Simple Search:

Classification of oil palm nitrogen status from SPOT-6 satellite using support vector machine and spectral indices


Citation

Amirruddin, Amiratul Diyana and Muharam, Farrah Melissa (2017) Classification of oil palm nitrogen status from SPOT-6 satellite using support vector machine and spectral indices. In: International Conference on Big Data Applications in Agriculture (ICBAA2017), 5-6 Dec. 2017, Auditorium Putra, TNCPI Building, Universiti Putra Malaysia. (pp. 107-117).

Abstract / Synopsis

Nitrogen (N) management is important in sustaining oil palm production. Remote sensing based approaches such as spectral index has promise in assessing the N nutrition content of many crops. The objectives of this study are to examine the N classification capability of three spectral indexes (SI): visible (Vis), near infrared (NIR) and a combination of visible and NIR (Vis+NIR) using data from the SPOT-6 satellite. N treatments varied from 0 to 2 kg per palm and were applied to both mature palms. The N-sensitive SIs tested in this study were age-dependent. The Vis index such as BGRI1 (CVA= 79.55%) and the Vis+NIR indices such as NDVI, NG, IPVI and GNDVI (CVA= 81.82%) were the best indices to assess N status of young and prime mature palms through the SVM classifier. Nonetheless, the SVM classifier showed promising potential in classifying foliar N content of mature palms that can possibly be used further for developing a new index in assessing N content of oil palms.


Download File

[img] PDF
Technical_Paper_7.pdf
Restricted to Repository staff only

Download (492kB)

Additional Metadata

Item Type: Conference or Workshop Item (Paper)
Divisions: Faculty of Agriculture
Institute of Plantation Studies
Publisher: Institute of Plantation Studies, Universiti Putra Malaysia
Keywords: Nitrogen; Oil palm; Satellite; Machine learning; Spectral index
Depositing User: Nabilah Mustapa
Date Deposited: 07 Feb 2018 08:42
Last Modified: 07 Feb 2018 08:42
URI: http://psasir.upm.edu.my/id/eprint/58870
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item