Multi-sensor prediction of Eucalyptus stand volume: A support vector approach
| Autor: | Simone Pedro da Silva, Cibele Hummel do Amaral, Marcus Vinicius de Freitas Silveira, Guilherme Silverio Aquino de Souza, Vicente Paulo Soares, João Flávio Costa dos Santos, José Marinaldo Gleriani, Sidney Geraldo Silveira Velloso, Antônio Santana Ferraz, Getulio Fonseca Domingues, Helio Garcia Leite |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Synthetic aperture radar
Multilinear map Mean squared error Artificial neural network Atomic and Molecular Physics and Optics Regression Computer Science Applications Random forest Support vector machine Linear regression Computers in Earth Sciences Engineering (miscellaneous) Remote sensing Mathematics |
| Zdroj: | ISPRS Journal of Photogrammetry and Remote Sensing. 156:135-146 |
| ISSN: | 0924-2716 |
| Popis: | Stem volume is a key attribute of Eucalyptus forest plantations upon which decision-making is based at diverse levels of planning. Quantifying volume through remote sensing can support a proper management of forests. Because of limitations on spaceborne optical and synthetic aperture radar sensors, this study integrated both types of datasets assembled using support vector regression (SVR) to retrieve the stand volume of Eucalyptus plantations. We assessed different combinations of sensors and a minimum number of plots to develop an SVR model. Finally, the best SVR performance was compared with other analytical methods already tested and in the literature: multilinear regression, artificial neural networks (ANN), and random forest (RF). Here, we introduce a test for comparative analysis of the performance of different methods. We found that SVR accurately predicted stem volume of Brazilian fast-growing Eucalyptus forest plantations. Gaussian radial basis was the most suitable kernel function. Integrating the optical and L-band backscatter data increased the predictive accuracy compared to a single sensor model. Combining NIR-band data from ALOS AVNIR-2 and backscatter of L-band horizontal emitted and vertical received (HV) electric fields from ALOS PALSAR produced the most accurate SVR model (with an R2 of 0.926 and root mean square error of 11.007 m3/ha). The number of field plots sufficient for model development with non-redundant explanatory variables was 77. Under this condition, SVR performed similarly to ANN and outperformed the multiple linear regression and random forest methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect