Maize (Zea mays L.) is one of the most consumed grains in the world. Within the context of continuous climate change and the reduced availability of arable land, it is urgent to breed new maize varieties and screen for the desired traits, e.g., high yield and strong stress tolerance. Traditional phenotyping methods relying on manual assessment are time-consuming and prone to human errors. Recently, the application of uncrewed aerial vehicles (UAVs) has gained increasing attention in plant phenotyping due to their efficiency in data collection. Moreover, hyperspectral sensors integrated with UAVs can offer data streams with high spectral and spatial resolutions, which are valuable for estimating plant traits. In this study, we collected UAV hyperspectral imagery over a maize breeding field biweekly across the growing season, resulting in 11 data collections in total. Multiple machine learning models were developed to estimate the grain yield and flowering time of the maize breeding lines using the hyperspectral imagery. The performance of the machine learning models and the efficacy of different hyperspectral features were evaluated. The results showed that the models with the multi-temporal imagery outperformed those with imagery from single data collections, and the ridge regression using the full band reflectance achieved the best estimation accuracies, with the correlation coefficients (r) between the estimates and ground truth of 0.54 for grain yield, 0.91 for days to silking, and 0.92 for days to anthesis. In addition, we assessed the estimation performance with data acquired at different growth stages to identify the good periods for the UAV survey. The best estimation results were achieved using the data collected around the tasseling stage (VT) for the grain yield estimation and around the reproductive stages (R1 or R4) for the flowering time estimation. Our results showed that the robust phenotyping framework proposed in this study has great potential to help breeders efficiently estimate key agronomic traits at early growth stages.

Accurate prediction of the phenotypic outcomes produced by different combinations of genotypes, environments, and management interventions remains a key goal in biology with direct applications to agriculture, research, and conservation. The past decades have seen an expansion of new methods applied toward this goal. Here we predict maize yield using deep neural networks, compare the efficacy of 2 model development methods, and contextualize model performance using conventional linear and machine learning models. We examine the usefulness of incorporating interactions between disparate data types. We find deep learning and best linear unbiased predictor (BLUP) models with interactions had the best overall performance. BLUP models achieved the lowest average error, but deep learning models performed more consistently with similar average error. Optimizing deep neural network submodules for each data type improved model performance relative to optimizing the whole model for all data types at once. Examining the effect of interactions in the best-performing model revealed that including interactions altered the model's sensitivity to weather and management features, including a reduction of the importance scores for timepoints expected to have a limited physiological basis for influencing yield—those at the extreme end of the season, nearly 200 days post planting. Based on these results, deep learning provides a promising avenue for the phenotypic prediction of complex traits in complex environments and a potential mechanism to better understand the influence of environmental and genetic factors.

Genotype-by-environment (G×E) interactions can significantly affect crop performance and stability. Investigating G×E requires extensive data sets with diverse cultivars tested over multiple locations and years. The Genomes-to-Fields (G2F) Initiative has tested maize hybrids in more than 130 year-locations in North America since 2014. Here, we curate and expand this data set by generating environmental covariates (using a crop model) for each of the trials. The resulting data set includes DNA genotypes and environmental data linked to more than 70,000 phenotypic records of grain yield and flowering traits for more than 4000 hybrids. We show how this valuable data set can serve as a benchmark in agricultural modeling and prediction, paving the way for countless G×E investigations in maize. We use multivariate analyses to characterize the data set’s genetic and environmental structure, study the association of key environmental factors with traits, and provide benchmarks using genomic prediction models.

Objectives: The Genomes to Fields (G2F) 2022 Maize Genotype by Environment (GxE) Prediction Competition aimed to develop models for predicting grain yield for the 2022 Maize GxE project field trials, leveraging the datasets previously generated by this project and other publicly available data. Data description: This resource used data from the Maize GxE project within the G2F Initiative [1]. The dataset included phenotypic and genotypic data of the hybrids evaluated in 45 locations from 2014 to 2022. Also, soil, weather, environmental covariates data and metadata information for all environments (combination of year and location). Competitors also had access to ReadMe files which described all the files provided. The Maize GxE is a collaborative project and all the data generated becomes publicly available [2]. The dataset used in the 2022 Prediction Competition was curated and lightly filtered for quality and to ensure naming uniformity across years.

The Stiff Stalk heterotic pool is a foundation of US maize seed parent germplasm and has been heavily utilized by both public and private maize breeders since its inception in the 1930s. Flowering time and plant height are critical characteristics for both inbred parents and their test crossed hybrid progeny. To study these traits, a 6-parent multiparent advanced generation intercross population was developed including maize inbred lines B73, B84, PHB47 (B37 type), LH145 (B14 type), PHJ40 (novel early Stiff Stalk), and NKH8431 (B73/B14 type). A set of 779 doubled haploid lines were evaluated for flowering time and plant height in 2 field replicates in 2016 and 2017, and a subset of 689 and 561 doubled haploid lines were crossed to 2 testers, respectively, and evaluated as hybrids in 2 locations in 2018 and 2019 using an incomplete block design. Markers were derived from a practical haplotype graph built from the founder whole genome assemblies and genotype-by-sequencing and exome capture-based sequencing of the population. Genetic mapping utilizing an update to R/qtl2 revealed differing profiles of significant loci for both traits between 635 of the DH lines and 2 sets of 570 and 471 derived hybrids. Genomic prediction was used to test the feasibility of predicting hybrid phenotypes based on the per se data. Predictive abilities were highest on direct models trained using the data they would predict (0.55–0.63), and indirect models trained using per se data to predict hybrid traits had slightly lower predictive abilities (0.49–0.55). Overall, this finding is consistent with the overlapping and nonoverlapping significant quantitative trait loci found within the per se and hybrid populations and suggests that selections for phenology traits can be made effectively on doubled haploid lines before hybrid data is available.

Objectives: This release note describes the Maize GxE project datasets within the Genomes to Fields (G2F) Initiative. The Maize GxE project aims to understand genotype by environment (GxE) interactions and use the information collected to improve resource allocation efficiency and increase genotype predictability and stability, particularly in scenarios of variable environmental patterns. Hybrids and inbreds are evaluated across multiple environments and phenotypic, genotypic, environmental, and metadata information are made publicly available. Data description: The datasets include phenotypic data of the hybrids and inbreds evaluated in 30 locations across the US and one location in Germany in 2020 and 2021, soil and climatic measurements and metadata information for all environments (combination of year and location), ReadMe, and description files for each data type. A set of common hybrids is present in each environment to connect with previous evaluations. Each environment had a collaborator responsible for collecting and submitting the data, the GxE coordination team combined all the collected information and removed obvious erroneous data. Collaborators received the combined data to use, verify and declare that the data generated in their own environments was accurate. Combined data is released to the public with minimal filtering to maintain fidelity to the original data.