Comparison of partial least squares and support vector regressions for predicting leaf area index on a tropical grassland using hyperspectral data

Zolo Kiala; John Odindi; Onisimo Mutanga; Kabir Peerbhay

doi:10.1117/1.JRS.10.036015

15 August 2016 Comparison of partial least squares and support vector regressions for predicting leaf area index on a tropical grassland using hyperspectral data

Zolo Kiala, John Odindi, Onisimo Mutanga, Kabir Peerbhay

Author Affiliations +

Journal of Applied Remote Sensing, Vol. 10, Issue 3, 036015 (August 2016). https://doi.org/10.1117/1.JRS.10.036015

Abstract

Leaf area index (LAI) is a key biophysical parameter commonly used to determine vegetation status, productivity, and health in tropical grasslands. Accurate LAI estimates are useful in supporting sustainable rangeland management by providing information related to grassland condition and associated goods and services. The performance of support vector regression (SVR) was compared to partial least square regression (PLSR) on selected optimal hyperspectral bands to detect LAI in heterogeneous grassland. Results show that PLSR performed better than SVR at the beginning and end of summer. At the peak of the growing season (mid-summer), during reflectance saturation, SVR models yielded higher accuracies (R²=0.902 and RMSE=0.371 m² m⁻²) than PLSR models (R²=0.886 and RMSE=0.379 m² m⁻²). For the combined dataset (all of summer), SVR models were slightly more accurate (R²=0.74 and RMSE=0.578 m²m⁻²) than PLSR models (R²=0.732 and RMSE=0.58 m² m⁻²). Variable importance on the projection scores show that most of the bands were located in the near-infrared and shortwave regions of the electromagnetic spectrum, thus providing a basis to investigate the potential of sensors on aerial and satellite platforms for large-scale grassland LAI prediction.

Citation Download Citation

Zolo Kiala, John Odindi, Onisimo Mutanga, and Kabir Peerbhay "Comparison of partial least squares and support vector regressions for predicting leaf area index on a tropical grassland using hyperspectral data," Journal of Applied Remote Sensing 10(3), 036015 (15 August 2016). https://doi.org/10.1117/1.JRS.10.036015

Published: 15 August 2016

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE