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.

Mycotoxins are secondary metabolites produced by fungi that, depending on the type and exposure levels, can be a threat to human and animal health. When multiple mycotoxins occur together, their risk effects on human and animal health can be additive or synergistic. Little information is known about the specific types of mycotoxins or their co-occurrence in the state of Michigan and the Great Lakes region of the United States. To understand the types, incidences, severities, and frequency of co-occurrence of mycotoxins in maize grain (Zea mays L.), samples were collected from across Michigan over two years and analyzed for 20 different mycotoxins. Every sample was contaminated with at least four and six mycotoxins in 2017 and 2018, respectively. Incidence and severity of each mycotoxin varied by year and across locations. Correlations were found between mycotoxins, particularly mycotoxins produced by Fusarium spp. Environmental differences at each location played a role in which mycotoxins were present and at what levels. Overall, data from this study demonstrated that mycotoxin co-occurrence occurs at high levels in Michigan, especially with mycotoxins produced by Fusarium spp., such as deoxynivalenol.

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.

Long‐term weather patterns (environmental conditions or stresses exceeding 10 days in length) have the potential to influence corn (Zea mays L.) growth, development, and yield. This review summarizes the current knowledge (with emphasis placed on the Midwestern U.S. production environment) on how long‐term weather conditions affect corn growth and yield, including (i) drought and heat stress, (ii) solar radiation, and (iii) distribution of heat unit accumulation during the season. Each section contains summaries of how these environmental factors influence corn growth and yield and provides context into past events experienced. The focus of the review is on dent corn grown for grain production, though relevant issues related to other types (i.e., silage corn) are included. This review also discusses agronomic recommendations or considerations to help alleviate the negative effects of stress conditions and identify areas where future research would be beneficial to continue improving the resiliency of corn cropping systems. Periods of high heat and water deficit as well as limited light availability challenge the ability to maximize yield production in corn. Temperature affects crop growth and development through the season, and accurately describing phenological progression using heat unit accumulation is a challenge. Advances in corn breeding and genetics, hybrid selection, and agronomic management practices will be key to ensuring long‐range productivity and fully leveraging possible benefits from the shifts in long‐range weather patterns.

As soybean [Glycine max (L.) Merr.] yields reach record highs, more nutrients are required to maintain these production levels. This study was conducted to evaluate the effect of S and N on soybean yield in diverse environments across the United States. Data were collected from a total of 52 sites in 10 states over 2 yr (2019 and 2020) for this study. A factorial arrangement of three S rates (11, 22, and 33 kg S ha⁻¹) using two sources (ammonium sulfate [AMS] and calcium sulfate [CaSO₄]) were broadcasted by hand at planting. Additionally, to examine the impact of N on soybean yield, urea was applied at 10, 20, and 29 kg N ha⁻¹ to equal that supplied by AMS. A zero‐fertilizer control treatment was also included. Soil samples prior to fertilization as well as grain yield at R8 were collected and analyzed to understand what environmental conditions favor soybean response to S additions. Results indicated that soil and environmental factors are poor indicators of yield response to S and N additions. Yield responses to S and N additions were observed in yield environments averaging >3,643 kg ha⁻¹, but S did not limit yield in most environments (n = 49). Partial profit analysis was conducted at two soybean grain prices (US$0.32 and $0.55 kg ha⁻¹). Yield increases were only profitable at 2 site‐years at the tested soybean grain prices. Overall results suggest that use of N and S fertilizers are rarely justified across diverse growing environments.