Kan vi skille mellom vanlig gran og sitka gran?

see this website Fremmede treslag kan sees som en trussel mot biologisk mangfold, og dette gir et behov for kartlegging og overvåking av forekomster av slike treslag. Fjernmåling har blitt foreslått som en verktøy for en slik kartlegging og overvåking, og i denne studien tester vi muligheten for å skille mellom to granarter ved hjelp av Lansat 8 satelittbilder, flyfoto og flybåren laserskanner. Feltobservasjoner fra skogbestand dominert av enten norsk gran (Picea abies) eller sitkagran (Picea sitchensis) ble koblet med variabler ekstrahert fra de fjernmålte dataene. Tre ulike klassifiseringsmetoder ble sammenlignet: “random forest” “support vector machine” og logistisk regresjon. Nøyaktigheten på klassifiseringen ble evaluert gjennom en kryssvalidering, og ulike kombinasjoner av klassifiseringsmetode og type fjernmålingsdata ble undersøkt. Nøyaktigheten varierte mellom 53% og 79% med den høyeste nøyaktigheten ved bruk av satelittbilder i kombinasjon med flybilder. Effekten av å inkludere data fra flybårne sensorer i tillegg til satelittdata var imidlertid ikke veldig stor i denne studien. Videre fant vi at klassifiseringen varierte ved bruk av ulike Landsat 8 satelittbilder.

buy Tinidazole Referanse:

  • [DOI] M. Hauglin and H. O. Ørka, “Discriminating between native norway spruce and invasive sitka spruce—a comparison of multitemporal landsat 8 imagery, aerial images and airborne laser scanner data,” Remote sensing, vol. 8, iss. 5, p. 363, 2016.
    [Bibtex] [Abstract] [Download PDF]

    Invasive species can be considered a threat to biodiversity, and remote sensing has been proposed as a tool for detection and monitoring of invasive species. In this study, we test the ability to discriminate between two tree species of the same genera, using data from Landsat 8 satellite imagery, aerial images, and airborne laser scanning. Ground observations from forest stands dominated by either Norway spruce (Picea abies) or Sitka spruce (Picea sitchensis) were coupled with variables derived from each of the three sets of remote sensing data. Random forest, support vector machine, and logistic regression classification models were fit to the data, and the classification accuracy tested by performing a cross-validation. Classification accuracies were compared for different combinations of remote sensing data and classification methods. The overall classification accuracy varied from 0.53 to 0.79, with the highest accuracy obtained using logistic regression with a combination of data derived from Landsat imagery and aerial images. The corresponding kappa value was 0.58. The contribution to the classification accuracy from using airborne data in addition to Landsat imagery was not substantial in this study. The classification accuracy varied between models using data from individual Landsat images.

    @Article{Hauglin2016,
    Title = {Discriminating between Native Norway Spruce and Invasive Sitka Spruce—A Comparison of Multitemporal Landsat 8 Imagery, Aerial Images and Airborne Laser Scanner Data},
    Author = {Hauglin, Marius and Ørka, Hans Ole},
    Journal = {Remote Sensing},
    Year = {2016},
    Number = {5},
    Pages = {363},
    Volume = {8},
    Abstract = {Invasive species can be considered a threat to biodiversity, and remote sensing has been proposed as a tool for detection and monitoring of invasive species. In this study, we test the ability to discriminate between two tree species of the same genera, using data from Landsat 8 satellite imagery, aerial images, and airborne laser scanning. Ground observations from forest stands dominated by either Norway spruce (Picea abies) or Sitka spruce (Picea sitchensis) were coupled with variables derived from each of the three sets of remote sensing data. Random forest, support vector machine, and logistic regression classification models were fit to the data, and the classification accuracy tested by performing a cross-validation. Classification accuracies were compared for different combinations of remote sensing data and classification methods. The overall classification accuracy varied from 0.53 to 0.79, with the highest accuracy obtained using logistic regression with a combination of data derived from Landsat imagery and aerial images. The corresponding kappa value was 0.58. The contribution to the classification accuracy from using airborne data in addition to Landsat imagery was not substantial in this study. The classification accuracy varied between models using data from individual Landsat images.},
    Doi = {10.3390/rs8050363},
    ISSN = {2072-4292},
    Owner = {hanso},
    Timestamp = {2016.09.28},
    Url = {http://www.mdpi.com/2072-4292/8/5/363}
    }

Leave a Reply

Your email address will not be published. Required fields are marked *