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 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.

Automated summary

Developed in response to the rapid loss or change of natural ecosystems, especially wetlands, due to human activities and climate change, this study presents a Deep Convolutional Neural Network (DCNN) model using a modified architecture of AlexNet and a Generative Adversarial Network (GAN) for wetland classification and generation of Sentinel-1 and Sentinel-2 data. Tested in a 370 sq. km area in Newfoundland, the proposed model achieved an average accuracy of 92.30% with improved F-1 scores for various wetland classes compared to the original CNN network of AlexNet. These results demonstrate the high capability of the proposed model for large-scale wetland classification tasks.