Deep Learning-Based Classification of High-Resolution Satellite Images for Mangrove Mapping
Source abstract
Abstract
Detailed information about mangroves is crucial for ecological and environmental protection and sustainable development. It is difficult to capture small patches of mangroves from satellite images with relatively low to medium resolution. In this study, high-resolution (0.8–2 m) images from Chinese GaoFen (GF) and ZiYuan (ZY) series satellites were used to map the distribution of mangroves in coastal areas of Guangdong Province, China. A deep-learning network, U2-Net, with attention gates was applied to extract multi-scale information of mangroves from satellite images. The results showed that the attention U2-Net model performed well on mangrove classification. The overall accuracy, precision, and F1-score values were 96.5%, 92.0%, and 91.5%, respectively, which were higher than those obtained from other machine-learning methods such as Random Forest or U-Net. Based on the high-resolution mangrove maps generated from long satellite image time series, we also investigated the spatiotemporal evolution of the mangrove forest in Shuidong Bay. The results can provide crucial information for government administrators, scientists, and other stakeholders to monitor the dynamic changes in mangroves.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Coastal wetland ecosystem dynamics · Flood Risk Assessment and Management · Remote Sensing and LiDAR Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Marine Technology, Faculty of Information Science and Engineering, Ocean University of China, Qingdao 266100, China
PIESAT Information Technology Co., Ltd., Beijing 100195, China
Fujian Marine Forecasts, Fuzhou 350003, China
Funding
2022 Research Program of Sanya Yazhou Bay Science and Technology City · National Natural Science Foundation of China
References (28)
Show source-provided references
1. Enhanced mangrove vegetation index based on hyperspectral images for mapping mangrove10.1016/j.isprsjprs.2022.05.003 ↗
2. Monitoring loss and recovery of mangrove forests during 42 years: The achievements of mangrove conservation in China
3. Hu, T., Zhang, Y., Su, Y., Zheng, Y., Lin, G., and Guo, Q. (2020). Mapping the global mangrove forest aboveground biomass using multisource remote sensing data. Remote Sens., 12.10.3390/rs12101690 ↗
4. An integrated comparative approach to mangrove vegetation mapping using advanced remote sensing and GIS technologies: Preliminary results10.1007/BF00029135 ↗
5. A review of the application of multispectral remote sensing in the study of mangrove ecosystems with special emphasis on image processing techniques10.1007/s41324-019-00268-y ↗
6. Per-pixel and sub-pixel classifications of high-resolution satellite data for mangrove species mapping
7. Wang, D., Wan, B., Qiu, P., Su, Y., Guo, Q., and Wu, X. (2018). Artificial mangrove species mapping using pléiades-1: An evaluation of pixel-based and object-based classifications with selected machine learning algorithms. Remote Sens., 10.10.3390/rs10020294 ↗
8. Optimized rule-based logistic model tree algorithm for mapping mangrove species using ALOS PALSAR imagery and GIS in the tropical region10.1007/s12665-018-7373-y ↗
9. Kamal, M., Jamaluddin, I., Parela, A., and Farda, N.M. (2019, January 14–18). Comparison of Google Earth Engine (GEE)-based machine learning classifiers for mangrove mapping. Proceedings of the 40th Asian Conference Remote Sensing, ACRS, Daejeon, Republic of Korea.
10. Comparison of machine learning algorithms for mangrove species identification in Malad creek, Mumbai using WorldView-2 and Google Earth images10.1007/s11852-022-00891-2 ↗
11. Automatic waterline extraction and topographic mapping of tidal flats from SAR images based on deep learning10.1029/2021GL096007 ↗
12. Coastal inundation mapping from bitemporal and dual-polarization SAR imagery based on deep convolutional neural networks10.1029/2019JC015577 ↗
13. Reconstruction of subsurface temperature field in the south China Sea from satellite observations based on an attention U-net model10.1109/TGRS.2022.3200545 ↗
14. Iovan, C., Kulbicki, M., and Mermet, E. (October, January 26). Deep convolutional neural network for mangrove mapping. Proceedings of the IGARSS 2020—2020 IEEE International Geoscience and Remote Sensing Symposium, Waikoloa, HI, USA.10.1109/IGARSS39084.2020.9323802 ↗
15. Research on mangrove drone monitoring based on convolutional neural network
16. Guo, Y., Liao, J., and Shen, G. (2021). Mapping large-scale mangroves along the maritime silk road from 1990 to 2015 using a novel deep learning model and landsat data. Remote Sens., 13.10.3390/rs13020245 ↗
17. Hu, L., Xu, N., Liang, J., Li, Z., Chen, L., and Zhao, F. (2020). Advancing the mapping of mangrove forests at national-scale using Sentinel-1 and Sentinel-2 time-series data with Google Earth Engine: A case study in China. Remote Sens., 12.10.3390/rs12193120 ↗
18. Comprehensive analysis of climate-related comfort in southern China: Climatology, trend, and interannual variations10.1016/j.uclim.2022.101349 ↗
19. (2020, March 14). PIE-Ortho Software. Available online: http://www.piesat.cn/website/cn/pages/product/software/pie-ortho.html.
20. Cooley, T., Anderson, G.P., Felde, G.W., Hoke, M.L., Ratkowski, A.J., Chetwynd, J.H., Gardner, J.A., Adler-Golden, S.M., Matthew, M.W., and Berk, A. (2002, January 24–28). FLAASH, a MODTRAN4-based atmospheric correction algorithm, its application and validation. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium, Toronto, ON, Canada.
21. Zhang, Y. (2008). System and Method for Image Fusion. (No. 7340099), U.S. Patent.
22. U2-Net: Going deeper with nested U-structure for salient object detection10.1016/j.patcog.2020.107404 ↗
23. Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N.Y., and Kainz, B. (2018). Attention u-net: Learning where to look for the pancreas. arXiv.
24. Smith, L.N. (2017, January 24–31). Cyclical learning rates for training neural networks. Proceedings of the 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), Santa Rosa, CA, USA.10.1109/WACV.2017.58 ↗
25. Neural network classification of mangrove species from multi-seasonal Ikonos imagery10.14358/PERS.74.7.921 ↗
26. Khan, A.R., Khan, A., Masud, S., and Rahman, R.M. (2021, January 16–18). Analyzing the Land Cover Change and Degradation in Sundarbans Mangrove Forest Using Machine Learning and Remote Sensing Technique. Proceedings of the Advances in Computational Intelligence: 16th International Work-Conference on Artificial Neural Networks, IWANN 2021, Virtual Event. Proceedings, Part II 16, 2021.
27. A mangrove extraction method combined with sem-dense connections by convolutional neural network
28. Deep semantic segmentation of mangroves in Brazil combining spatial, temporal, and polarization data from Sentinel-1 time series10.1016/j.ocecoaman.2022.106381 ↗