.png){kind=icon}
.png){kind=icon}
Return
Differentiating Tree Crops and Planted Forests Patterns in China Using Flowering Phenology From Satellite Time Series
.png){kind=icon}
PRE
AI
赵
Q
Y
T
DOI：10.1109/lgrs.2026.3713310.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Planted forests play an important role in meeting the growing demand for forest products and supporting ecological restoration. However, they are often omitted from land cover products or confused with tree crops because of their similar spectral characteristics. This study focused on large-scale afforestation and reforestation associated with national ecological restoration programs. Landsat-derived Normalized Difference Vegetation Index (NDVI) time series corresponding to key disturbance periods (e.g., clearcutting and planting) were integrated with the LandTrendr algorithm to identify planted trees. In addition, an improved Flowering Phenology Index (FPI) was developed by combining field spectral measurements with Sentinel-2 observations to capture the flowering characteristics of tree crops. Then, the random forest (RF) model was used to evaluate different combinations of temporal, spatial, and flowering-related features. The results showed that incorporating FPI improved classification performance. The <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${F}1$ </tex-math></inline-formula> score of the planted forest class increased from 0.747 to 0.822 when FPI was added to the spectral feature set. The highest accuracy was achieved by combining FPI with temporal and spatial spectral features, yielding an <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${F}1$ </tex-math></inline-formula> score of 0.864. These results demonstrate the potential of integrating long term vegetation trajectories and flowering phenology for distinguishing planted forests from tree crops at regional scales.
Keywords:
Flowering phenology index (FPI)
landsat
planted forests
Sentinel
time-series analysis
tree crops
Journal
I
IF:
4.4
Papers:
486
Citations:
0
Organization
Cited Papers