Examination of the performance of ASEL and MPViT algorithms for classifying mangrove species of multiple natural reserves of Beibu Gulf, south China
Mangrove is the highest productive ecosystems in the global coastal zone, which has high blue carbon sink function and carbon neutrality potential. Fine species classification is essential for mangrove conservation and sustainable development, and has attracted much attention in recent years using e...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-10-01
|
| Series: | Ecological Indicators |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1470160X23010129 |
| _version_ | 1797683047009615872 |
|---|---|
| author | Bolin Fu Xu He Yiyin Liang Tengfang Deng Huajian Li Hongchang He Mingming Jia Donglin Fan Feng Wang |
| author_facet | Bolin Fu Xu He Yiyin Liang Tengfang Deng Huajian Li Hongchang He Mingming Jia Donglin Fan Feng Wang |
| author_sort | Bolin Fu |
| collection | DOAJ |
| description | Mangrove is the highest productive ecosystems in the global coastal zone, which has high blue carbon sink function and carbon neutrality potential. Fine species classification is essential for mangrove conservation and sustainable development, and has attracted much attention in recent years using ensemble learning and multi-dimensional data. However, the current mangrove species classification based on traditional stacking ensemble learning still faces challenges due to the correlation between base classifiers, differences in meta-classifier capabilities, the subjectivity of parameter tuning, and data redundancy. To address these issues, this paper utilized unmanned aerial vehicle (UAV) multispectral images of three mangrove nature reserves in Beibu Gulf, south China, to examine the classification and generalization ability of our proposed Adaptive Stacking Ensemble Learning (ASEL) algorithm for different mangrove species. We also aim to verify the feasibility of the Multi-Path Vision Transformer for Dense Prediction (MPViT) algorithm for mangrove species mapping, and compare its performance with the ASEL algorithm for mangrove species classification. Finally, we used the SHapley Additive Explanations (SHAP) method to measure the contribution of feature variables to the model, exploring the sensitivity of different image features to mangrove species mapping. This study highlights that: (1) The two ASEL algorithms achieved high accuracy classification of mangrove species with the overall classification accuracy ranging from 79.8% to 96.2%. The ACE-Stacking and AOM-Stacking algorithms performed better classification ability than the traditional stacking algorithm, with the mean overall classification accuracy increasing from 0.9% to 3.3%. The McNemar test further indicated that the differences in classification results derived from three algorithms were significant at the 95% confidence interval, demonstrating the better classification and generalization ability of the ASEL algorithm. (2) The MPViT algorithm achieved better classification accuracy in the three reserves, with an overall accuracy of 95.5%-97.3%, which was 0.6%-5.4% higher than the two ASEL algorithms. The average accuracy of identifying mangrove species was over 95.3% in all reserves, demonstrating the desirable mangrove classification performance of MPViT algorithm. (3) The identification accuracies (F1 scores) of mangrove species in different reserves were ranged from 0.848 to 0.984. Cyperus malaccensi had the highest identification accuracy. (4) The SHAP method interpreted the great contribution of digital surface model and variable atmospherically resistant index features on mangrove species classification. The red band and ratio vegetation index was sensitive to Aegiceras corniculatum and to Cyperus malaccensi. |
| first_indexed | 2024-03-12T00:08:48Z |
| format | Article |
| id | doaj.art-0a48f17ce1fd4a858b72d97e005f5517 |
| institution | Directory Open Access Journal |
| issn | 1470-160X |
| language | English |
| last_indexed | 2024-03-12T00:08:48Z |
| publishDate | 2023-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Indicators |
| spelling | doaj.art-0a48f17ce1fd4a858b72d97e005f55172023-09-16T05:30:14ZengElsevierEcological Indicators1470-160X2023-10-01154110870Examination of the performance of ASEL and MPViT algorithms for classifying mangrove species of multiple natural reserves of Beibu Gulf, south ChinaBolin Fu0Xu He1Yiyin Liang2Tengfang Deng3Huajian Li4Hongchang He5Mingming Jia6Donglin Fan7Feng Wang8College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, China; Corresponding author.College of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, ChinaKey Laboratory of Wetland Ecology and Environment, Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130102, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, ChinaCollege of Geomatics and Geoinformation, Guilin University of Technology, Guilin 541006, ChinaMangrove is the highest productive ecosystems in the global coastal zone, which has high blue carbon sink function and carbon neutrality potential. Fine species classification is essential for mangrove conservation and sustainable development, and has attracted much attention in recent years using ensemble learning and multi-dimensional data. However, the current mangrove species classification based on traditional stacking ensemble learning still faces challenges due to the correlation between base classifiers, differences in meta-classifier capabilities, the subjectivity