A Water Extraction Method for Multiple Terrains Area Based on Multisource Fused Images: A Case Study of the Yangtze River Basin
In recent years, flooding and droughts in the Yangtze River basin have become increasingly unpredictable. Remote sensing is an effective tool for monitoring water distribution. However, cloudy weather and mountainous terrain directly affect water extraction from remote sensing images. A single data...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10845130/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In recent years, flooding and droughts in the Yangtze River basin have become increasingly unpredictable. Remote sensing is an effective tool for monitoring water distribution. However, cloudy weather and mountainous terrain directly affect water extraction from remote sensing images. A single data source cannot resolve this issue and often encounters the challenge of “different features having the same spectrum.” To address these problems, we constructed a dataset using both active and passive remote sensing data and designed a partitioning scheme with corresponding water body extraction rules for multiple terrains area. This partitioning method and its associated rules significantly reduce the false positive rate of water extraction in mountainous areas. Our approach successfully extracts water bodies from cloudy optical imagery without being hindered by cloud cover, thereby enhancing the usability of optical remote sensing images. The accuracy of our method reaches 91.73%, with a Kappa value of 0.90. In multiple terrains area, our method's Kappa coefficient is 0.39 higher than synthetic aperture radar and optical imagery water index and 0.06 higher than Res-U-Net. It shows superior performance and greater stability in mountainous and cloudy regions. In conclusion, this method facilitates consistent water extraction on large datasets. |
|---|---|
| ISSN: | 1939-1404 2151-1535 |