Application of Machine Learning Methodologies for Predicting Corn Economic Optimal Nitrogen Rate

Qin, Zhisheng; Myers, D. Brenton; Ransom, Curtis J.; Kitchen, Newell R.; Liang, Sang Zi; Camberato, James J.; Carter, Paul R.; Ferguson, Richard B.; Fernández, Fabián G.; Franzen, David W.; Laboski, Carrie A. M.; Malone, Brad D.; Nafziger, Emerson D.; Sawyer, John E.; Shanahan, John F.

doi:10.2134/agronj2018.03.0222

Cited by 60 publications

(47 citation statements)

References 38 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to simple N recommendation tools such as the yield goal approach, soil nitrate-N test, or use of the long-term average EONR, our model accounts for spatial and temporal variability and thus is well suited for application in precision agriculture. This study expands earlier efforts to predict corn's EONR using more than one explanatory variable in Argentina (Gregoret et al, 2011;Coyos et al, 2018) and in the USA (Qin et al, 2018). Gregoret et al (2011) considered total soil N and available water, Coyos et al (2018) soil N, planting time, and soil type, while Qin et al (2018) considered soil water holding capacity and minimum groundwater table depth.…”

Section: Implications Of the Developed Modelsmentioning

confidence: 83%

“…This study expands earlier efforts to predict corn's EONR using more than one explanatory variable in Argentina (Gregoret et al, 2011;Coyos et al, 2018) and in the USA (Qin et al, 2018). Gregoret et al (2011) considered total soil N and available water, Coyos et al (2018) soil N, planting time, and soil type, while Qin et al (2018) considered soil water holding capacity and minimum groundwater table depth. Our model has six explanatory variables for EONR, which resulted from statistical analysis of their importance (Fig.…”

Section: Implications Of the Developed Modelsmentioning

confidence: 83%

See 1 more Smart Citation

Development of a nitrogen recommendation tool for corn considering static and dynamic variables

Puntel

Pagani

Archontoulis

2019

European Journal of Agronomy

View full text Add to dashboard Cite

Many soil and weather variables can affect the economical optimum nitrogen (N) rate (EONR) for maize. We classified 54 potential factors as dynamic (change rapidly over time, e.g. soil water) and static (change slowly over time, e.g. soil organic matter) and explored their relative importance on EONR and yield prediction by analyzing a dataset with 51 N trials from Central-West region of Argentina. Across trials, the average EONR was 113 ± 83 kg N ha −1 and the average optimum yield was 12.3 ± 2.2 Mg ha −1 , which is roughly 50% higher than the current N rates used and yields obtained by maize producers in that region. Dynamic factors alone explained 50% of the variability in the EONR whereas static factors explained only 20%. Best EONR predictions resulted by combining one static variable (soil depth) together with four dynamic variables (number of days with precipitation>20 mm, residue amount, soil nitrate at planting, and heat stress around silking). The resulting EONR model had a mean absolute error of 39 kg N ha −1 and an adjusted R 2 of 0.61. Interestingly, the yield of the previous crop was not an important factor explaining EONR variability. Regression models for yield at optimum and at zero N fertilization

show abstract

Section: Implications Of the Developed Modelsmentioning

confidence: 83%

Section: Implications Of the Developed Modelsmentioning

confidence: 83%

Development of a nitrogen recommendation tool for corn considering static and dynamic variables

Puntel

Pagani

Archontoulis

2019

European Journal of Agronomy

View full text Add to dashboard Cite

show abstract

“…For example, Ramanantenasoa et al (2019) evaluated the performance of various ML based meta-models to emulate the complex process-based models in predicting ammonia emissions produced by agricultural activities and demonstrated the superiority of random forests compared to LASSO regression. Lawes et al (2019) used ML and APSIM modeling to predict optimum N rates for wheat, Puntel et al (2019) and Qin et al (2018) used ML and experimental data to predict optimum N rates to maize, while others are exploring coupling ML and simulation models to develop faster and more flexible tools for impact regional assessments (Fienen et al 2015) and simulation model parameterization (Gladish et al 2019).…”

Section: Discussionmentioning

confidence: 99%

“…Although the literature is rich on comparisons among the skill of various ML algorithms in predicting agricultural outcomes (e.g. Landau et al 2000, Sheehy et al 2006, González Sánchez et al 2014, Morellos et al 2016, Qin et al 2018, these are largely based on empirical data. Sensitivity analysis studies have looked at the performance of several approaches to emulate simulated results (Gladish et al 2019), but their focus is on approximating the distribution of continuous crop model parameters.…”

Section: Introductionmentioning

confidence: 99%

Maize yield and nitrate loss prediction with machine learning algorithms

Shahhosseini

Martinez-Feria

et al. 2019

Environ. Res. Lett.