of parameter tuning, and data redundancy. To address these issues, this paper utilized unmanned aerial vehicle (UAV) multispectral images of three mangrove nature reserves in Beibu Gulf, south China, to examine the classification and generalization ability of our proposed Adaptive Stacking Ensemble Learning (ASEL) algorithm for different mangrove species. We also aim to verify the feasibility of the Multi-Path Vision Transformer for Dense Prediction (MPViT) algorithm for mangrove species mapping, and compare its performance with the ASEL algorithm for mangrove species classification. Finally, we used the SHapley Additive Explanations (SHAP) method to measure the contribution of feature variables to the model, exploring the sensitivity of different image features to mangrove species mapping. This study highlights that: (1) The two ASEL algorithms achieved high accuracy classification of mangrove species with the overall classification accuracy ranging from 79.8% to 96.2%. The ACE-Stacking and AOM-Stacking algorithms performed better classification ability than the traditional stacking algorithm, with the mean overall classification accuracy increasing from 0.9% to 3.3%. The McNemar test further indicated that the differences in classification results derived from three algorithms were significant at the 95% confidence interval, demonstrating the better classification and generalization ability of the ASEL algorithm. (2) The MPViT algorithm achieved better classification accuracy in the three reserves, with an overall accuracy of 95.5%-97.3%, which was 0.6%-5.4% higher than the two ASEL algorithms. The average accuracy of identifying mangrove species was over 95.3% in all reserves, demonstrating the desirable mangrove classification performance of MPViT algorithm. (3) The identification accuracies (F1 scores) of mangrove species in different reserves were ranged from 0.848 to 0.984. Cyperus malaccensi had the highest identification accuracy. (4) The SHAP method interpreted the great contribution of digital surface model and variable atmospherically resistant index features on mangrove species classification. The red band and ratio vegetation index was sensitive to Aegiceras corniculatum and to Cyperus malaccensi.http://www.sciencedirect.com/science/article/pii/S1470160X23010129Mangrove species classificationUAV multispectral imagesAdaptive stacking ensemble learning algorithmsMulti-Path Vision Transformer algorithmSHapley Additive explanations |
| spellingShingle | Bolin Fu Xu He Yiyin Liang Tengfang Deng Huajian Li Hongchang He Mingming Jia Donglin Fan Feng Wang Examination of the performance of ASEL and MPViT algorithms for classifying mangrove species of multiple natural reserves of Beibu Gulf, south China Ecological Indicators Mangrove species classification UAV multispectral images Adaptive stacking ensemble learning algorithms Multi-Path Vision Transformer algorithm SHapley Additive explanations |
| title | Examination of the performance of ASEL and MPViT algorithms for classifying mangrove species of multiple natural reserves of Beibu Gulf, south China |
| title_full | Examination of the performance of ASEL and MPViT algorithms for classifying mangrove species of multiple natural reserves of Beibu Gulf, south China |
| title_fullStr | Examination of the performance of ASEL and MPViT algorithms for classifying mangrove species of multiple natural reserves of Beibu Gulf, south China |
| title_full_unstemmed | Examination of the performance of ASEL and MPViT algorithms for classifying mangrove species of multiple natural reserves of Beibu Gulf, south China |
| title_short | Examination of the performance of ASEL and MPViT algorithms for classifying mangrove species of multiple natural reserves of Beibu Gulf, south China |
| title_sort | examination of the performance of asel and mpvit algorithms for classifying mangrove species of multiple natural reserves of beibu gulf south china |
| topic | Mangrove species classification UAV multispectral images Adaptive stacking ensemble learning algorithms Multi-Path Vision Transformer algorithm SHapley Additive explanations |
| url | http://www.sciencedirect.com/science/article/pii/S1470160X23010129 |
| work_keys_str_mv | AT bolinfu examinationoftheperformanceofaselandmpvitalgorithmsforclassifyingmangrovespeciesofmultiplenaturalreservesofbeibugulfsouthchina AT xuhe examinationoftheperformanceofaselandmpvitalgorithmsforclassifyingmangrovespeciesofmultiplenaturalreservesofbeibugulfsouthchina AT yiyinliang examinationoftheperformanceofaselandmpvitalgorithmsforclassifyingmangrovespeciesofmultiplenaturalreservesofbeibugulfsouthchina AT tengfangdeng examinationoftheperformanceofaselandmpvitalgorithmsforclassifyingmangrovespeciesofmultiplenaturalreservesofbeibugulfsouthchina AT huajianli examinationoftheperformanceofaselandmpvitalgorithmsforclassifyingmangrovespeciesofmultiplenaturalreservesofbeibugulfsouthchina AT hongchanghe examinationoftheperformanceofaselandmpvitalgorithmsforclassifyingmangrovespeciesofmultiplenaturalreservesofbeibugulfsouthchina AT mingmingjia examinationoftheperformanceofaselandmpvitalgorithmsforclassifyingmangrovespeciesofmultiplenaturalreservesofbeibugulfsouthchina AT donglinfan examinationoftheperformanceofaselandmpvitalgorithmsforclassifyingmangrovespeciesofmultiplenaturalreservesofbeibugulfsouthchina AT fengwang examinationoftheperformanceofaselandmpvitalgorithmsforclassifyingmangrovespeciesofmultiplenaturalreservesofbeibugulfsouthchina |