Tree Species Classification in Mixed Deciduous Forests Using Very High Spatial Resolution Satellite Imagery and Machine Learning Methods
Spatially explicit information on tree species composition is important for both the forest management and conservation sectors. In combination with machine learning algorithms, very high-resolution satellite imagery may provide an effective solution to reduce the need for labor-intensive and time-c...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/23/3926 |
| _version_ | 1797546170631847936 |
|---|---|
| author | Martina Deur Mateo Gašparović Ivan Balenović |
| author_facet | Martina Deur Mateo Gašparović Ivan Balenović |
| author_sort | Martina Deur |
| collection | DOAJ |
| description | Spatially explicit information on tree species composition is important for both the forest management and conservation sectors. In combination with machine learning algorithms, very high-resolution satellite imagery may provide an effective solution to reduce the need for labor-intensive and time-consuming field-based surveys. In this study, we evaluated the possibility of using multispectral WorldView-3 (WV-3) satellite imagery for the classification of three main tree species (<i>Quercus robur</i> L., <i>Carpinus betulus</i> L., and <i>Alnus glutinosa</i> (L.) Geartn.) in a lowland, mixed deciduous forest in central Croatia. The pixel-based supervised classification was performed using two machine learning algorithms: random forest (RF) and support vector machine (SVM). Additionally, the contribution of gray level cooccurrence matrix (GLCM) texture features from WV-3 imagery in tree species classification was evaluated. Principal component analysis confirmed GLCM variance to be the most significant texture feature. Of the 373 visually interpreted reference polygons, 237 were used as training polygons and 136 were used as validation polygons. The validation results show relatively high overall accuracy (85%) for tree species classification based solely on WV-3 spectral characteristics and the RF classification approach. As expected, an improvement in classification accuracy was achieved by a combination of spectral and textural features. With the additional use of GLCM variance, the overall accuracy improved by 10% and 7% for RF and SVM classification approaches, respectively. |
| first_indexed | 2024-03-10T14:26:16Z |
| format | Article |
| id | doaj.art-7a0314f6f60047e69ec84edfde4c05f0 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T14:26:16Z |
| publishDate | 2020-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-7a0314f6f60047e69ec84edfde4c05f02023-11-20T22:57:11ZengMDPI AGRemote Sensing2072-42922020-11-011223392610.3390/rs12233926Tree Species Classification in Mixed Deciduous Forests Using Very High Spatial Resolution Satellite Imagery and Machine Learning MethodsMartina Deur0Mateo Gašparović1Ivan Balenović2Institute for spatial planning of Šibenik-Knin County, Vladimira Nazora 1/IV, 22000 Šibenik, CroatiaChair of Photogrammetry and Remote Sensing, Faculty of Geodesy, University of Zagreb, 10000 Zagreb, CroatiaDivision for Forest Management and Forestry Economics, Croatian Forest Research Institute, Trnjanska cesta 35, HR-10000 Zagreb, CroatiaSpatially explicit information on tree species composition is important for both the forest management and conservation sectors. In combination with machine learning algorithms, very high-resolution satellite imagery may provide an effective solution to reduce the need for labor-intensive and time-consuming field-based surveys. In this study, we evaluated the possibility of using multispectral WorldView-3 (WV-3) satellite imagery for the classification of three main tree species (<i>Quercus robur</i> L., <i>Carpinus betulus</i> L., and <i>Alnus glutinosa</i> (L.) Geartn.) in a lowland, mixed deciduous forest in central Croatia. The pixel-based supervised classification was performed using two machine learning algorithms: random forest (RF) and support vector machine (SVM). Additionally, the contribution of gray level cooccurrence matrix (GLCM) texture features from WV-3 imagery in tree species classification was evaluated. Principal component analysis confirmed GLCM variance to be the most significant texture feature. Of the 373 visually interpreted reference polygons, 237 were used as training polygons and 136 were used as validation polygons. The validation results show relatively high overall accuracy (85%) for tree species classification based solely on WV-3 spectral characteristics and the RF classification approach. As expected, an improvement in classification accuracy was achieved by a combination of spectral and textural features. With the additional use of GLCM variance, the overall accuracy improved by 10% and 7% for RF and SVM classification approaches, respectively.https://www.mdpi.com/2072-4292/12/23/3926pixel-based supervised classificationrandom forestsupport vector machinegray level cooccurrence matrix (GLCM)principal component analysis (PCA)WorldView-3 |
| spellingShingle | Martina Deur Mateo Gašparović Ivan Balenović Tree Species Classification in Mixed Deciduous Forests Using Very High Spatial Resolution Satellite Imagery and Machine Learning Methods Remote Sensing pixel-based supervised classification random forest support vector machine gray level cooccurrence matrix (GLCM) principal component analysis (PCA) WorldView-3 |
| title | Tree Species Classification in Mixed Deciduous Forests Using Very High Spatial Resolution Satellite Imagery and Machine Learning Methods |
| title_full | Tree Species Classification in Mixed Deciduous Forests Using Very High Spatial Resolution Satellite Imagery and Machine Learning Methods |
| title_fullStr | Tree Species Classification in Mixed Deciduous Forests Using Very High Spatial Resolution Satellite Imagery and Machine Learning Methods |
| title_full_unstemmed | Tree Species Classification in Mixed Deciduous Forests Using Very High Spatial Resolution Satellite Imagery and Machine Learning Methods |
| title_short | Tree Species Classification in Mixed Deciduous Forests Using Very High Spatial Resolution Satellite Imagery and Machine Learning Methods |
| title_sort | tree species classification in mixed deciduous forests using very high spatial resolution satellite imagery and machine learning methods |
| topic | pixel-based supervised classification random forest support vector machine gray level cooccurrence matrix (GLCM) principal component analysis (PCA) WorldView-3 |
| url | https://www.mdpi.com/2072-4292/12/23/3926 |
| work_keys_str_mv | AT martinadeur treespeciesclassificationinmixeddeciduousforestsusingveryhighspatialresolutionsatelliteimageryandmachinelearningmethods AT mateogasparovic treespeciesclassificationinmixeddeciduousforestsusingveryhighspatialresolutionsatelliteimageryandmachinelearningmethods AT ivanbalenovic treespeciesclassificationinmixeddeciduousforestsusingveryhighspatialresolutionsatelliteimageryandmachinelearningmethods |