Next Article in Journal
Remote Sensing-Based Analysis of Urban Landscape Change in the City of Bucharest, Romania
Next Article in Special Issue
Infrared and Visible Image Object Detection via Focused Feature Enhancement and Cascaded Semantic Extension
Previous Article in Journal
Evaluating Short-Term Tidal Flat Evolution Through UAV Surveys: A Case Study in the Po Delta (Italy)
Previous Article in Special Issue
An Interval Temporal Logic for Time Series Specification and Data Integration
Article

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

1
Chair of Geoinformatics, Faculty of Geodesy, University of Zagreb, 10000 Zagreb, Croatia
2
Chair of Photogrammetry and Remote Sensing, Faculty of Geodesy, University of Zagreb, 10000 Zagreb, Croatia
*
Author to whom correspondence should be addressed.
Academic Editor: Piotr Kaniewski
Remote Sens. 2021, 13(12), 2321; https://doi.org/10.3390/rs13122321
Received: 12 May 2021 / Revised: 9 June 2021 / Accepted: 10 June 2021 / Published: 13 June 2021
(This article belongs to the Special Issue Multi-Sensor Systems and Data Fusion in Remote Sensing)
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. View Full-Text
Keywords: classification; CORINE; feature selection; LUCAS; MDA; random forest; SAR; sentinel classification; CORINE; feature selection; LUCAS; MDA; random forest; SAR; sentinel
Show Figures

Graphical abstract

MDPI and ACS Style

Dobrinić, D.; Gašparović, M.; Medak, D. Sentinel-1 and 2 Time-Series for Vegetation Mapping Using Random Forest Classification: A Case Study of Northern Croatia. Remote Sens. 2021, 13, 2321. https://doi.org/10.3390/rs13122321

AMA Style

Dobrinić D, Gašparović M, Medak D. Sentinel-1 and 2 Time-Series for Vegetation Mapping Using Random Forest Classification: A Case Study of Northern Croatia. Remote Sensing. 2021; 13(12):2321. https://doi.org/10.3390/rs13122321

Chicago/Turabian Style

Dobrinić, Dino, Mateo Gašparović, and Damir Medak. 2021. "Sentinel-1 and 2 Time-Series for Vegetation Mapping Using Random Forest Classification: A Case Study of Northern Croatia" Remote Sensing 13, no. 12: 2321. https://doi.org/10.3390/rs13122321

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop