Detection of Tree Species in Beijing Plain Afforestation Project Using Satellite Sensors and Machine Learning Algorithms
Mapping tree species distributions in urban areas is significant for managing afforestation plans and pest infestations but can be challenging over large areas. This research compared the classification accuracy of three data sources and three machine learning algorithm combinations. It evaluated th...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Forests |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4907/14/9/1889 |
| _version_ | 1797580006606503936 |
|---|---|
| author | Xudong Zhang Linfeng Yu Quan Zhou Dewei Wu Lili Ren Youqing Luo |
| author_facet | Xudong Zhang Linfeng Yu Quan Zhou Dewei Wu Lili Ren Youqing Luo |
| author_sort | Xudong Zhang |
| collection | DOAJ |
| description | Mapping tree species distributions in urban areas is significant for managing afforestation plans and pest infestations but can be challenging over large areas. This research compared the classification accuracy of three data sources and three machine learning algorithm combinations. It evaluated the cost benefit of various combinations by mapping the species distribution of the Beijing Plain Afforestation Project with a three-level hierarchical approach. First, vegetation and non-vegetation were mapped. Then, tree crowns were extracted from the vegetation mask. Finally, Decision Tree (DT), Support Vector Machines (SVM), and Random Forest (RF) were applied to the three data sources: Pléiades-1B, WorldView-2, and Sentinel-2. The tree species classification was based on the original bands and spectral and texture indices. Sentinel-2 performed well at the stand level, with an overall accuracy of 89.29%. WorldView-2 was significantly better than Pléiades-1 at the single-tree identification level. The combination of WorldView-2 and SVM achieved the best classification result, with an overall accuracy of 90.91%. This research concludes that the low-resolution Sentinel-2 sensor can accurately map tree areas while performing satisfactorily in classifying pure forests. For mixed forests, on the other hand, WorldView-2 and Pléiades-1, which have higher resolutions, are needed for single-tree scale classification. Compared to Pléiades-1, WorldView-2 produced higher classification accuracy. In addition, this study combines algorithm comparison to provide further reference and guidance for plantation forest classification. |
| first_indexed | 2024-03-10T22:44:12Z |
| format | Article |
| id | doaj.art-46ef7a2c663742e9a29e02e90e1eb640 |
| institution | Directory Open Access Journal |
| issn | 1999-4907 |
| language | English |
| last_indexed | 2024-03-10T22:44:12Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Forests |
| spelling | doaj.art-46ef7a2c663742e9a29e02e90e1eb6402023-11-19T10:47:26ZengMDPI AGForests1999-49072023-09-01149188910.3390/f14091889Detection of Tree Species in Beijing Plain Afforestation Project Using Satellite Sensors and Machine Learning AlgorithmsXudong Zhang0Linfeng Yu1Quan Zhou2Dewei Wu3Lili Ren4Youqing Luo5Beijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing 100083, ChinaBeijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing 100083, ChinaBeijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing 100083, ChinaBeijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing 100083, ChinaBeijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing 100083, ChinaBeijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing 100083, ChinaMapping tree species distributions in urban areas is significant for managing afforestation plans and pest infestations but can be challenging over large areas. This research compared the classification accuracy of three data sources and three machine learning algorithm combinations. It evaluated the cost benefit of various combinations by mapping the species distribution of the Beijing Plain Afforestation Project with a three-level hierarchical approach. First, vegetation and non-vegetation were mapped. Then, tree crowns were extracted from the vegetation mask. Finally, Decision Tree (DT), Support Vector Machines (SVM), and Random Forest (RF) were applied to the three data sources: Pléiades-1B, WorldView-2, and Sentinel-2. The tree species classification was based on the original bands and spectral and texture indices. Sentinel-2 performed well at the stand level, with an overall accuracy of 89.29%. WorldView-2 was significantly better than Pléiades-1 at the single-tree identification level. The combination of WorldView-2 and SVM achieved the best classification result, with an overall accuracy of 90.91%. This research concludes that the low-resolution Sentinel-2 sensor can accurately map tree areas while performing satisfactorily in classifying pure forests. For mixed forests, on the other hand, WorldView-2 and Pléiades-1, which have higher resolutions, are needed for single-tree scale classification. Compared to Pléiades-1, WorldView-2 produced higher classification accuracy. In addition, this study combines algorithm comparison to provide further reference and guidance for plantation forest classification.https://www.mdpi.com/1999-4907/14/9/1889Sentinel-2Pléiades-1WorldView-2machine learningafforestation |
| spellingShingle | Xudong Zhang Linfeng Yu Quan Zhou Dewei Wu Lili Ren Youqing Luo Detection of Tree Species in Beijing Plain Afforestation Project Using Satellite Sensors and Machine Learning Algorithms Forests Sentinel-2 Pléiades-1 WorldView-2 machine learning afforestation |
| title | Detection of Tree Species in Beijing Plain Afforestation Project Using Satellite Sensors and Machine Learning Algorithms |
| title_full | Detection of Tree Species in Beijing Plain Afforestation Project Using Satellite Sensors and Machine Learning Algorithms |
| title_fullStr | Detection of Tree Species in Beijing Plain Afforestation Project Using Satellite Sensors and Machine Learning Algorithms |
| title_full_unstemmed | Detection of Tree Species in Beijing Plain Afforestation Project Using Satellite Sensors and Machine Learning Algorithms |
| title_short | Detection of Tree Species in Beijing Plain Afforestation Project Using Satellite Sensors and Machine Learning Algorithms |
| title_sort | detection of tree species in beijing plain afforestation project using satellite sensors and machine learning algorithms |
| topic | Sentinel-2 Pléiades-1 WorldView-2 machine learning afforestation |
| url | https://www.mdpi.com/1999-4907/14/9/1889 |
| work_keys_str_mv | AT xudongzhang detectionoftreespeciesinbeijingplainafforestationprojectusingsatellitesensorsandmachinelearningalgorithms AT linfengyu detectionoftreespeciesinbeijingplainafforestationprojectusingsatellitesensorsandmachinelearningalgorithms AT quanzhou detectionoftreespeciesinbeijingplainafforestationprojectusingsatellitesensorsandmachinelearningalgorithms AT deweiwu detectionoftreespeciesinbeijingplainafforestationprojectusingsatellitesensorsandmachinelearningalgorithms AT liliren detectionoftreespeciesinbeijingplainafforestationprojectusingsatellitesensorsandmachinelearningalgorithms AT youqingluo detectionoftreespeciesinbeijingplainafforestationprojectusingsatellitesensorsandmachinelearningalgorithms |