journal article·2022-08-19Open access

Identifying Coastal Wetlands Changes Using a High-Resolution Optical Images Feature Hierarchical Selection Method

Ruijuan Wu, Jing Wang

Applied Sciences· Volume 12· Issue 16

Abstract

Coastal wetlands are dynamic and fragile ecosystems where complex changes have taken place. As they are affected by environmental changes and human activities, it is of great practical significance to monitor coastal wetlands changes regularly. High-resolution optical data can observe changes in coastal wetlands, however, the impact of different optical features on the identification of changes in coastal wetlands is not clear. Simultaneously, the combination of many features could cause the “dimension disaster” problem. In addition, only small amounts of training samples are accessible at pre- or post-changed time. In order to solve the above problems, the feature hierarchical selection method is proposed, taking into account the jumping degree of different image features. The influence of different optical features on wetland classification was analyzed. In addition, a training samples transfer learning strategy was designed for wetland classification, and the classification result at pre- and post-changed times were compared to identify the “from-to” coastal wetlands changes. The southeastern coastal wetlands located in Jiangsu Province were used as a study area, and ZY-3 images in 2013 and 2018 were used to verify the proposed methods. The results show that the feature hierarchical selection method can provide a quantitative reference for optimal subset feature selection. A training samples transfer learning strategy was used to classify post-changed optical data, the overall accuracy of transferred training samples was 91.16%, and it ensures the accuracy requirements for change identification. In the study area, the salt marsh increased mainly from the sea area, because salt marshes expand rapidly throughout coastal areas, and aquaculture ponds increased from the sea area and salt marshes, because of the considerable economic benefits of the aquacultural industry.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Land Use and Ecosystem Services · Remote-Sensing Image Classification · Remote Sensing in Agriculture

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Key Laboratory for Digital Land and Resources of Jiangxi Province, East China University of Technology, Nanchang 330013, China

School of Geography and Resource Science, Neijiang Normal University, Neijiang 641102, China

State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, CAS, Beijing 100101, China

College of Water Sciences, Beijing Normal University, Beijing 100875, China

Funding

National Natural Science Foundation of China · State Key Laboratory of Resources and Environmental Information System · Key Laboratory for Digital Land and Resources of Jiangxi Province, East China University of Technology · Key Laboratory of Surveying and Mapping Science and Geospatial Information Technology of Ministry of Natural Resources · Scientific Research Innovation Team Project of Neijiang Normal University

References (36)

