Next Article in Journal
Impacts of Re-Vegetation on Surface Soil Moisture over the Chinese Loess Plateau Based on Remote Sensing Datasets
Next Article in Special Issue
Automated Detection of Forest Gaps in Spruce Dominated Stands Using Canopy Height Models Derived from Stereo Aerial Imagery
Previous Article in Journal
Evaluation of VIIRS and MODIS Thermal Emissive Band Calibration Stability Using Ground Target
Previous Article in Special Issue
Moving Towards Dynamic Ocean Management: How Well Do Modeled Ocean Products Predict Species Distributions?
Article Menu

Export Article

Open AccessArticle
Remote Sens. 2016, 8(2), 161; doi:10.3390/rs8020161

Tree Species Abundance Predictions in a Tropical Agricultural Landscape with a Supervised Classification Model and Imbalanced Data

1
School of Forest Resources and Conservation, University of Florida, PO Box 11041 Gainesville, FL 32611, USA
2
Department of Global Ecology, Carnegie Institution for Science, 260 Panama St., Stanford, CA 94305, USA
3
Department of Computer and Information Science and Engineering, University of Florida, PO Box 116120, Gainesville, FL 32611, USA
4
Smithsonian Tropical Research Institute, Apartado 0843–03092, Balboa, Ancon, Republic of Panama
*
Author to whom correspondence should be addressed.
Academic Editors: Susan L. Ustin, Clement Atzberger and Prasad S. Thenkabail
Received: 2 December 2015 / Revised: 3 February 2016 / Accepted: 14 February 2016 / Published: 19 February 2016
(This article belongs to the Special Issue Remote Sensing of Biodiversity)
View Full-Text   |   Download PDF [5505 KB, uploaded 1 March 2016]   |  

Abstract

Mapping species through classification of imaging spectroscopy data is facilitating research to understand tree species distributions at increasingly greater spatial scales. Classification requires a dataset of field observations matched to the image, which will often reflect natural species distributions, resulting in an imbalanced dataset with many samples for common species and few samples for less common species. Despite the high prevalence of imbalanced datasets in multiclass species predictions, the effect on species prediction accuracy and landscape species abundance has not yet been quantified. First, we trained and assessed the accuracy of a support vector machine (SVM) model with a highly imbalanced dataset of 20 tropical species and one mixed-species class of 24 species identified in a hyperspectral image mosaic (350–2500 nm) of Panamanian farmland and secondary forest fragments. The model, with an overall accuracy of 62% ± 2.3% and F-score of 59% ± 2.7%, was applied to the full image mosaic (23,000 ha at a 2-m resolution) to produce a species prediction map, which suggested that this tropical agricultural landscape is more diverse than what has been presented in field-based studies. Second, we quantified the effect of class imbalance on model accuracy. Model assessment showed a trend where species with more samples were consistently over predicted while species with fewer samples were under predicted. Standardizing sample size reduced model accuracy, but also reduced the level of species over- and under-prediction. This study advances operational species mapping of diverse tropical landscapes by detailing the effect of imbalanced data on classification accuracy and providing estimates of tree species abundance in an agricultural landscape. Species maps using data and methods presented here can be used in landscape analyses of species distributions to understand human or environmental effects, in addition to focusing conservation efforts in areas with high tree cover and diversity. View Full-Text
Keywords: Support Vector Machine; imaging spectroscopy; class imbalance; tropics; agriculture; operational species mapping Support Vector Machine; imaging spectroscopy; class imbalance; tropics; agriculture; operational species mapping
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).

Supplementary material

Scifeed alert for new publications

Never miss any articles matching your research from any publisher
  • Get alerts for new papers matching your research
  • Find out the new papers from selected authors
  • Updated daily for 49'000+ journals and 6000+ publishers
  • Define your Scifeed now

SciFeed Share & Cite This Article

MDPI and ACS Style

Graves, S.J.; Asner, G.P.; Martin, R.E.; Anderson, C.B.; Colgan, M.S.; Kalantari, L.; Bohlman, S.A. Tree Species Abundance Predictions in a Tropical Agricultural Landscape with a Supervised Classification Model and Imbalanced Data. Remote Sens. 2016, 8, 161.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Remote Sens. EISSN 2072-4292 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top