Paolo Guadagna
Papers
3
Total Citations
37
H-Index
2
About
Paolo Guadagna is a researcher at the forefront of precision viticulture, specializing in the application of deep learning and hyperspectral imaging to automate critical vineyard operations. His work primarily targets two labor-intensive tasks: winter pruning and ripeness estimation. Guadagna’s major contributions include developing novel computer vision methods for detecting pruning regions and segmenting plant organs in dormant grapevines, as well as pioneering on-the-go, non-destructive ripeness assessment using proximal snapshot hyperspectral imaging. His most cited paper (2023, 24 citations) demonstrates how deep learning can reduce the bottleneck of selective winter pruning, a task requiring 80-120 hours per hectare annually. A subsequent study (2024, 11 citations) advances high-throughput, real-time fruit monitoring to optimize harvest timing. By creating semantic-instance-aware plant models for precise pruning point detection, Guadagna is laying the groundwork for fully autonomous robotic pruning systems. His integrated approach—combining machine vision, robotics, and spectral analysis—directly addresses the skilled labor shortage in viticulture, promising to significantly lower production costs while maintaining quality.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3