Together with the rise of whole-genome sequencing of many plant species, large-scale and high-throughput plant phenotyping (HTP), as well as associated phenotypic analysis, has become a bottleneck that needs to be urgently relieved (Yang et al., 2020). Plant genetics and crop breeding can be accelerated by recent rapid advances through diverse technologies, from sensors to feature extraction, combined with increasing systems integration and decreasing costs in software and hardware systems. The integration of artificial intelligence (AI) driven techniques (e.g., deep learning and machine learning), computer vision, and big-data analytics, and their optimization for the life sciences, has opened doors to new opportunities for a broad plant science research community to develop step change solutions to bridge the gap between traits of interest and genomic information for novel biological discoveries (Tardieu et al., 2017; Zhao et al., 2019). In particular, recent developments in multi-factorial phenotypic models can be dynamically generated from large biological datasets to characterize phenotypic features, including the prediction of genotypic reaction to complex environments as well as genotype-based phenotypic changes across multiple seasons (Großkinsky et al., 2015; Furbank et al., 2019). Such methodological and technical advances have empowered plant scientists to unravel the genetics of complex phenotypes at the levels of cell, organ, tissue, plant, and population (Fiorani and Schurr, 2013).
