Climate change has a strong influence on weather patterns and significantly affects crop yields globally. El Niño Southern Oscillation (ENSO) has a strong influence on the U.S. climate and is related to agricultural production variability. ENSO effects are location-specific and in southeastern U.S. strongly connect with climate variability. When combined with climate change, the effects on growing season climate patterns and crop yields might be greater than expected. In our study, historical monthly precipitation and temperature data were coupled with non-irrigated maize yield data (33–43 years depending on the location) to show a potential yield suppression of ~15% for one °C increase in southeastern U.S. growing season maximum temperature. Yield suppression ranged between −25 and −2% among locations suppressing the southeastern U.S. average yield trend since 1981 by 17 kg ha−1year−1 (~25%), mainly due to year-to-year June temperature anomalies. Yields varied among ENSO phases from 1971–2013, with greater yields observed during El Niño phase. During La Niña years, maximum June temperatures were higher than Neutral and El Niño, whereas June precipitation was lower than El Niño years. Our data highlight the importance of developing location-specific adaptation strategies quantifying both, climate change and ENSO effects on month-specific growing season climate conditions.

Core Ideas Evaluation of the influence of planting date on corn aflatoxin. Evaluation on how in‐season weather conditions influence corn aflatoxin. Evaluation of the influence of planting density on corn aflatoxin. Identification of the growing season periods when the aflatoxin risk is highest. Evaluation of the relationship between yield and corn aflatoxin. Aflatoxins are a group of toxins produced by fungi found on corn (Zea mays L.). Aflatoxin contamination can make it unmarketable. Fortunately, management practices that reduce stress during critical growth stages lessen contamination. A study was conducted at Fairhope, AL (2010–2014), and Prattville, AL (2013–2014), to evaluate the effect of planting dates, plant densities, and in‐season weather conditions on preharvest aflatoxin contamination. The experiment had a split‐split‐plot design replicated six times, with inoculation method assigned to the main plots, planting date to the subplots, and planting density to the sub‐subplots. Results showed that delaying planting from mid‐March to mid‐April reduced aflatoxin levels and increasing the planting density from 44,480 to 74,130 plants ha−1 did not impact toxin accumulation. Multiple linear regression indicated that minimum air temperature and rainfall models could explain from 50 to 76% of the observed aflatoxin variability. However, the effect of both variables on aflatoxin contamination levels changed during the period pre‐silking (14 d prior) to physiological maturity. Minimum temperature alone had the strongest positive influence on aflatoxin over the 2 wk after mid‐silk. A reduction in rainfall during 2 wk prior mid‐silk and from Day 43 after mid‐silk to physiological maturity resulted on high aflatoxin contamination levels. In conclusion, a better understanding of the influence of weather variables on corn contamination may lead to better crop management and development of more accurate prediction systems.

No abstract

HighlightsNARX and LSTM recurrent neural networks were evaluated for prediction of irrigation prescriptions.LSTM neural networks presented the best performance for irrigation scheduling using soil matric potential sensors.NARX neural networks had the best performance for predicting irrigation prescriptions using weather data.High performance for several time-ahead predictions using both recurrent neural networks, with R2 > 0.94.The results can be adopted as a decision-support tool in irrigation scheduling for fields with different types of soils.Abstract. The implementation of adequate irrigation strategies could be done through real-time monitoring of soil water status at several soil depths; however, this could also represent a complex nonlinear problem due to the plant-soil-weather relationships. In this study, two recurrent neural network (RNN) models were evaluated to estimate irrigation prescriptions. Data for this study were collected from an on-farm corn irrigation study conducted between 2017 and 2019 in Samson, Alabama. The study used hourly data of weather and soil matric potential (SMP) monitored at three soil depths from 13 sensor probes installed on a loamy fine sand soil and a sandy clay loam soil. Two neural network methods, i.e., a nonlinear autoregressive with exogenous (NARX) input system and long short-term memory (LSTM), were trained, validated, and tested with a maximum dataset of 20,052 records and a maximum of eight categorical attributes to estimate one-step irrigation prescriptions. The performance of both methods was evaluated by varying the model development parameters (neurons or blocks, dropout, and epochs) and determining their impact on the final model prediction. Results showed that both RNN models demonstrated good capability in the prediction of irrigation prescriptions for the soil types studied, with a coefficient of determination (R2) > 0.94 and root mean square error (RMSE) < 1.2 mm. The results of this study indicate that after training the RNNs using the dataset collected in the field, models using only SMP sensors at three soil depths obtained the best performance, followed by models that used only data of solar radiation, temperature, and relative humidity in the prediction of irrigation prescriptions. For future applicability, the RNN models can be extended using datasets from other places for training, which would allow the adoption of a unique data-driven soil moisture model for irrigation scheduling useful in a wide range of soil types. Keywords: Corn, Irrigation scheduling, Machine learning, Modeling, Soil matric potential sensor.