Precision Agriculture: Crop Mapping using Machine Learning and Sentinel-2 Satellite Imagery
This work addresses food security and climate change impacts by improving crop cultivation efficiency for agricultural stakeholders, though it is incremental as it applies existing methods to a specific domain.
The study tackled crop mapping for precision agriculture by segmenting lavender fields using deep learning and pixel-based methods on Sentinel-2 satellite imagery, achieving a Dice coefficient of 0.8324 with a U-Net model.
Food security has grown in significance due to the changing climate and its warming effects. To support the rising demand for agricultural products and to minimize the negative impact of climate change and mass cultivation, precision agriculture has become increasingly important for crop cultivation. This study employs deep learning and pixel-based machine learning methods to accurately segment lavender fields for precision agriculture, utilizing various spectral band combinations extracted from Sentinel-2 satellite imagery. Our fine-tuned final model, a U-Net architecture, can achieve a Dice coefficient of 0.8324. Additionally, our investigation highlights the unexpected efficacy of the pixel-based method and the RGB spectral band combination in this task.