A Synergic Use of Sentinel-1 and Sentinel-2 Imagery for Complex Wetland Classification Using Generative Adversarial Network (GAN) Scheme
Due to anthropogenic activities and climate change, many natural ecosystems, especially wetlands, are lost or changing at a rapid pace. For the last decade, there has been increasing attention towards developing new tools and methods for the mapping and classification of wetlands using remote sensin...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Water |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4441/13/24/3601 |
| _version_ | 1797499814605225984 |
|---|---|
| author | Ali Jamali Masoud Mahdianpari Fariba Mohammadimanesh Brian Brisco Bahram Salehi |
| author_facet | Ali Jamali Masoud Mahdianpari Fariba Mohammadimanesh Brian Brisco Bahram Salehi |
| author_sort | Ali Jamali |
| collection | DOAJ |
| description | Due to anthropogenic activities and climate change, many natural ecosystems, especially wetlands, are lost or changing at a rapid pace. For the last decade, there has been increasing attention towards developing new tools and methods for the mapping and classification of wetlands using remote sensing. At the same time, advances in artificial intelligence and machine learning, particularly deep learning models, have provided opportunities to advance wetland classification methods. However, the developed deep and very deep algorithms require a higher number of training samples, which is costly, logistically demanding, and time-consuming. As such, in this study, we propose a Deep Convolutional Neural Network (DCNN) that uses a modified architecture of the well-known DCNN of the AlexNet and a Generative Adversarial Network (GAN) for the generation and classification of Sentinel-1 and Sentinel-2 data. Applying to an area of approximately 370 sq. km in the Avalon Peninsula, Newfoundland, the proposed model with an average accuracy of 92.30% resulted in F-1 scores of 0.82, 0.85, 0.87, 0.89, and 0.95 for the recognition of swamp, fen, marsh, bog, and shallow water, respectively. Moreover, the proposed DCNN model improved the F-1 score of bog, marsh, fen, and swamp wetland classes by 4%, 8%, 11%, and 26%, respectively, compared to the original CNN network of AlexNet. These results reveal that the proposed model is highly capable of the generation and classification of Sentinel-1 and Sentinel-2 wetland samples and can be used for large-extent classification problems. |
| first_indexed | 2024-03-10T03:52:50Z |
| format | Article |
| id | doaj.art-116920b0bc8a4f6fbcdf0c9086953bfb |
| institution | Directory Open Access Journal |
| issn | 2073-4441 |
| language | English |
| last_indexed | 2024-03-10T03:52:50Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Water |
| spelling | doaj.art-116920b0bc8a4f6fbcdf0c9086953bfb2023-11-23T11:01:36ZengMDPI AGWater2073-44412021-12-011324360110.3390/w13243601A Synergic Use of Sentinel-1 and Sentinel-2 Imagery for Complex Wetland Classification Using Generative Adversarial Network (GAN) SchemeAli Jamali0Masoud Mahdianpari1Fariba Mohammadimanesh2Brian Brisco3Bahram Salehi4Civil 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, CanadaC-CORE, 1 Morrissey Road, St. John’s, NL A1B 3X5, CanadaThe Canada Centre for Mapping and Earth Observation, Ottawa, ON K1S 5K2, CanadaDepartment of Environmental Resources Engineering, College of Environmental Science and Forestry (SUNY ESF), State University of New York, Syracuse, NY 13210, USADue to anthropogenic activities and climate change, many natural ecosystems, especially wetlands, are lost or changing at a rapid pace. For the last decade, there has been increasing attention towards developing new tools and methods for the mapping and classification of wetlands using remote sensing. At the same time, advances in artificial intelligence and machine learning, particularly deep learning models, have provided opportunities to advance wetland classification methods. However, the developed deep and very deep algorithms