Robust Identification of Vegetation Change Using Shapelet-Based Temporal Segmentation of Landsat Time-Series Stacks: A Case Study in the Qilian Mountains
Although many algorithms have been developed for monitoring annual vegetation change, most require complex controlling parameters or can only detect abrupt forest disturbances. We developed a new shapelet-based temporal segmentation vegetation change detection algorithm (SVCD) to identify the pre-ch...
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/10812654/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Although many algorithms have been developed for monitoring annual vegetation change, most require complex controlling parameters or can only detect abrupt forest disturbances. We developed a new shapelet-based temporal segmentation vegetation change detection algorithm (SVCD) to identify the pre-change baseline and directly measure changes using data-driven change detection rules. A temporal sliding window-based anomaly checking procedure is applied to the annual maximum composite of spectral vegetation indices in the growing season to remove the unmasked clouds, cloud shadows, and other temporary changes. Then, an iterative shapelet searching algorithm is performed on each given time series trajectory to filter out all atypical subseries. Finally, a multiple-spectral-index-based thresholding method is developed to measure the difference in spectral indices' statistical values between atypical and typical (stable) subseries. When those values exceed the predefined threshold values, the shapelet windows are flagged as having changed. SVCD was tested on a Landsat scene in the Qilian Mountains (WRS-2 Path 133 Row 34), a region with extensive natural and human-driven land cover changes over three decades. A stratified random sampling of 1012 pixels in persistent vegetation areas and 80 in changed areas showed SVCD achieved 99.0%<inline-formula><tex-math notation="LaTeX">$\pm$</tex-math></inline-formula>0.6% accuracy (95% confidence intervals). Applied across the entire Qilian Mountains, it outperformed LandTrendr with 99.5%<inline-formula><tex-math notation="LaTeX">$\pm$</tex-math></inline-formula>0.4% accuracy. These results highlight SVCD's strong potential for precise, noise-resistant vegetation change detection. |
|---|---|
| ISSN: | 1939-1404 2151-1535 |