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 using Machine Learning
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. A LightGBM model predicts 13 phenological stages for eight major crops across Germany at 20 m scale, trained on DWD national phenology observations from 2017 to 2021.
Key Insights
- Across all stages and crops, the model reached R² > 0.43 and a mean absolute error of 6 days at national scale.
- Fusing radar sensors with climate data improved phenology identification — Sentinel-1 maintains continuity when clouds limit Sentinel-2.
- Predictions transferred across different spatial and temporal contexts within Germany.
Abstract
Crop phenology describes the physiological development stages of crops from planting to harvest which is valuable information for decision makers to plan and adapt agricultural management strategies. In the era of big Earth observation data ubiquity, attempts have been made to accurately detect crop phenology using Remote Sensing (RS) and high resolution weather data. However, most studies have focused on large scale predictions of phenology or developed methods which are not adequate to help crop modeler communities on leveraging Sentinel-1 and Sentinal-2 data and fusing them with high resolution climate data, using a novel framework. For this, we trained a Machine Learning (ML) LightGBM model to predict 13 phenological stages for eight major crops across Germany at 20 m scale. Observed phenologies were taken from German national phenology network (German Meteorological Service; DWD) between 2017 and 2021. We proposed a thorough feature selection analysis to find the best combination of RS and climate data to detect phenological stages. At national scale, predicted phenology resulted in a reasonable precision of R² > 0.43 and a low Mean Absolute Error of 6 days, averaged over all phenological stages and crops. The spatio-temporal analysis of the model predictions demonstrates its transferability across different spatial and temporal context of Germany. The results indicated that combining radar sensors with climate data yields a very promising performance for a multitude of practical applications.