AI-Driven Innovations in Plant Phenotyping and Genomics

Plant science is rapidly integrating artificial intelligence (AI) and machine learning (ML) to improve the precision, scale, and throughput of phenotypic analysis. However, translating computational advances into reliable field and laboratory applications remains difficult due to environmental variability, sensor noise, heterogeneous datasets, and limited model interpretability. While early applications relied heavily on standard convolutional networks, current research requires robust methodologies capable of handling multi-modal sensor inputs, complex 3D plant structures, and cross-environment deployment. Important challenges remain in model generalizability, reproducibility, validation on independent datasets, and the development of transparent AI frameworks.This Research Topic focuses on cutting-edge AI and computer vision methodologies specifically developed or adapted for plant phenotyping in Technical Advances in Plant Science. We aim to highlight technical innovations that advance trait measurement accuracy, automate multi-dimensional feature extraction, and ensure model robustness across diverse crop species and growth conditions.We welcome Original Research, Methods, Reviews, and Perspectives addressing, but not limited to, the following core themes:• Vision transformers, foundation models, and self-supervised learning for image-based plant phenotyping • 3D reconstruction, point-cloud analysis, and multi-view sensing for organ- and canopy-level trait quantification• Domain adaptation, transfer learning, and cross-environment model generalizability • Explainable, interpretable, and biologically grounded AI architectures for high-throughput phenotyping • Open benchmark datasets, reproducible computational workflows, and standardized validation protocolsThis Research Topic welcomes Original Research, Reviews, Mini Reviews, Systematic Reviews, Methods, Perspectives, Brief Research Reports, Data Reports, Opinions, and General Commentaries. Topic editors: Frédéric Cointault, David Rousseau, Jean-Pierre Chanet Source: https://www.frontiersin.org/research-topics/85264/ai-driven-innovations-in-plant-phenotyping-and-genomics