152

View full text Add to dashboard Cite

Pre-growing season prediction of crop production outcomes such as grain yields and nitrogen (N) losses can provide insights to farmers and agronomists to make decisions. Simulation crop models can assist in scenario planning, but their use is limited because of data requirements and long runtimes. Thus, there is a need for more computationally expedient approaches to scale up predictions. We evaluated the potential of four machine learning (ML) algorithms (LASSO Regression, Ridge Regression, random forests, Extreme Gradient Boosting, and their ensembles) as meta-models for a cropping systems simulator (APSIM) to inform future decision support tool development. We asked:(1) How well do ML meta-models predict maize yield and N losses using pre-season information? (2) How many data are needed to train ML algorithms to achieve acceptable predictions? (3) Which input data variables are most important for accurate prediction? And (4) do ensembles of ML meta-models improve prediction? The simulated dataset included more than three million data including genotype, environment and management scenarios. XGBoost was the most accurate ML model in predicting yields with a relative mean square error (RRMSE) of 13.5%, and Random forests most accurately predicted N loss at planting time, with a RRMSE of 54%. ML meta-models reasonably reproduced simulated maize yields using the information available at planting, but not N loss. They also differed in their sensitivities to the size of the training dataset. Across all ML models, yield prediction error decreased by 10%-40% as the training dataset increased from 0.5 to 1.8 million data points, whereas N loss prediction error showed no consistent pattern. ML models also differed in their sensitivities to input variables (weather, soil properties, management, initial conditions), thus depending on the data availability researchers may use a different ML model. Modest prediction improvements resulted from ML ensembles. These results can help accelerate progress in coupling simulation models and ML toward developing dynamic decision support tools for pre-season management.

show abstract

“…Prior efforts showed promising results using ML algorithms to directly predict EONR using soil and weather information (Qin et al, 2018). However, these efforts did not utilize existing N recommendation methods which are already familiar to farmers.…”

Section: Improving Nitrogen Recommendation Toolsmentioning

confidence: 99%

Statistical and machine learning methods evaluated for incorporating soil and weather into corn nitrogen recommendations

Ransom

Kitchen²,

Camberato

et al. 2019

Computers and Electronics in Agriculture

Self Cite

View full text Add to dashboard Cite

Nitrogen (N) fertilizer recommendation tools could be improved for estimating corn (Zea mays L.) N needs by incorporating site-specific soil and weather information. However, an evaluation of analytical methods is needed to determine the success of incorporating this information. The objectives of this research were to evaluate statistical and machine learning (ML) algorithms for utilizing soil and weather information for improving corn N recommendation tools. Eight algorithms [stepwise, ridge regression, least absolute shrinkage and selection operator (Lasso), elastic net regression, principal component regression (PCR), partial least squares regression (PLSR), decision tree, and random forest] were evaluated using a dataset containing measured soil and weather variables from a regional database. The performance was evaluated based on how well these algorithms predicted corn economically optimal N rates (EONR) from 49 sites in the U.S. Midwest. Multiple algorithm modeling scenarios were examined with and without adjustment for multicollinearity and inclusion of two-way interaction terms to identify the soil and weather variables that could improve three dissimilar N recommendation tools. Results showed the out-of-sample root-mean-square error (RMSE) for the decision tree and some random forest modeling scenarios were better than the stepwise or ridge regression, but not significantly different than any other algorithm. The best ML algorithm for adjusting N recommendation tools was the random forest approach (r 2 increased between 0.72 and 0.84 and the RMSE decreased between 41 and 94 kg N ha −1). However, the ML algorithm that best adjusted tools while using a minimal amount of variables was the decision tree. This method was simple, needing only one or two variables (regardless of modeling scenario) and provided moderate improvement as r 2 values increased between 0.15 and 0.51 and RMSE decreased between 16 and 66 kg N ha −1. Using ML algorithms to adjust N recommendation tools with soil and weather information shows promising results for better N management in the U.S. Midwest.

show abstract

Application of Machine Learning Methodologies for Predicting Corn Economic Optimal Nitrogen Rate

Cited by 60 publications

References 38 publications

Development of a nitrogen recommendation tool for corn considering static and dynamic variables

Development of a nitrogen recommendation tool for corn considering static and dynamic variables

Maize yield and nitrate loss prediction with machine learning algorithms

Statistical and machine learning methods evaluated for incorporating soil and weather into corn nitrogen recommendations

Contact Info

Product

Resources

About