Classifying forest species using hyperspectral data in Balah Forest Reserve, Kelantan, Peninsular Malaysia
This study attempts to classify forest species using hyperspectral data for supporting resources management. The primary dataset used was AISA sensor. The sensor was mounted onboard the NOMAD GAF-27 aircraft at 2,000 m altitude creating a 2 m spatial resolution on the ground. Pre-processing was carr...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Institute of Forest Science, Kangwon National University
2013
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/29108/ http://psasir.upm.edu.my/id/eprint/29108/1/29108.pdf |
| _version_ | 1848846306663989248 |
|---|---|
| author | Mat Zain, Ruhasmizan Ismail, Mohd Hasmadi Hassan Zaki, Pakhriazad |
| author_facet | Mat Zain, Ruhasmizan Ismail, Mohd Hasmadi Hassan Zaki, Pakhriazad |
| author_sort | Mat Zain, Ruhasmizan |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | This study attempts to classify forest species using hyperspectral data for supporting resources management. The primary dataset used was AISA sensor. The sensor was mounted onboard the NOMAD GAF-27 aircraft at 2,000 m altitude creating a 2 m spatial resolution on the ground. Pre-processing was carried out with CALIGEO software, which automatically corrects for both geometric and radiometric distortions of the raw image data. The radiance data set was then converted to at-sensor reflectance derived from the FODIS sensor. Spectral Angle Mapper (SAM) technique was used for image classification. The spectra libraries for tree species were established after confirming the appropriate match between field spectra and pixel spectra. Results showed that the highest spectral signature in NIR range were Kembang Semangkok (Scaphium macropodum), followed by Meranti Sarang Punai (Shorea parvifolia) and Chengal (Neobalanocarpus hemii). Meanwhile, the lowest spectral response were Kasai (Pometia pinnata), Kelat (Eugenia spp.) and Merawan (Hopea beccariana), respectively. The overall accuracy obtained was 79%. Although the accuracy of SAM techniques is below the expectation level, SAM classifier was able to classify tropical tree species. In future it is believe that the most effective way of ground data collection is to use the ground object that has the strongest response to sensor for more significant tree signatures. |
| first_indexed | 2025-11-15T09:00:37Z |
| format | Article |
| id | upm-29108 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T09:00:37Z |
| publishDate | 2013 |
| publisher | Institute of Forest Science, Kangwon National University |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-291082016-04-22T09:15:42Z http://psasir.upm.edu.my/id/eprint/29108/ Classifying forest species using hyperspectral data in Balah Forest Reserve, Kelantan, Peninsular Malaysia Mat Zain, Ruhasmizan Ismail, Mohd Hasmadi Hassan Zaki, Pakhriazad This study attempts to classify forest species using hyperspectral data for supporting resources management. The primary dataset used was AISA sensor. The sensor was mounted onboard the NOMAD GAF-27 aircraft at 2,000 m altitude creating a 2 m spatial resolution on the ground. Pre-processing was carried out with CALIGEO software, which automatically corrects for both geometric and radiometric distortions of the raw image data. The radiance data set was then converted to at-sensor reflectance derived from the FODIS sensor. Spectral Angle Mapper (SAM) technique was used for image classification. The spectra libraries for tree species were established after confirming the appropriate match between field spectra and pixel spectra. Results showed that the highest spectral signature in NIR range were Kembang Semangkok (Scaphium macropodum), followed by Meranti Sarang Punai (Shorea parvifolia) and Chengal (Neobalanocarpus hemii). Meanwhile, the lowest spectral response were Kasai (Pometia pinnata), Kelat (Eugenia spp.) and Merawan (Hopea beccariana), respectively. The overall accuracy obtained was 79%. Although the accuracy of SAM techniques is below the expectation level, SAM classifier was able to classify tropical tree species. In future it is believe that the most effective way of ground data collection is to use the ground object that has the strongest response to sensor for more significant tree signatures. Institute of Forest Science, Kangwon National University 2013 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/29108/1/29108.pdf Mat Zain, Ruhasmizan and Ismail, Mohd Hasmadi and Hassan Zaki, Pakhriazad (2013) Classifying forest species using hyperspectral data in Balah Forest Reserve, Kelantan, Peninsular Malaysia. Journal of Forest and Environmental Science, 29 (2). pp. 131-137. ISSN 2288-9744; ESSN: 2288-9752 http://www.jofs.or.kr/journal/view.html?uid=429&start=310&sort=&scale=&key=&oper=&key_word=&year1=&year2=&Vol=&Num=ueckrxhbbaz&PG=&book=&mod=&sflag=&sub_box=&aut_box=&sos_box=&pub_box=&key_box=&abs_box=&year= 10.7747/JFS.2013.29.2.131 |
| spellingShingle | Mat Zain, Ruhasmizan Ismail, Mohd Hasmadi Hassan Zaki, Pakhriazad Classifying forest species using hyperspectral data in Balah Forest Reserve, Kelantan, Peninsular Malaysia |
| title | Classifying forest species using hyperspectral data in Balah Forest Reserve, Kelantan, Peninsular Malaysia |
| title_full | Classifying forest species using hyperspectral data in Balah Forest Reserve, Kelantan, Peninsular Malaysia |
| title_fullStr | Classifying forest species using hyperspectral data in Balah Forest Reserve, Kelantan, Peninsular Malaysia |
| title_full_unstemmed | Classifying forest species using hyperspectral data in Balah Forest Reserve, Kelantan, Peninsular Malaysia |
| title_short | Classifying forest species using hyperspectral data in Balah Forest Reserve, Kelantan, Peninsular Malaysia |
| title_sort | classifying forest species using hyperspectral data in balah forest reserve, kelantan, peninsular malaysia |
| url | http://psasir.upm.edu.my/id/eprint/29108/ http://psasir.upm.edu.my/id/eprint/29108/ http://psasir.upm.edu.my/id/eprint/29108/ http://psasir.upm.edu.my/id/eprint/29108/1/29108.pdf |