Core Ideas: A current estimate of global P use efficiency for cereal production is not available. This study shows that world P use efficiency for cereal crops is low. Using the difference method, average world P use efficiency from 1961 to 2013 was 16%. A current estimate of global phosphorus use efficiency (PUE) for cereal production is not available. The objectives of this paper were to estimate PUE for cereal crops grown in the world and to review methods for improvement. Phosphorus use efficiency was determined using world cereal harvested area, total grain production, and P fertilizer consumption from 1961 to 2013, in addition to assumptions established from previous literature. World PUE of cereal crops was calculated using both balance and difference methods. Using the balance method, cereal grain P uptake is divided by the P fertilizer applied. Alternatively, the difference method accounts for P coming from the soil and that is subtracted from applied P. Utilized in this analysis is the estimate that cereal production accounts for 61% of the total harvested cropland. Cereal grain yields increased from 1.35 to 3.90 Mg h⁻¹ between 1961 and 2013. In 1961, the world's fertilizer P consumption was 4,770,182 Mg and increased to 16,662,470 Mg of P fertilizer by 2013. This represents a 3.5× increase in P fertilizer consumption over 53 yr. Phosphorus use efficiency estimated using the balance method was 77%. Using the difference method, PUE for cereal production in the world was estimated to be 16%.

Core Ideas: Potassium use efficiency in cereals is unknown. World demand for potassium in agriculture is increasing. Potassium is a non‐renewable resource. Worldwide potassium (K) fertilizer use has grown, while the expected fertilizer use efficiency has decreased. The objective of this paper was to estimate potassium use efficiency (KUE) for cereal crops and report on methods that will most likely lead to improved KUE. World KUE was calculated using the total area under cereal production, total cereal grain production, percent K content in cereal grains and K fertilizer consumed from 1961 to 2015. All data was obtained from FAOSTAT except percent K grain content, which was acquired from the USDA. The reported KUE estimate included assumptions established in prior literature. The percent K coming from the soil was estimated at 71%, while previous year K fertilizer‐residual‐effects were offset by knowing that similar amounts of fertilizer K will be applied in following years. At current consumption rates, existing K reserves as K₂0 are estimated to last 100 yr meaning that mining operations will need to expand to meet expected market demands. Results showed that cereal production increased by a factor of 3.2 from 1961 to 2015 and that was accompanied by a threefold increase in fertilizer K consumed. Estimated KUE from 1961 to 2015 for world cereal crops using the difference method was 19%. Combined with findings from this paper, estimates of N, P, and K use efficiency for cereal production in the world stand at 33, 16, and 19%, respectively.

Timely and cost-effective crop yield prediction is vital in crop management decision-making. This study evaluates the efficacy of Unmanned Aerial Vehicle (UAV)-based Vegetation Indices (VIs) coupled with Machine Learning (ML) models for corn (Zea mays) yield prediction at vegetative (V6) and reproductive (R5) growth stages using a limited number of training samples at the farm scale. Four agronomic treatments, namely Austrian Winter Peas (AWP) (Pisum sativum L.) cover crop, biochar, gypsum, and fallow with sixteen replications were applied during the non-growing corn season to assess their impact on the following corn yield. Thirty different variables (i.e., four spectral bands: green, red, red edge, and near-infrared and twenty-six VIs) were derived from UAV multispectral data collected at the V6 and R5 stages to assess their utility in yield prediction. Five different ML algorithms including Linear Regression (LR), k-Nearest Neighbor (KNN), Random Forest (RF), Support Vector Regression (SVR), and Deep Neural Network (DNN) were evaluated in yield prediction. One-year experimental results of different treatments indicated a negligible impact on overall corn yield. Red edge, canopy chlorophyll content index, red edge chlorophyll index, chlorophyll absorption ratio index, green normalized difference vegetation index, green spectral band, and chlorophyll vegetation index were among the most suitable variables in predicting corn yield. The SVR predicted yield for the fallow with a Coefficient of Determination (R²) and Root Mean Square Error (RMSE) of 0.84 and 0.69 Mg/ha at V6 and 0.83 and 1.05 Mg/ha at the R5 stage, respectively. The KNN achieved a higher prediction accuracy for AWP (R² = 0.69 and RMSE = 1.05 Mg/ha at V6 and 0.64 and 1.13 Mg/ha at R5) and gypsum treatment (R² = 0.61 and RMSE = 1.49 Mg/ha at V6 and 0.80 and 1.35 Mg/ha at R5). The DNN achieved a higher prediction accuracy for biochar treatment (R² = 0.71 and RMSE = 1.08 Mg/ha at V6 and 0.74 and 1.27 Mg/ha at R5). For the combined (AWP, biochar, gypsum, and fallow) treatment, the SVR produced the most accurate yield prediction with an R² and RMSE of 0.36 and 1.48 Mg/ha at V6 and 0.41 and 1.43 Mg/ha at the R5. Overall, the treatment-specific yield prediction was more accurate than the combined treatment. Yield was most accurately predicted for fallow than other treatments regardless of the ML model used. SVR and KNN outperformed other ML models in yield prediction. Yields were predicted with similar accuracy at both growth stages. Thus, this study demonstrated that VIs coupled with ML models can be used in multi-stage corn yield prediction at the farm scale, even with a limited number of training data.

