong, as 11.9%, 3.9%, and 4.3% of the vegetation pixels were classified as D. panamensis, H. guayacan, and J. copaia, respectively, using the binary SVM models versus only 4.1%, 0.7%, and 1.0%, respectively, using the biased SVM models. Accordingly, the binary SVM maps were noticeably noisier than those produced from biased SVM (Fig 4). We found the higher precision provided by the biased SVM models to be desirable for our mapping application; therefore, we chose biased SVM as the basis for the final species classification model.


Operational Tree Species Mapping in a Diverse Tropical Forest with Airborne Imaging Spectroscopy.

Baldeck CA, Asner GP, Martin RE, Anderson CB, Knapp DE, Kellner JR, Wright SJ - PLoS ONE (2015)

Mapped prediction results of binary and biased SVM models for the three focal species.The true-color representation of the raw imagery is on the left-hand side, results from the binary SVM models are in the center, and results from the biased SVM models are on the right-hand side. The three spectral bands used to display the true-color image are R = 640 nm, G = 550 nm, and B = 460 nm.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4496029&req=5

pone.0118403.g004: Mapped prediction results of binary and biased SVM models for the three focal species.The true-color representation of the raw imagery is on the left-hand side, results from the binary SVM models are in the center, and results from the biased SVM models are on the right-hand side. The three spectral bands used to display the true-color image are R = 640 nm, G = 550 nm, and B = 460 nm.
Mentions: In general, binary SVM had higher sensitivity but lower specificity than biased SVM for the same focal species (Fig 3). The average model sensitivity for binary SVM was 0.036–0.057 higher across species than that of biased SVM. The difference was smaller for specificity, which was 0.004–0.012 higher across species for biased SVM compared to binary SVM. The maps produced from these models were consistent with this general result as more pixels were assigned to the focal class by the binary SVM models (Fig 4). However, the contrast in the amount of pixels assigned to the focal classes was quite strong, as 11.9%, 3.9%, and 4.3% of the vegetation pixels were classified as D. panamensis, H. guayacan, and J. copaia, respectively, using the binary SVM models versus only 4.1%, 0.7%, and 1.0%, respectively, using the biased SVM models. Accordingly, the binary SVM maps were noticeably noisier than those produced from biased SVM (Fig 4). We found the higher precision provided by the biased SVM models to be desirable for our mapping application; therefore, we chose biased SVM as the basis for the final species classification model.

Bottom Line: First, we compared two leading single-class classification methods--binary support vector machine (SVM) and biased SVM--for their performance in identifying pixels of a single focal species.From this comparison we determined that biased SVM was more precise and created a multi-species classification model by combining the three biased SVM models.We attribute the success of our model to recent classification and mapping techniques adapted to species detection in diverse closed-canopy forests, which can pave the way for remote species mapping in a wider variety of ecosystems.

View Article: PubMed Central - PubMed

Affiliation: Department of Global Ecology, Carnegie Institution for Science, Stanford, CA, United States of America.

ABSTRACT
Remote identification and mapping of canopy tree species can contribute valuable information towards our understanding of ecosystem biodiversity and function over large spatial scales. However, the extreme challenges posed by highly diverse, closed-canopy tropical forests have prevented automated remote species mapping of non-flowering tree crowns in these ecosystems. We set out to identify individuals of three focal canopy tree species amongst a diverse background of tree and liana species on Barro Colorado Island, Panama, using airborne imaging spectroscopy data. First, we compared two leading single-class classification methods--binary support vector machine (SVM) and biased SVM--for their performance in identifying pixels of a single focal species. From this comparison we determined that biased SVM was more precise and created a multi-species classification model by combining the three biased SVM models. This model was applied to the imagery to identify pixels belonging to the three focal species and the prediction results were then processed to create a map of focal species crown objects. Crown-level cross-validation of the training data indicated that the multi-species classification model had pixel-level producer's accuracies of 94-97% for the three focal species, and field validation of the predicted crown objects indicated that these had user's accuracies of 94-100%. Our results demonstrate the ability of high spatial and spectral resolution remote sensing to accurately detect non-flowering crowns of focal species within a diverse tropical forest. We attribute the success of our model to recent classification and mapping techniques adapted to species detection in diverse closed-canopy forests, which can pave the way for remote species mapping in a wider variety of ecosystems.

No MeSH data available.


Related in: MedlinePlus