Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 1131853

Sentinel-1 and 2 Time-Series for Vegetation Mapping Using Random Forest Classification: A Case Study of Northern Croatia


Dobrinić, Dino; Gašparović, Mateo; Medak, Damir
Sentinel-1 and 2 Time-Series for Vegetation Mapping Using Random Forest Classification: A Case Study of Northern Croatia // Remote sensing, 13 (2021), 12; 1-20 doi:10.3390/rs13122321 (međunarodna recenzija, članak, znanstveni)


CROSBI ID: 1131853 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Sentinel-1 and 2 Time-Series for Vegetation Mapping Using Random Forest Classification: A Case Study of Northern Croatia

Autori
Dobrinić, Dino ; Gašparović, Mateo ; Medak, Damir

Izvornik
Remote sensing (2072-4292) 13 (2021), 12; 1-20

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
classification ; CORINE ; feature selection ; LUCAS ; MDA ; random forest ; SAR ; sentinel

Sažetak
Land-cover (LC) mapping in a morphologically heterogeneous landscape area is a challenging task since various LC classes (e.g., crop types in agricultural areas) are spectrally similar. Most research is still mostly relying on optical satellite imagery for these tasks, whereas synthetic aperture radar (SAR) imagery is often neglected. Therefore, this research assessed the classification accuracy using the recent Sentinel-1 (S1) SAR and Sentinel-2 (S2) time- series data for LC mapping, especially vegetation classes. Additionally, ancillary data, such as texture features, spectral indices from S1 and S2, respectively, as well as digital elevation model (DEM), were used in different classification scenarios. Random Forest (RF) was used for classification tasks using a proposed hybrid reference dataset derived from European Land Use and Coverage Area Frame Survey (LUCAS), CORINE, and Land Parcel Identification Systems (LPIS) LC database. Based on the RF variable selection using Mean Decrease Accuracy (MDA), the combination of S1 and S2 data yielded the highest overall accuracy (OA) of 91.78%, with a total disagreement of 8.22%. The most pertinent features for vegetation mapping were GLCM Mean and Variance for S1, NDVI, along with Red and SWIR band for S2, whereas the digital elevation model produced major classification enhancement as an input feature. The results of this study demonstrated that the aforementioned approach (i.e., RF using a hybrid reference dataset) is well-suited for vegetation mapping using Sentinel imagery, which can be applied for large-scale LC classifications.

Izvorni jezik
Engleski

Znanstvena područja
Geodezija



POVEZANOST RADA


Projekti:
IP-2016-06-5621 - Geoprostorno praćenje zelene infrastrukture na temelju terestričkih, zračnih i satelitskih snimaka (GEMINI) (Medak, Damir, HRZZ - 2016-06) ( POIROT)

Ustanove:
Geodetski fakultet, Zagreb

Profili:

Avatar Url Damir Medak (autor)

Avatar Url Dino Dobrinić (autor)

Avatar Url Mateo Gašparović (autor)

Citiraj ovu publikaciju

Dobrinić, Dino; Gašparović, Mateo; Medak, Damir
Sentinel-1 and 2 Time-Series for Vegetation Mapping Using Random Forest Classification: A Case Study of Northern Croatia // Remote sensing, 13 (2021), 12; 1-20 doi:10.3390/rs13122321 (međunarodna recenzija, članak, znanstveni)
Dobrinić, D., Gašparović, M. & Medak, D. (2021) Sentinel-1 and 2 Time-Series for Vegetation Mapping Using Random Forest Classification: A Case Study of Northern Croatia. Remote sensing, 13 (12), 1-20 doi:10.3390/rs13122321.
@article{article, year = {2021}, pages = {1-20}, DOI = {10.3390/rs13122321}, keywords = {classification, CORINE, feature selection, LUCAS, MDA, random forest, SAR, sentinel}, journal = {Remote sensing}, doi = {10.3390/rs13122321}, volume = {13}, number = {12}, issn = {2072-4292}, title = {Sentinel-1 and 2 Time-Series for Vegetation Mapping Using Random Forest Classification: A Case Study of Northern Croatia}, keyword = {classification, CORINE, feature selection, LUCAS, MDA, random forest, SAR, sentinel} }
@article{article, year = {2021}, pages = {1-20}, DOI = {10.3390/rs13122321}, keywords = {classification, CORINE, feature selection, LUCAS, MDA, random forest, SAR, sentinel}, journal = {Remote sensing}, doi = {10.3390/rs13122321}, volume = {13}, number = {12}, issn = {2072-4292}, title = {Sentinel-1 and 2 Time-Series for Vegetation Mapping Using Random Forest Classification: A Case Study of Northern Croatia}, keyword = {classification, CORINE, feature selection, LUCAS, MDA, random forest, SAR, sentinel} }

Časopis indeksira:


  • Current Contents Connect (CCC)
  • Web of Science Core Collection (WoSCC)
    • Science Citation Index Expanded (SCI-EXP)
    • SCI-EXP, SSCI i/ili A&HCI
  • Scopus


Citati





    Contrast
    Increase Font
    Decrease Font
    Dyslexic Font