Search for: All records

Abstract Preharvest yield estimates can be used for harvest planning, marketing, and prescribing in‐season fertilizer and pesticide applications. One approach that is being widely tested is the use of machine learning (ML) or artificial intelligence (AI) algorithms to estimate yields. However, one barrier to the adoption of this approach is that ML/AI algorithms behave as a black block. An alternative approach is to create an algorithm using Bayesian statistics. In Bayesian statistics, prior information is used to help create the algorithm. However, algorithms based on Bayesian statistics are not often computationally efficient. The objective of the current study was to compare the accuracy and computational efficiency of four Bayesian models that used different assumptions to reduce the execution time. In this paper, the Bayesian multiple linear regression (BLR), Bayesian spatial, Bayesian skewed spatial regression, and the Bayesian nearest neighbor Gaussian process (NNGP) models were compared with ML non‐Bayesian random forest model. In this analysis, soybean (Glycine max) yields were the response variable (y), and spaced‐based blue, green, red, and near‐infrared reflectance that was measured with the PlanetScope satellite were the predictor (x). Among the models tested, the Bayesian (NNGP;R²‐testing = 0.485) model, which captures the short‐range correlation, outperformed the (BLR;R²‐testing = 0.02), Bayesian spatial regression (SRM;R²‐testing = 0.087), and Bayesian skewed spatial regression (sSRM;R²‐testing = 0.236) models. However, associated with improved accuracy was an increase in run time from 534 s for the BLR model to 2047 s for the NNGP model. These data show that relatively accurate within‐field yield estimates can be obtained without sacrificing computational efficiency and that the coefficients have biological meaning. However, all Bayesian models had lowerR²values and higher execution times than the random forest model. 

Core Ideas Decision support systems (DSSs) are one component of precision agriculture (PA). The accuracy of DSSs may be improved by using algorithms based on machine learning. Barriers to DSSs include financial constraints, hesitancy to change, data privacy, and workforce limitations. Professional opportunities exist to overcome DSS adoption barriers. 

By influencing soil organic carbon (SOC), cover crops play a key role in shaping soil health and hence the system's long‐term sustainability. However, the magnitude by which cover crops impacts SOC depends on multiple factors, including soil type, climate, crop rotation, tillage type, cover crop growth, and years under management. To elucidate how these multiple factors influence the relative impact of cover crops on SOC, we conducted a meta‐analysis on the impacts of cover crops within rotations that included corn (Zea maysL.) on SOC accumulation. Information on climatic conditions, soil characteristics, management, and cover crop performance was extracted, resulting in 198 paired comparisons from 61 peer‐reviewed studies. Over the course of each study, cover crops on average increased SOC by 7.3% (95% CI, 4.9%–9.6%). Furthermore, the impact of cover crop–induced increases in percent change SOC was evaluated across soil textures, cover crop types, crop rotations, biomass amounts, cover crop durations, tillage practices, and climatic zones. Our results suggest that current cover crop–based corn production systems are sequestering 5.5 million Mg of SOC per year in the United States and have the potential to sequester 175 million Mg SOC per year globally. These findings can be used to improve carbon footprint calculations and develop science‐based policy recommendations. Taken altogether, cover cropping is a promising strategy to sequester atmospheric C and hence make corn production systems more resilient to changing climates. 

Abstract Because the manual counting of soybean ( Glycine max ) plants, pods, and seeds/pods is unsuitable for soybean yield predictions, alternative methods are desired. Therefore, the objective was to determine if satellite remote sensing − based artificial intelligence (AI) models could be used to predict soybean yield. In the study, multiple remote sensing − based AI models were developed for soybean growth stage ranging from VE/VC (plant emergence) to R6/R7 (full seed to beginning maturity). The ability of the Deep Neural Network (DNN), Support Vector Machine (SVM), Random Forest (RF), Least Absolute Shrinkage and Selection Operator (LASSO), and AdaBoost to predict soybean yield, based on blue, green, red, and near infrared reflectance data collected by the PlanetScope satellite at 6 growth stages, was determined. Remote sensing and soybean yield monitor data from 3 different fields in two years (2019 and 2021) were aggregated into 24,282 grid cells that had the dimensions of 10 by 10m. A comparison across models showed that the DNN outperformed the other models. Moreover, as crops matured from VE/VC to R4/R5, the R 2 value of the models increased from 0.26 to over 0.70. These findings indicate that remote sensing data collected at different growth stages can be combined for soybean yield predictions. Moreover, additional work needs to be conducted to assess the model's ability to predict soybean yield with vegetation indices (VI) data for fields not used to train the model. This article is protected by copyright. All rights reserved 

Core Ideas The rye cover crop decreased N 2 O–N emission during early growth and increased emission during decomposition. The rye cover crop reduced the partial CO 2e from 496 to −1,061. In 2019 and 2020, decomposing cover crop emitted 27 and 69% of fixed C, respectively. The random forest model outperformed other models by accounting for 73% of the variation in the N 2 O–N daily emissions. Daily CO 2 ‐C emissions was also best predicted by the random forest model with 85% of variation explained.