Swin Transformer for Complex Coastal Wetland Classification Using the Integration of Sentinel-1 and Sentinel-2 Imagery
The emergence of deep learning techniques has revolutionized the use of machine learning algorithms to classify complicated environments, notably in remote sensing. Convolutional Neural Networks (CNNs) have shown considerable promise in classifying challenging high-dimensional remote sensing data, p...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/14/2/178 |
| _version_ | 1797489679395717120 |
|---|---|
| author | Ali Jamali Masoud Mahdianpari |
| author_facet | Ali Jamali Masoud Mahdianpari |
| author_sort | Ali Jamali |
| collection | DOAJ |
| description | The emergence of deep learning techniques has revolutionized the use of machine learning algorithms to classify complicated environments, notably in remote sensing. Convolutional Neural Networks (CNNs) have shown considerable promise in classifying challenging high-dimensional remote sensing data, particularly in the classification of wetlands. State-of-the-art Natural Language Processing (NLP) algorithms, on the other hand, are transformers. Despite the fact that transformers have been utilized for a few remote sensing applications, they have not been compared to other well-known CNN networks in complex wetland classification. As such, for the classification of complex coastal wetlands in the study area of Saint John city, located in New Brunswick, Canada, we modified and employed the Swin Transformer algorithm. Moreover, the developed transformer classifier results were compared with two well-known deep CNNs of AlexNet and VGG-16. In terms of average accuracy, the proposed Swin Transformer algorithm outperformed the AlexNet and VGG-16 techniques by 14.3% and 44.28%, respectively. The proposed Swin Transformer classifier obtained F-1 scores of 0.65, 0.71, 0.73, 0.78, 0.82, 0.84, and 0.84 for the recognition of coastal marsh, shrub, bog, fen, aquatic bed, forested wetland, and freshwater marsh, respectively. The results achieved in this study suggest the high capability of transformers over very deep CNN networks for the classification of complex landscapes in remote sensing. |
| first_indexed | 2024-03-10T00:20:06Z |
| format | Article |
| id | doaj.art-a9f693854d084e008d3c59e07c877955 |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-10T00:20:06Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-a9f693854d084e008d3c59e07c8779552023-11-23T15:44:06ZengMDPI AGWater2073-44412022-01-0114217810.3390/w14020178Swin Transformer for Complex Coastal Wetland Classification Using the Integration of Sentinel-1 and Sentinel-2 ImageryAli Jamali0Masoud Mahdianpari1Civil Engineering Department, Faculty of Engineering, University of Karabük, Karabük 78050, TurkeyDepartment of Electrical and Computer Engineering, Memorial University of Newfoundland, St. John’s, NL A1B 3X5, CanadaThe emergence of deep learning techniques has revolutionized the use of machine learning algorithms to classify complicated environments, notably in remote sensing. Convolutional Neural Networks (CNNs) have shown considerable promise in classifying challenging high-dimensional remote sensing data, particularly in the classification of wetlands. State-of-the-art Natural Language Processing (NLP) algorithms, on the other hand, are transformers. Despite the fact that transformers have been utilized for a few remote sensing applications, they have not been compared to other well-known CNN networks in complex wetland classification. As such, for the classification of complex coastal wetlands in the study area of Saint John city, located in New Brunswick, Canada, we modified and employed the Swin Transformer algorithm. Moreover, the developed transformer classifier results were compared with two well-known deep CNNs of AlexNet and VGG-16. In terms of average accuracy, the proposed Swin Transformer algorithm outperformed the AlexNet and VGG-16 techniques by 14.3% and 44.28%, respectively. The proposed Swin Transformer classifier obtained F-1 scores of 0.65, 0.71, 0.73, 0.78, 0.82, 0.84, and 0.84 for the recognition of coastal marsh, shrub, bog, fen, aquatic bed, forested wetland, and freshwater marsh, respectively. The results achieved in this study suggest the high capability of transformers over very deep CNN networks for the classification of complex landscapes in remote sensing.https://www.mdpi.com/2073-4441/14/2/178wetland classificationswin transformerVGG-16AlexNetCNNdeep convolutional neural network |
| spellingShingle | Ali Jamali Masoud Mahdianpari Swin Transformer for Complex Coastal Wetland Classification Using the Integration of Sentinel-1 and Sentinel-2 Imagery Water wetland classification swin transformer VGG-16 AlexNet CNN deep convolutional neural network |
| title | Swin Transformer for Complex Coastal Wetland Classification Using the Integration of Sentinel-1 and Sentinel-2 Imagery |
| title_full | Swin Transformer for Complex Coastal Wetland Classification Using the Integration of Sentinel-1 and Sentinel-2 Imagery |
| title_fullStr | Swin Transformer for Complex Coastal Wetland Classification Using the Integration of Sentinel-1 and Sentinel-2 Imagery |
| title_full_unstemmed | Swin Transformer for Complex Coastal Wetland Classification Using the Integration of Sentinel-1 and Sentinel-2 Imagery |
| title_short | Swin Transformer for Complex Coastal Wetland Classification Using the Integration of Sentinel-1 and Sentinel-2 Imagery |
| title_sort | swin transformer for complex coastal wetland classification using the integration of sentinel 1 and sentinel 2 imagery |
| topic | wetland classification swin transformer VGG-16 AlexNet CNN deep convolutional neural network |
| url | https://www.mdpi.com/2073-4441/14/2/178 |
| work_keys_str_mv | AT alijamali swintransformerforcomplexcoastalwetlandclassificationusingtheintegrationofsentinel1andsentinel2imagery AT masoudmahdianpari swintransformerforcomplexcoastalwetlandclassificationusingtheintegrationofsentinel1andsentinel2imagery |