Naslov
Accuracy Assessment of Remotely Sensed Data in Vegetation Mapping Process

Autori
Peternel, Hrvoje ; Kušan, Vladimir ; Antonić, Oleg ; Pernar, Renata ; Jelaska, Sven D.

Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, sažetak, znanstveni

Izvornik
Zbornik sažetaka / Besendorfer, Višnja ; Kopjar, Nevenka ; Vidaković.Cifrek, Željka ; Tkalec, Mirta ; Bauer, Nataša ; Lukša, Žaklin - Zagreb : Hrvatsko biološko društvo, 2009, 141-142

ISBN
978-953-6241-07-1

Skup
10. Hrvatski biološki kongres

Mjesto i datum
Osijek, Hrvatska, 14.09.2009. - 20.09.2009

Vrsta sudjelovanja
Poster

Vrsta recenzije
Domaća recenzija

Ključne riječi
accuracy assessment; GIS; kappa statistics; remote sensing; vegetation mapping

Sažetak
Vegetation is a fundamental variable that affects and links many parts of physical environments. Changes in vegetation cover have significant effects on basic processes (biogeochemical cycling, soil erosion) and thereby on biodiversity. The accurate and up-to-date information about land cover changes is necessary for understanding and assessment of the environmental consequences of such changes. In this study the thematic accuracy of classification of remotely sensed data in vegetation mapping process has been computed. The investigation area included the Nature Park &laquo ; Žumberak – Samoborsko gorje&raquo ; . Tree thematic maps with different minimum mapping units were used (2.25 ha, 9 ha, 25 ha). Error matrix was used to compute overall accuracy, producer's accuracy, user's accuracy, and omission and commission errors. The Kappa statistics, which is based on the difference between the actual agreement in the error matrix and the chance agreement, was used to compute KHAT values. Accuracy assessment was carried out at two levels: Level I – 2 categories: nonforest and forest habitats, and Level II – 5 categories: anthropogenic habitats, nonforest vegetation, fir forests, conifer forests, oak forests. The results show that overall accuracy ranges from 49% to 94%, and that KHAT values range from 29, 89% to 87.06%. This study shows that the accuracy of classification of remotely sensed data depends on both the minimum mapping unit and the number of categories used in classification scheme.

Izvorni jezik
Engleski

Znanstvena područja
Geologija, Biologija, Šumarstvo

POVEZANOST RADA