TY - JOUR
T1 - Classification of ASAS multiangle and multispectral measurements using artificial neural networks
AU - Abuelgasim, Abdelgadir A.
AU - Gopal, Sucharita
AU - Irons, James R.
AU - Strahler, Alan H.
N1 - Funding Information:
This work was partiallyf undedb y USRA Visiting Scientist Programd uringt hef irst author'sv isitto GoddardS paceF light Center,M aryland,J une-Augus1t 993. SucharitaG opal'sr e-searchis supportedb y a grantf romN ationalS cienceF ounda-tion (SBR-9300633A)l.a nS trahler'ps articipationw asp artially supportedb y NASA ContractN AS5-31369(E arth Observing SystemM ODIS InstrumenTte am)T. he authorsw ouldl ike to thankt heA SASc lusters tafffo r theira ssistancien ASASd ata processingA.S ASo perationasr ef undedb yt heT errestriaEl col-ogyP rogramM, issionsto PlanetE arthO 2~iceN,A SAH eadquar-tersu nderR TOP No. 462-75-02.
PY - 1996/8
Y1 - 1996/8
N2 - Because the anisotropy of the Earth's surface reflectance is strongly influenced by vegetation cover, multidirectional remotely sensed data can be highly effective in discriminating among land cover classes. This article explores the use of multiangle and multispectral data from the Advanced Solid-State Array Spectroradiometer (ASAS) in land cover mapping using artificial neural networks. A multilayer feed-forward network is trained to identify five land cover classes in Voyageurs National Park, Minnesota. Multiangle data achieve 89% of accuracy when applied to a single band (774- 790 nm), 7-directional imagery and 88% accuracy when applied to multispectral nadir data. Analysis of error using the confusion matrix indicated that the higher classification accuracy is obtained primarily for three classes: deciduous forest, wetlands, and water. The results suggest that 1) directional radiance measurements contain much useful information for discrimination among land cover classes, 2) the incorporation of more than one spectral multiangle band improves the overall classification accuracy compared to a single multiangle band, and 3) neural networks can successfully learn class discriminations from directional radiance data and/or multidomain data.
AB - Because the anisotropy of the Earth's surface reflectance is strongly influenced by vegetation cover, multidirectional remotely sensed data can be highly effective in discriminating among land cover classes. This article explores the use of multiangle and multispectral data from the Advanced Solid-State Array Spectroradiometer (ASAS) in land cover mapping using artificial neural networks. A multilayer feed-forward network is trained to identify five land cover classes in Voyageurs National Park, Minnesota. Multiangle data achieve 89% of accuracy when applied to a single band (774- 790 nm), 7-directional imagery and 88% accuracy when applied to multispectral nadir data. Analysis of error using the confusion matrix indicated that the higher classification accuracy is obtained primarily for three classes: deciduous forest, wetlands, and water. The results suggest that 1) directional radiance measurements contain much useful information for discrimination among land cover classes, 2) the incorporation of more than one spectral multiangle band improves the overall classification accuracy compared to a single multiangle band, and 3) neural networks can successfully learn class discriminations from directional radiance data and/or multidomain data.
UR - http://www.scopus.com/inward/record.url?scp=0030302438&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0030302438&partnerID=8YFLogxK
U2 - 10.1016/0034-4257(95)00197-2
DO - 10.1016/0034-4257(95)00197-2
M3 - Article
AN - SCOPUS:0030302438
SN - 0034-4257
VL - 57
SP - 79
EP - 87
JO - Remote Sensing of Environment
JF - Remote Sensing of Environment
IS - 2
ER -