Daniel Petti

Florida Museum of Natural History, University of Florida

Papers

Total Citations

H-Index

About

Daniel Petti is a trailblazer at the intersection of artificial intelligence and precision agriculture, with a primary research focus on deploying advanced machine learning—particularly Graph Neural Networks (GNNs)—to solve complex, real-world challenges in plant phenotyping and crop monitoring. His most cited work, "AGI for Agriculture" (2023, 8 citations), explores the transformative potential of Artificial General Intelligence across sectors, with a specific emphasis on revolutionizing agricultural data analysis and management. Petti’s core technical contributions lie in multi-object tracking and counting for plants. He developed lightweight GNN-based frameworks for tracking individual plant organs over time, as detailed in his 2021 and 2024 papers (2 and 7 citations, respectively), offering a novel alternative to traditional CNN-based methods used in autonomous driving. His most recent work, "Real‐Time Multi‐View Flower Counting With a Ground Mobile Robot" (2025, 3 citations), directly addresses the labor-intensive bottleneck of manual cotton flowering data collection, providing an automated, scalable solution for breeders and growers. By bridging cutting-edge graph-based AI with agricultural robotics, Petti is enabling high-throughput, data-driven insights that promise to accelerate crop breeding and improve yield estimation.