Machine Learning Techniques for Land Use/Land Cover Classification of Medium Resolution Optical Satellite Imagery Focusing on Temporary Inundated Areas
Classification of multispectral optical satellite data using machine learning techniques to derive land use/land cover thematic data is important for many applications. Comparing the latest algorithms, our research aims to determine the best option to classify land use/land cover with special focus...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Szeged
2020-04-01
|
| Series: | Journal of Environmental Geography |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/jengeo-2020-0005 |
| _version_ | 1818245908748304384 |
|---|---|
| author | van Leeuwen Boudewijn Tobak Zalán Kovács Ferenc |
| author_facet | van Leeuwen Boudewijn Tobak Zalán Kovács Ferenc |
| author_sort | van Leeuwen Boudewijn |
| collection | DOAJ |
| description | Classification of multispectral optical satellite data using machine learning techniques to derive land use/land cover thematic data is important for many applications. Comparing the latest algorithms, our research aims to determine the best option to classify land use/land cover with special focus on temporary inundated land in a flat area in the south of Hungary. These inundations disrupt agricultural practices and can cause large financial loss. Sentinel 2 data with a high temporal and medium spatial resolution is classified using open source implementations of a random forest, support vector machine and an artificial neural network. Each classification model is applied to the same data set and the results are compared qualitatively and quantitatively. The accuracy of the results is high for all methods and does not show large overall differences. A quantitative spatial comparison demonstrates that the neural network gives the best results, but that all models are strongly influenced by atmospheric disturbances in the image. |
| first_indexed | 2024-12-12T14:40:24Z |
| format | Article |
| id | doaj.art-f4bfd4bdb90e4c1c86321073928e3ef2 |
| institution | Directory Open Access Journal |
| issn | 2060-467X |
| language | English |
| last_indexed | 2024-12-12T14:40:24Z |
| publishDate | 2020-04-01 |
| publisher | University of Szeged |
| record_format | Article |
| series | Journal of Environmental Geography |
| spelling | doaj.art-f4bfd4bdb90e4c1c86321073928e3ef22022-12-22T00:21:15ZengUniversity of SzegedJournal of Environmental Geography2060-467X2020-04-01131-2435210.2478/jengeo-2020-0005jengeo-2020-0005Machine Learning Techniques for Land Use/Land Cover Classification of Medium Resolution Optical Satellite Imagery Focusing on Temporary Inundated Areasvan Leeuwen Boudewijn0Tobak Zalán1Kovács Ferenc2Department of Physical Geography and Geoinformatics, University of Szeged, Egyetem u. 2-6, 6722 Szeged, HungaryDepartment of Physical Geography and Geoinformatics, University of Szeged, Egyetem u. 2-6, 6722 Szeged, HungaryDepartment of Physical Geography and Geoinformatics, University of Szeged, Egyetem u. 2-6, 6722 Szeged, HungaryClassification of multispectral optical satellite data using machine learning techniques to derive land use/land cover thematic data is important for many applications. Comparing the latest algorithms, our research aims to determine the best option to classify land use/land cover with special focus on temporary inundated land in a flat area in the south of Hungary. These inundations disrupt agricultural practices and can cause large financial loss. Sentinel 2 data with a high temporal and medium spatial resolution is classified using open source implementations of a random forest, support vector machine and an artificial neural network. Each classification model is applied to the same data set and the results are compared qualitatively and quantitatively. The accuracy of the results is high for all methods and does not show large overall differences. A quantitative spatial comparison demonstrates that the neural network gives the best results, but that all models are strongly influenced by atmospheric disturbances in the image.https://doi.org/10.2478/jengeo-2020-0005sentinel 2artificial neural networkrandom forestsupport vector machinemachine learningclassification |
| spellingShingle | van Leeuwen Boudewijn Tobak Zalán Kovács Ferenc Machine Learning Techniques for Land Use/Land Cover Classification of Medium Resolution Optical Satellite Imagery Focusing on Temporary Inundated Areas Journal of Environmental Geography sentinel 2 artificial neural network random forest support vector machine machine learning classification |
| title | Machine Learning Techniques for Land Use/Land Cover Classification of Medium Resolution Optical Satellite Imagery Focusing on Temporary Inundated Areas |
| title_full | Machine Learning Techniques for Land Use/Land Cover Classification of Medium Resolution Optical Satellite Imagery Focusing on Temporary Inundated Areas |
| title_fullStr | Machine Learning Techniques for Land Use/Land Cover Classification of Medium Resolution Optical Satellite Imagery Focusing on Temporary Inundated Areas |
| title_full_unstemmed | Machine Learning Techniques for Land Use/Land Cover Classification of Medium Resolution Optical Satellite Imagery Focusing on Temporary Inundated Areas |
| title_short | Machine Learning Techniques for Land Use/Land Cover Classification of Medium Resolution Optical Satellite Imagery Focusing on Temporary Inundated Areas |
| title_sort | machine learning techniques for land use land cover classification of medium resolution optical satellite imagery focusing on temporary inundated areas |
| topic | sentinel 2 artificial neural network random forest support vector machine machine learning classification |
| url | https://doi.org/10.2478/jengeo-2020-0005 |
| work_keys_str_mv | AT vanleeuwenboudewijn machinelearningtechniquesforlanduselandcoverclassificationofmediumresolutionopticalsatelliteimageryfocusingontemporaryinundatedareas AT tobakzalan machinelearningtechniquesforlanduselandcoverclassificationofmediumresolutionopticalsatelliteimageryfocusingontemporaryinundatedareas AT kovacsferenc machinelearningtechniquesforlanduselandcoverclassificationofmediumresolutionopticalsatelliteimageryfocusingontemporaryinundatedareas |