Rapid in vitro propagation protocol standardized for an endangered medicinal plant – Picrorhiza kurroa

The agricultural sector faces unprecedented 21st-century challenges due to climate change, resource limitations, and a growing global population. Developing high-yielding, stress-resilient, and nutrient-rich crops has become more critical than ever. Accurate, high-throughput phenotyping, quantifying plant traits that reflect genetic and environmental interactions, is essential for accelerating crop improvement. Traditional phenotyping methods are labor-intensive, time-consuming, and prone to human error. Advances in artificial intelligence (AI), particularly deep learning, are revolutionizing plant phenotyping by leveraging imaging technologies such as RGB, hyperspectral, thermal, and 3D systems. These tools enable automated, precise analysis of complex traits at scale. This review highlights AI-driven phenotyping approaches in crop breeding, with emphasis on convolutional neural networks (CNNs), vision transformers, and multi-modal learning through UAVs, ground-based platforms, and integrated sensor arrays. Key applications include early disease detection, biomass estimation, canopy modeling, and yield prediction. Integrating phenotypic, genotypic, and environmental data using AI will significantly enhance genomic selection, driving more efficient and sustainable crop breeding strategies.