ELULC‐10, a 10 m European Land Use and Land Cover Map Using Sentinel and Landsat Data in Google Earth Engine
(2022) In Remote Sensing 14(13).- Abstract
Land Use/Land Cover (LULC) maps can be effectively produced by cost‐effective and frequent satellite observations. Powerful cloud computing platforms are emerging as a growing trend in the high utilization of freely accessible remotely sensed data for LULC mapping over largescale regions using big geodata. This study proposes a workflow to generate a 10 m LULC map of Europe with nine classes, ELULC‐10, using European Sentinel‐1/‐2 and Landsat‐8 images, as well as the LUCAS reference samples. More than 200 K and 300 K of in situ surveys and images, respectively, were employed as inputs in the Google Earth Engine (GEE) cloud computing platform to perform classification by an object‐based segmentation algorithm and an Artificial Neural... (More)
Land Use/Land Cover (LULC) maps can be effectively produced by cost‐effective and frequent satellite observations. Powerful cloud computing platforms are emerging as a growing trend in the high utilization of freely accessible remotely sensed data for LULC mapping over largescale regions using big geodata. This study proposes a workflow to generate a 10 m LULC map of Europe with nine classes, ELULC‐10, using European Sentinel‐1/‐2 and Landsat‐8 images, as well as the LUCAS reference samples. More than 200 K and 300 K of in situ surveys and images, respectively, were employed as inputs in the Google Earth Engine (GEE) cloud computing platform to perform classification by an object‐based segmentation algorithm and an Artificial Neural Network (ANN). A novel ANN‐based data preparation was also presented to remove noisy reference samples from the LUCAS dataset. Additionally, the map was improved using several rule‐based postprocessing steps. The overall accuracy and kappa coefficient of 2021 ELULC‐10 were 95.38% and 0.94, respectively. A detailed report of the classification accuracies was also provided, demonstrating an accurate classification of different classes, such as Woodland and Cropland. Furthermore, rule‐based post processing improved LULC class identifications when compared with current studies. The workflow could also supply seasonal, yearly, and change maps considering the proposed integration of complex machine learning algorithms and large satellite and survey data.
(Less)
- author
- Mirmazloumi, S. Mohammad ; Kakooei, Mohammad ; Mohseni, Farzane LU ; Ghorbanian, Arsalan LU ; Amani, Meisam ; Crosetto, Michele and Monserrat, Oriol
- organization
- publishing date
- 2022-07-01
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Europe, Google Earth Engine, Landsat‐8, LUCAS, LULC, remote sensing, Sentinel
- in
- Remote Sensing
- volume
- 14
- issue
- 13
- article number
- 3041
- publisher
- MDPI AG
- external identifiers
-
- scopus:85133246977
- ISSN
- 2072-4292
- DOI
- 10.3390/rs14133041
- language
- English
- LU publication?
- yes
- id
- 14529ac8-e142-4631-9d44-3872ccf49ae7
- date added to LUP
- 2022-09-22 15:32:39
- date last changed
- 2023-11-28 14:02:35
@article{14529ac8-e142-4631-9d44-3872ccf49ae7, abstract = {{<p>Land Use/Land Cover (LULC) maps can be effectively produced by cost‐effective and frequent satellite observations. Powerful cloud computing platforms are emerging as a growing trend in the high utilization of freely accessible remotely sensed data for LULC mapping over largescale regions using big geodata. This study proposes a workflow to generate a 10 m LULC map of Europe with nine classes, ELULC‐10, using European Sentinel‐1/‐2 and Landsat‐8 images, as well as the LUCAS reference samples. More than 200 K and 300 K of in situ surveys and images, respectively, were employed as inputs in the Google Earth Engine (GEE) cloud computing platform to perform classification by an object‐based segmentation algorithm and an Artificial Neural Network (ANN). A novel ANN‐based data preparation was also presented to remove noisy reference samples from the LUCAS dataset. Additionally, the map was improved using several rule‐based postprocessing steps. The overall accuracy and kappa coefficient of 2021 ELULC‐10 were 95.38% and 0.94, respectively. A detailed report of the classification accuracies was also provided, demonstrating an accurate classification of different classes, such as Woodland and Cropland. Furthermore, rule‐based post processing improved LULC class identifications when compared with current studies. The workflow could also supply seasonal, yearly, and change maps considering the proposed integration of complex machine learning algorithms and large satellite and survey data.</p>}}, author = {{Mirmazloumi, S. Mohammad and Kakooei, Mohammad and Mohseni, Farzane and Ghorbanian, Arsalan and Amani, Meisam and Crosetto, Michele and Monserrat, Oriol}}, issn = {{2072-4292}}, keywords = {{Europe; Google Earth Engine; Landsat‐8; LUCAS; LULC; remote sensing; Sentinel}}, language = {{eng}}, month = {{07}}, number = {{13}}, publisher = {{MDPI AG}}, series = {{Remote Sensing}}, title = {{ELULC‐10, a 10 m European Land Use and Land Cover Map Using Sentinel and Landsat Data in Google Earth Engine}}, url = {{http://dx.doi.org/10.3390/rs14133041}}, doi = {{10.3390/rs14133041}}, volume = {{14}}, year = {{2022}}, }