Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
June 7, 2026Open Access

Hybrid SAR-Optical Remote Sensing for Flood Inundation Mapping: Feature Contribution Analysis in a Wetland Environment

View Full Paper
Ask AI
Bookmark
Share

Authors

DPDesy Ika PuspitasariENEdi NoersasongkoUniversitas Dian NuswantoroPPurwantoUniversitas Dian Nuswantoro

Discussion

Loading...

Member takes

Implication

Randomized trial demonstrates enhanced flood mapping accuracy in wetland environments, suggesting multisensor integration improves classification robustness.

Key Points

  • This study aims to enhance flood inundation mapping accuracy using a hybrid SAR-optical method in wetland environments.
  • Developed a hybrid SAR-optical method combining Sentinel-1 backscatter and Sentinel-2 water indices (AWEI and FWEI).
  • Evaluated four machine learning classifiers (Random Forest, SVM, Logistic Regression, XGBoost) through spatial validation.
  • Used change detection to derive flood inundation maps from pre- and post-flood water classifications.
  • AWEI showed superior performance in water discrimination compared to individual features.
  • SVM achieved optimal classification balance with overall accuracy (OA) of 0.98, Kappa of 0.97, and F1 score of 0.98 for water detection.
  • Multisensor integration significantly improved classification stability and spatial delineation of flood-affected areas.

Cite This Study

Puspitasari et al. (2026) studied this question.

synapsesocial.com/papers/6a250cbc7def13d035e1cd57https://doi.org/10.19139/soic-2310-5070-4067
View Full Paper
Ask AI
Bookmark
Share