EUVIMEDEUVIMED entdecken
Crossref

Potential of dynamic features derived from temporally dense Sentinel-1/2 imagery for improved floodplain wetland mapping

Xiyuan Xiong, Shuchen Yu, Lunche Wang, Xihui Gu, Wen Xiao, Yao Du, Qiuhua He, Lan Feng, Zengliang Luo, Qian Cao, Liu Yang, Zhitong Wang

Progress in Physical Geography: Earth and Environment · 2026-08 · 50 (4) · 497-520

DOI: 10.1177/03091333261434476 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Progress in Physical Geography: Earth and Environment, online erschienen am 10.03.2026. Verfasst von Xiyuan Xiong und 11 weiteren Autor:innen. Die Arbeit nennt 68 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Floodplain wetlands are dynamic and vulnerable ecosystems, requiring accurate and detailed spatial information for sustainable management and conservation. Multi-source and multi-temporal remote sensing data have been commonly used to address spatiotemporal uncertainties, whereas the multivariate dynamic information embedded in these data remains underutilized. Therefore, this study developed three dynamic features derived from temporally dense Sentinel-1/2 imagery to improve floodplain wetland mapping on the Google Earth Engine (GEE) platform. First, hydrological dynamics were captured through the Inundation Frequency (IF) based on the Sentinel-1 Dual-Polarized Water Index (SDWI) time series. Second, vegetation dynamics and combined hydrological-vegetation variations were captured through Phenology Indicators (PIs) and a novel Inundation-Phenology Index (IPI), based on fitted NDVI and NDWI time series using all available Sentinel-2 observations. Finally, these features were introduced to classify a typical floodplain area in the middle Yangtze River, China, using the Random Forest algorithm with superpixels optimized. The results achieved an overall accuracy (OA) of 96.24% and a Kappa coefficient of 0.95, improving by 9.72 percentage points in OA and 0.12 in Kappa over the initial features (median composites of spectral/polarization bands and indices) alone. Comparative experiments, SHAP interpretation, and spatial consistency analysis revealed the following: (1) IF demonstrated notable and stable performance, significantly improving classification in frequently inundated areas; (2) PIs enhanced vegetation prediction, primarily attributed to EOS (end of growing season) and LOS (length of growing season); (3) IPI facilitated the differentiation between open water and transition zones, particularly benefiting complex and highly dynamic transitional areas. This study presents the considerable potential of proposed dynamic features, with results expected to support refined management and ecological conservation.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Xiong, X., Yu, S., Wang, L., Gu, X., Xiao, W., Du, Y., He, Q., Feng, L., Luo, Z., Cao, Q., Yang, L., & Wang, Z. (2026). Potential of dynamic features derived from temporally dense Sentinel-1/2 imagery for improved floodplain wetland mapping. Progress in Physical Geography: Earth and Environment, 50(4), 497-520. https://doi.org/10.1177/03091333261434476

Vancouver

Xiong X, Yu S, Wang L, Gu X, Xiao W, Du Y, et al. Potential of dynamic features derived from temporally dense Sentinel-1/2 imagery for improved floodplain wetland mapping. Progress in Physical Geography: Earth and Environment. 2026;50(4):497-520. doi:10.1177/03091333261434476

BibTeX
@article{Xiong2026,
  author = {Xiong, Xiyuan and Yu, Shuchen and Wang, Lunche and Gu, Xihui and Xiao, Wen and Du, Yao and He, Qiuhua and Feng, Lan and Luo, Zengliang and Cao, Qian and Yang, Liu and Wang, Zhitong},
  title = {Potential of dynamic features derived from temporally dense Sentinel-1/2 imagery for improved floodplain wetland mapping},
  journal = {Progress in Physical Geography: Earth and Environment},
  year = {2026},
  volume = {50},
  number = {4},
  pages = {497--520},
  doi = {10.1177/03091333261434476}
}
Kostenlos starten →