Identification of Riparian Vegetation Types with Machine Learning Based on LiDAR Point-Cloud Made Along the Lower Tisza’s Floodplain
The very dense floodplain vegetation on the artificially confined floodplains results in decreased flood conveyance, thus increase in flood levels and flood hazard. Therefore, proper floodplain management is needed, which must be supported by vegetation assessment studies. The aims of the paper are...
| 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-2020-0006 |
| _version_ | 1828472348360048640 |
|---|---|
| author | Fehérváry István Kiss Tímea |
| author_facet | Fehérváry István Kiss Tímea |
| author_sort | Fehérváry István |
| collection | DOAJ |
| description | The very dense floodplain vegetation on the artificially confined floodplains results in decreased flood conveyance, thus increase in flood levels and flood hazard. Therefore, proper floodplain management is needed, which must be supported by vegetation assessment studies. The aims of the paper are to introduce the method and the results of riparian vegetation classification of a floodplain area along the Lower Tisza (Hungary) based on automatized acquisition of airborne LiDAR survey. In the study area 15x15 m large training plots (voxels) were selected, and the statistical parameters of their LiDAR point clouds were determined. Applying an automatized parameter selection and 10-fold cross-validation he most suitable decision tree was selected, and following a series of classification steps the training plots were classified. Based on the decision tree all the pixels of the entire study area were analysed and their vegetation types were determined. The classification was validated by field survey. On the studied floodplain area the accuracy of the classification was 83%. |
| first_indexed | 2024-12-11T05:27:34Z |
| format | Article |
| id | doaj.art-4166b4032ec14fab86fdf7590c196c49 |
| institution | Directory Open Access Journal |
| issn | 2060-467X |
| language | English |
| last_indexed | 2024-12-11T05:27:34Z |
| publishDate | 2020-04-01 |
| publisher | University of Szeged |
| record_format | Article |
| series | Journal of Environmental Geography |
| spelling | doaj.art-4166b4032ec14fab86fdf7590c196c492022-12-22T01:19:31ZengUniversity of SzegedJournal of Environmental Geography2060-467X2020-04-01131-2536110.2478/jengeo-2020-0006jengeo-2020-0006Identification of Riparian Vegetation Types with Machine Learning Based on LiDAR Point-Cloud Made Along the Lower Tisza’s FloodplainFehérváry István0Kiss Tímea1Lower Tisza Hydrological Directorate, Stefánia 4, 6720 Szeged, HungaryUniversity of Szeged, Department of Physical Geography and Geoinformatics, Egyetem str. 2-6, 6722 Szeged, HungaryThe very dense floodplain vegetation on the artificially confined floodplains results in decreased flood conveyance, thus increase in flood levels and flood hazard. Therefore, proper floodplain management is needed, which must be supported by vegetation assessment studies. The aims of the paper are to introduce the method and the results of riparian vegetation classification of a floodplain area along the Lower Tisza (Hungary) based on automatized acquisition of airborne LiDAR survey. In the study area 15x15 m large training plots (voxels) were selected, and the statistical parameters of their LiDAR point clouds were determined. Applying an automatized parameter selection and 10-fold cross-validation he most suitable decision tree was selected, and following a series of classification steps the training plots were classified. Based on the decision tree all the pixels of the entire study area were analysed and their vegetation types were determined. The classification was validated by field survey. On the studied floodplain area the accuracy of the classification was 83%.https://doi.org/10.2478/jengeo-2020-0006airborne lidarscikit-learngini impuritydecision treeriparian forest |
| spellingShingle | Fehérváry István Kiss Tímea Identification of Riparian Vegetation Types with Machine Learning Based on LiDAR Point-Cloud Made Along the Lower Tisza’s Floodplain Journal of Environmental Geography airborne lidar scikit-learn gini impurity decision tree riparian forest |
| title | Identification of Riparian Vegetation Types with Machine Learning Based on LiDAR Point-Cloud Made Along the Lower Tisza’s Floodplain |
| title_full | Identification of Riparian Vegetation Types with Machine Learning Based on LiDAR Point-Cloud Made Along the Lower Tisza’s Floodplain |
| title_fullStr | Identification of Riparian Vegetation Types with Machine Learning Based on LiDAR Point-Cloud Made Along the Lower Tisza’s Floodplain |
| title_full_unstemmed | Identification of Riparian Vegetation Types with Machine Learning Based on LiDAR Point-Cloud Made Along the Lower Tisza’s Floodplain |
| title_short | Identification of Riparian Vegetation Types with Machine Learning Based on LiDAR Point-Cloud Made Along the Lower Tisza’s Floodplain |
| title_sort | identification of riparian vegetation types with machine learning based on lidar point cloud made along the lower tisza s floodplain |
| topic | airborne lidar scikit-learn gini impurity decision tree riparian forest |
| url | https://doi.org/10.2478/jengeo-2020-0006 |
| work_keys_str_mv | AT fehervaryistvan identificationofriparianvegetationtypeswithmachinelearningbasedonlidarpointcloudmadealongthelowertiszasfloodplain AT kisstimea identificationofriparianvegetationtypeswithmachinelearningbasedonlidarpointcloudmadealongthelowertiszasfloodplain |