Estimating biophysical parameters of rice with remote sensing data using support vector machines
- Publication Type:
- Journal Article
- Science China Life Sciences, 2012, 54 (3), pp. 272 - 281
- Issue Date:
|dc.identifier.citation||Science China Life Sciences, 2012, 54 (3), pp. 272 - 281||en_US|
|dc.description.abstract||Hyperspectral reflectance (350â2500 nm) measurements were made over two experimental rice fields containing two cultivars treated with three levels of nitrogen application. Four different transformations of the reflectance data were analyzed for their capability to predict rice biophysical parameters, comprising leaf area index (LAI; m2 green leaf area mâ2 soil) and green leaf chlorophyll density (GLCD; mg chlorophyll mâ2 soil), using stepwise multiple regression (SMR) models and support vector machines (SVMs). Four transformations of the rice canopy data were made, comprising reflectances (R), first-order derivative reflectances (D1), second-order derivative reflectances (D2), and logarithm transformation of reflectances (LOG). The polynomial kernel (POLY) of the SVM using R was the best model to predict rice LAI, with a root mean square error (RMSE) of 1.0496 LAI units. The analysis of variance kernel of SVM using LOG was the best model to predict rice GLCD, with an RMSE of 523.0741 mg mâ2. The SVM approach was not only superior to SMR models for predicting the rice biophysical parameters, but also provided a useful exploratory and predictive tool for analyzing different transformations of reflectance data.||en_US|
|dc.relation.ispartof||Science China Life Sciences||en_US|
|dc.subject.classification||Plant Biology & Botany||en_US|
|dc.title||Estimating biophysical parameters of rice with remote sensing data using support vector machines||en_US|
|utslib.for||0703 Crop and Pasture Production||en_US|
|utslib.for||0607 Plant Biology||en_US|
|utslib.for||06 Biological Sciences||en_US|
|pubs.organisational-group||/University of Technology Sydney|
|pubs.organisational-group||/University of Technology Sydney/Faculty of Science|
|pubs.organisational-group||/University of Technology Sydney/Strength - C3 - Climate Change Cluster|
OPUS (Open Publications of UTS Scholars) is the UTS institutional repository. It showcases the research of UTS staff and postgraduate students to a global audience. For you, as a researcher, OPUS increases the visibility and accessibility of your research by making it openly available regardless of where you choose to publish.
Items in OPUS are enhanced with high quality metadata and seeded to search engines such as Google Scholar as well as being linked to your UTS research profile, increasing discoverability and opportunities for citation of your work and collaboration. In addition, works in OPUS are preserved for long-term access and discovery.
The UTS Open Access Policy requires UTS research outputs to be openly available via OPUS. Depositing your work in OPUS also assists you in complying with ARC, NHMRC and other funder Open Access policies. Providing Open Access to your research outputs through OPUS not only ensures you comply with these important policies, but increases opportunities for other researchers to cite and build upon your work.
OPUS archives UTS research submitted for the UTS Research Output Collection (UTS ROC) and Excellence in Research for Australia (ERA). It also stores digital theses and forms of scholarship that do not usually see formal publication.
When you claim (or enter) your research in Symplectic Elements, simply upload a copy of your work which can be made openly available. Symplectic provides information on which version of your work to upload. If you are unsure, please supply a copy of the Accepted Manuscript version. Ensure you check the box to "agree to the OPUS license terms".
Once uploaded, your works are automatically sent to OPUS and placed temporarily in Closed Access until reviewed by UTS Library staff.
Once items are cleared of copyright constraints and/or publisher embargoes, your work is moved to Open Access and made accessible to the public.
Instructions are available from the Symplectic User Guide or contact firstname.lastname@example.org for further information.