A recent study published in Scientific Reports by Reji J and Rama Rao Nidamanuri explores the use of deep learning to predict plant height and crown area for vegetable crops based on LiDAR point cloud data. The researchers collected LiDAR data using a terrestrial laser scanner at various growth stages of tomato, eggplant, and cabbage crops in Bengaluru, India. They developed a hybrid deep learning framework combining Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks to predict plant structural parameters with around 80% accuracy. The hybrid model outperformed individual LSTM and GRU models in predicting crown area, showcasing improved spatial variability and complexity of plant growth. However, the accuracy decreased at advanced growth stages, closer to harvest time. Despite this limitation, the prediction quality remained consistent across different crops. This study aligns with the trend of integrating remote sensing technologies into precision agriculture to provide detailed insights into within-farm variations. The research demonstrates the potential of hybrid deep learning models in effectively predicting plant structural parameters, offering valuable tools for optimizing crop management practices.
Source link
Source link: https://www.hortidaily.com/article/9640298/predict-plant-structural-parameters-effectively-with-hybrid-deep-learning/
Hybrid deep learning predicts plant structural parameters effectively. #AgricultureTech