Show source-provided references
1. Reliability evaluation and migration of wetland samples10.1109/JSTARS.2021.3102866 ↗
2. Monitoring wetland changes on the source of the three open waters from 1990 to 2009, Qinghai, China10.1109/JSTARS.2012.2222354 ↗
3. Battaglia, M.J., Banks, S., Behnamian, A., Bourgeau-Chavez, L., Brisco, B., Corcoran, J., Chen, Z.H., Huberty, B., Klassen, J., and Knight, J. (2021). Multi-source EO for dynamic wetland mapping and monitoring in the Great Lakes Basin. Remote Sens., 13.10.3390/rs13040599 ↗
4. Remote sensing of wetlands in South America: Status and challenges10.1080/01431161.2017.1395971 ↗
5. Monitoring Andean high altitude wetlands in central Chile with seasonal optical data: A comparison between Worldview-2 and Sentinel-2 Imagery10.1016/j.isprsjprs.2018.04.001 ↗
6. Zhang, A.Z., Sun, G.Y., Ma, P., Jia, X.P., Ren, J.C., Huang, H., and Zhang, X.M. (2019). Coastal wetland mapping with Sentinel-2 MSI imagery based on gravitational optimized multilayer perceptron and morphological attribute profiles. Remote Sens., 11.10.3390/rs11080952 ↗
7. Classification mapping and species identification of salt marshes based on a short-time interval NDVI time-series from HJ-1 optical imagery
8. Mapping wetland dynamics with SAR-based change detection in the cloud10.1109/LGRS.2019.2903596 ↗
9. A collection of SAR methodologies for monitoring wetlands10.3390/rs70607615 ↗
10. Change detection from synthetic aperture radar images based on neighborhood-based ratio and extreme learning machine10.1117/1.JRS.10.046019 ↗
11. Integrating change magnitude maps of spectrally enhanced multi-features for landcover change detection10.1080/01431161.2021.1892860 ↗
12. A multi-feature fusion-based change detection method for remote sensing images10.1007/s12524-018-0864-1 ↗
13. Song, M., Zhong, Y.F., and Ma, A.L. (2018). Change detection based on multi-feature clustering using differential evolution for Landsat imagery. Remote Sens., 10.10.3390/rs10101664 ↗
14. Change detection method of high resolution remote sensing image based on D-S evidence theory feature fusion10.1109/ACCESS.2020.3047915 ↗
15. Object-based change detection from satellite imagery by segmentation optimization and multi-features fusion10.1080/01431161.2017.1308033 ↗
16. An adaptively weighted multi-feature method for object-based change detection in high spatial resolution remote sensing images10.1080/2150704X.2020.1716407 ↗
17. Chen, Q., Chen, Y.H., and Jiang, W.G. (2016). Genetic particle swarm optimization based feature selection for very-high-resolution remotely sensed imagery object change detection. Sensors, 16.10.3390/s16081204 ↗
18. Feature selection using principal component analysis for massive retweet detection10.1016/j.patrec.2014.05.020 ↗
19. A novel random forests-based feature selection method for microarray expression data analysis10.1504/IJDMB.2015.070852 ↗
20. Chen, Y.Y., He, X.F., Xu, J., Zhang, R.C., and Lu, Y.Y. (2020). Scattering feature set optimization and polarimetric SAR classification using object-oriented RF-SFS algorithm in coastal wetlands. Remote Sens., 12.10.3390/rs12030407 ↗
21. Wang, X., Liu, S.C., Du, P.J., Liang, H., Xia, J.S., and Li, Y.F. (2018). Object-based change detection in urban areas from high spatial resolution images based on multiple features and ensemble learning. Remote Sens., 10.10.3390/rs10020276 ↗
22. Semantic segmentation for remote sensing images based on adaptive feature selection network
23. Plant species classification in salt marshes using phenological parameters derived from Sentinel-2 pixel-differential time-series10.1016/j.rse.2021.112320 ↗
24. A Framework for automatic and unsupervised detection of multiple changes in multitemporal images10.1109/TGRS.2011.2171493 ↗
25. Shao, P., Shi, W.Z., He, P.F., Hao, M., and Zhang, X.K. (2016). Novel approach to unsupervised change detection based on a robust semi-supervised FCM clustering algorithm. Remote Sens., 8.10.3390/rs8030264 ↗
26. Adaptive generalized likelihood ratio test for change detection in SAR images10.1109/LGRS.2019.2922198 ↗
27. Deep learning and mapping based ternary change detection for information unbalanced images10.1016/j.patcog.2017.01.002 ↗
28. A critical synthesis of remotely sensed optical image change detection techniques10.1016/j.rse.2015.01.006 ↗
29. Change detection from remotely sensed images: From pixel-based to object-based approaches10.1016/j.isprsjprs.2013.03.006 ↗
30. Digital change detection techniques using remotely-sensed data10.1080/01431168908903939 ↗
31. The time variable in data fusion: A change detection perspective10.1109/MGRS.2015.2443494 ↗
32. Chen, D., Wang, Y.F., Shen, Z.Y., Liao, J.F., Chen, J.Z., and Sun, S.B. (2022). Long time-series mapping and change detection of coastal zone land use based on Google Earth Engine and multi-source data fusion. Remote Sens., 14.10.3390/rs14010001 ↗
33. A post-classification change detection method based on iterative slow feature analysis and Bayesian soft fusion10.1016/j.rse.2017.07.009 ↗
34. A novel approach for hyperspectral change detection based on uncertain area analysis and improved transfer learning10.1109/JSTARS.2020.2990481 ↗
35. Review of change detection methods for multi-temporal remote sensing imagery
36. Coastal wetlands change detection combining pixel-based and object-based methods