Climate change and its impact on agriculture productivity vary among crops and regions. The southeastern United States (SE-US) is agro-ecologically diversified, economically dependent on agriculture, and mostly overlooked by agroclimatic researchers. The objective of this study was to compute the effect of climatic variables; daily maximum temperature (T_max), daily minimum temperature (T_min), and rainfall on the yield of major cereal crops i.e., corn (Zea mays L.), rice (Oryza sativa L.), and wheat (Triticum aestivum L.) in SE-US. A fixed-effect model (panel data approach) was used by applying the production function on panel data from 1980 to 2020 from 11 SE-US states. An asymmetrical warming pattern was observed, where nocturnal warming was 105.90%, 106.30%, and 32.14%, higher than the diurnal warming during corn, rice, and wheat growing seasons, respectively. Additionally, a shift in rainfall was noticed ranging from 19.2 to 37.2 mm over different growing seasons. Rainfall significantly reduced wheat yield, while, it had no effect on corn and rice yields. The T_max and T_min had no significant effect on wheat yield. A 1 °C rise in T_max significantly decreased corn (− 34%) and rice (− 8.30%) yield which was offset by a 1 °C increase in T_min increasing corn (47%) and rice (22.40%) yield. Conclusively, overall temperature change of 1 °C in the SE-US significantly improved corn yield by 13%, rice yield by 14.10%, and had no effect on wheat yield.

Method of N application in winter wheat (Triticum aestivum L.) and its impact on estimated plant N loss has not been extensively evaluated. The effects of the pre‐plant N application method, topdress N application method, and their interactions on grain yield, grain protein concentration (GPC), nitrogen fertilizer recovery use efficiency (NFUE), and gaseous N loss was investigated. The trials were set up in an incomplete factorial within a randomized complete block design and replicated three times for 5 site‐years. Data collection included normalized difference vegetation index (NDVI), grain yield, and forage and grain N concentration. The NDVI before and after 90 growing degree days (GDD) were correlated with final grain yield, grain N uptake, GPC, and NFUE. At Efaw location, NDVI after 90 GDDs accounted for 58% of variation in grain yield and 51% variation in grain N uptake. However, NDVI was found to be a poor indicator of both GPC and NFUE. Grain yield was not affected by the method and timing of N application at Efaw. Alternatively, at Perkins, topdress applications resulted in higher yields. The GPC and NFUE were improved with the topdress applications. Generally, topdress application enhanced GPC and NFUE without decreasing the final grain yield. The difference method used in calculating gaseous N loss did not always reveal similar results, and estimated plant N loss was variable by site‐year, and depended on daily fluctuations in the environment.