require a higher number of training samples, which is costly, logistically demanding, and time-consuming. As such, in this study, we propose a Deep Convolutional Neural Network (DCNN) that uses a modified architecture of the well-known DCNN of the AlexNet and a Generative Adversarial Network (GAN) for the generation and classification of Sentinel-1 and Sentinel-2 data. Applying to an area of approximately 370 sq. km in the Avalon Peninsula, Newfoundland, the proposed model with an average accuracy of 92.30% resulted in F-1 scores of 0.82, 0.85, 0.87, 0.89, and 0.95 for the recognition of swamp, fen, marsh, bog, and shallow water, respectively. Moreover, the proposed DCNN model improved the F-1 score of bog, marsh, fen, and swamp wetland classes by 4%, 8%, 11%, and 26%, respectively, compared to the original CNN network of AlexNet. These results reveal that the proposed model is highly capable of the generation and classification of Sentinel-1 and Sentinel-2 wetland samples and can be used for large-extent classification problems.https://www.mdpi.com/2073-4441/13/24/3601wetland classificationmachine learningCNNDeep Convolutional Neural NetworkGenerative Adversarial Network |
| spellingShingle | Ali Jamali Masoud Mahdianpari Fariba Mohammadimanesh Brian Brisco Bahram Salehi A Synergic Use of Sentinel-1 and Sentinel-2 Imagery for Complex Wetland Classification Using Generative Adversarial Network (GAN) Scheme Water wetland classification machine learning CNN Deep Convolutional Neural Network Generative Adversarial Network |
| title | A Synergic Use of Sentinel-1 and Sentinel-2 Imagery for Complex Wetland Classification Using Generative Adversarial Network (GAN) Scheme |
| title_full | A Synergic Use of Sentinel-1 and Sentinel-2 Imagery for Complex Wetland Classification Using Generative Adversarial Network (GAN) Scheme |
| title_fullStr | A Synergic Use of Sentinel-1 and Sentinel-2 Imagery for Complex Wetland Classification Using Generative Adversarial Network (GAN) Scheme |
| title_full_unstemmed | A Synergic Use of Sentinel-1 and Sentinel-2 Imagery for Complex Wetland Classification Using Generative Adversarial Network (GAN) Scheme |
| title_short | A Synergic Use of Sentinel-1 and Sentinel-2 Imagery for Complex Wetland Classification Using Generative Adversarial Network (GAN) Scheme |
| title_sort | synergic use of sentinel 1 and sentinel 2 imagery for complex wetland classification using generative adversarial network gan scheme |
| topic | wetland classification machine learning CNN Deep Convolutional Neural Network Generative Adversarial Network |
| url | https://www.mdpi.com/2073-4441/13/24/3601 |
| work_keys_str_mv | AT alijamali asynergicuseofsentinel1andsentinel2imageryforcomplexwetlandclassificationusinggenerativeadversarialnetworkganscheme AT masoudmahdianpari asynergicuseofsentinel1andsentinel2imageryforcomplexwetlandclassificationusinggenerativeadversarialnetworkganscheme AT faribamohammadimanesh asynergicuseofsentinel1andsentinel2imageryforcomplexwetlandclassificationusinggenerativeadversarialnetworkganscheme AT brianbrisco asynergicuseofsentinel1andsentinel2imageryforcomplexwetlandclassificationusinggenerativeadversarialnetworkganscheme AT bahramsalehi asynergicuseofsentinel1andsentinel2imageryforcomplexwetlandclassificationusinggenerativeadversarialnetworkganscheme AT alijamali synergicuseofsentinel1andsentinel2imageryforcomplexwetlandclassificationusinggenerativeadversarialnetworkganscheme AT masoudmahdianpari synergicuseofsentinel1andsentinel2imageryforcomplexwetlandclassificationusinggenerativeadversarialnetworkganscheme AT faribamohammadimanesh synergicuseofsentinel1andsentinel2imageryforcomplexwetlandclassificationusinggenerativeadversarialnetworkganscheme AT brianbrisco synergicuseofsentinel1andsentinel2imageryforcomplexwetlandclassificationusinggenerativeadversarialnetworkganscheme AT bahramsalehi synergicuseofsentinel1andsentinel2imageryforcomplexwetlandclassificationusinggenerativeadversarialnetworkganscheme |