Research Context
Accurate crop phenology mapping is essential for agricultural monitoring, water planning, and food-security analysis. Cloud-sensitive optical records create temporal gaps in many regions.
A novel fusion of Sentinel-1 and Sentinel-2 with climate data for crop phenology estimation
Method
The framework combines Sentinel-1 SAR, Sentinel-2 multispectral data, and climate variables inside a machine-learning workflow to detect phenological stages through time.
Key Insights
- Sensor fusion improves continuity under cloudy conditions.
- Climate covariates strengthen temporal interpretation and prediction stability.
- The approach supports scalable crop monitoring workflows.