Using machine learning to produce a very high resolution land-cover map for Ireland
<p>Land-cover classifications in the form of maps are required for numerical modelling of weather and climate. Such maps are often of coarse resolution and are infrequently updated. Here we propose a novel approach for land-cover classification using a Convolutional Neural Network machine lear...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2021-05-01
|
| Series: | Advances in Science and Research |
| Online Access: | https://asr.copernicus.org/articles/18/65/2021/asr-18-65-2021.pdf |
| _version_ | 1818832960946700288 |
|---|---|
| author | E. Walsh G. Bessardon E. Gleeson P. Ulmas |
| author_facet | E. Walsh G. Bessardon E. Gleeson P. Ulmas |
| author_sort | E. Walsh |
| collection | DOAJ |
| description | <p>Land-cover classifications in the form of maps are required for numerical modelling of weather and climate. Such maps are often of coarse resolution and are infrequently updated. Here we propose a novel approach for land-cover classification using a Convolutional Neural Network machine learning algorithm to segment satellite images into various land-cover classes. Sentinel-2 satellite imagery, the CORINE land-cover database and the BigEarthNet dataset are used. A 10 m resolution map, called the Ulmas-Walsh map, has been created for Ireland that outperforms ECO-SG in terms of accuracy, as well as demonstrating a capacity for identifying features not labelled correctly in CORINE. The map can be updated on demand for any time of the year, subject to cloud cover. This is particularly useful for regions with large seasonal variation in land classifications such as Turloughs – seasonal lakes, flood plains and rotational crops.</p> |
| first_indexed | 2024-12-19T02:11:20Z |
| format | Article |
| id | doaj.art-c17d1b74e6254c9d9da726c29c77ba7a |
| institution | Directory Open Access Journal |
| issn | 1992-0628 1992-0636 |
| language | English |
| last_indexed | 2024-12-19T02:11:20Z |
| publishDate | 2021-05-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Advances in Science and Research |
| spelling | doaj.art-c17d1b74e6254c9d9da726c29c77ba7a2022-12-21T20:40:44ZengCopernicus PublicationsAdvances in Science and Research1992-06281992-06362021-05-0118658710.5194/asr-18-65-2021Using machine learning to produce a very high resolution land-cover map for IrelandE. Walsh0G. Bessardon1E. Gleeson2P. Ulmas3SFI Center for Research Training in Foundations of Data Science, University of Limerick, Limerick, V94 T9PX, IrelandClimate Services, Research and Applications Division, Met Éireann, 65/67 Glasnevin Hill, Dublin 9, D09 Y921, IrelandClimate Services, Research and Applications Division, Met Éireann, 65/67 Glasnevin Hill, Dublin 9, D09 Y921, IrelandNeurisium OÜ, Kaupmehe 7-A10, 10114 Tallinn, Estonia<p>Land-cover classifications in the form of maps are required for numerical modelling of weather and climate. Such maps are often of coarse resolution and are infrequently updated. Here we propose a novel approach for land-cover classification using a Convolutional Neural Network machine learning algorithm to segment satellite images into various land-cover classes. Sentinel-2 satellite imagery, the CORINE land-cover database and the BigEarthNet dataset are used. A 10 m resolution map, called the Ulmas-Walsh map, has been created for Ireland that outperforms ECO-SG in terms of accuracy, as well as demonstrating a capacity for identifying features not labelled correctly in CORINE. The map can be updated on demand for any time of the year, subject to cloud cover. This is particularly useful for regions with large seasonal variation in land classifications such as Turloughs – seasonal lakes, flood plains and rotational crops.</p>https://asr.copernicus.org/articles/18/65/2021/asr-18-65-2021.pdf |
| spellingShingle | E. Walsh G. Bessardon E. Gleeson P. Ulmas Using machine learning to produce a very high resolution land-cover map for Ireland Advances in Science and Research |
| title | Using machine learning to produce a very high resolution land-cover map for Ireland |
| title_full | Using machine learning to produce a very high resolution land-cover map for Ireland |
| title_fullStr | Using machine learning to produce a very high resolution land-cover map for Ireland |
| title_full_unstemmed | Using machine learning to produce a very high resolution land-cover map for Ireland |
| title_short | Using machine learning to produce a very high resolution land-cover map for Ireland |
| title_sort | using machine learning to produce a very high resolution land cover map for ireland |
| url | https://asr.copernicus.org/articles/18/65/2021/asr-18-65-2021.pdf |
| work_keys_str_mv | AT ewalsh usingmachinelearningtoproduceaveryhighresolutionlandcovermapforireland AT gbessardon usingmachinelearningtoproduceaveryhighresolutionlandcovermapforireland AT egleeson usingmachinelearningtoproduceaveryhighresolutionlandcovermapforireland AT pulmas usingmachinelearningtoproduceaveryhighresolutionlandcovermapforireland |