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

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

doi:10.1016/j.compag.2019.104872

Cited by 84 publications

(43 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Others have shown or suggested N recommendation tools could be improved by using various soil and weather adjustments (e.g. active‐optical reflectance sensors [Bean et al., 2018], pre‐sidedress soil nitrate tests, yield‐goal, and Maximum Return to Nitrogen calculators [Ransom, 2018; Ransom et al., 2019]). Similarly, existing N recommendation tools could be improved by adjustments using soil respiration.…”

Section: Resultsmentioning

confidence: 99%

Relating four‐day soil respiration to corn nitrogen fertilizer needs across 49 U.S. Midwest fields

Bean¹,

Kitchen

Veum

et al. 2020

Soil Science Soc of Amer J

Self Cite

View full text Add to dashboard Cite

Soil microbes drive biological functions that mediate chemical and physical processes necessary for plants to sustain growth. Laboratory soil respiration has been proposed as one universal soil health indicator representing these functions, potentially informing crop and soil management decisions. Research is needed to test the premise that soil respiration is helpful for profitable in‐season nitrogen (N) rate management decisions in corn (Zea mays L.). The objective of this research was two‐fold: (i) determine if the amount of N applied at the time of planting effected soil respiration, and (ii) evaluate the relationship of soil respiration to corn yield response to fertilizer N application. A total of 49 N response trials were conducted across eight states over three growing seasons (2014–2016). The 4‐day Comprehensive Assessment of Soil Health (CASH) soil respiration method was used to quantify soil respiration. Averaged over all sites, N fertilization did not impact soil respiration, but at four sites soil respiration decreased as N fertilizer rate applied at‐planting increased. Across all site‐years, soil respiration was moderately related to the economical optimum N rate (EONR) (r2 = 0.21). However, when analyzed by year, soil respiration was more strongly related to EONR in 2016 (r2 = 0.50) and poorly related for the first two years (r2 < 0.20). These results illustrate the factors influencing the ability of laboratory soil respiration to estimate corn N response, including growing‐season weather, and the potential of fusing soil respiration with other soil and weather measurements for improved N fertilizer recommendations.

show abstract

Section: Resultsmentioning

confidence: 99%

Relating four‐day soil respiration to corn nitrogen fertilizer needs across 49 U.S. Midwest fields

Bean¹,

Kitchen

Veum

et al. 2020

Soil Science Soc of Amer J

Self Cite

View full text Add to dashboard Cite

show abstract

“…Liu et al (2001) applied artificial neural networks to approximate a nonlinear function to relate the corn yield to input variables such as weather, soil, and management practices. Ransom et al (2019) evaluated machine learning methods for corn nitrogen recommendation tools using soil and weather information. Drummond et al (2003) investigated stepwise multiple linear regression, projection pursuit regression, and artificial neural networks to predict the grain yield based on the soil properties.…”

Section: Introductionmentioning

confidence: 99%

A CNN-RNN Framework for Crop Yield Prediction

2020

View full text Add to dashboard Cite

Crop yield prediction is extremely challenging due to its dependence on multiple factors such as crop genotype, environmental factors, management practices, and their interactions. This paper presents a deep learning framework using convolutional neural networks (CNNs) and recurrent neural networks (RNNs) for crop yield prediction based on environmental data and management practices. The proposed CNN-RNN model, along with other popular methods such as random forest (RF), deep fully connected neural networks (DFNN), and LASSO, was used to forecast corn and soybean yield across the entire Corn Belt (including 13 states) in the United States for years 2016, 2017, and 2018 using historical data. The new model achieved a root-mean-square-error (RMSE) 9% and 8% of their respective average yields, substantially outperforming all other methods that were tested. The CNN-RNN has three salient features that make it a potentially useful method for other crop yield prediction studies. (1) The CNN-RNN model was designed to capture the time dependencies of environmental factors and the genetic improvement of seeds over time without having their genotype information.(2) The model demonstrated the capability to generalize the yield prediction to untested environments without significant drop in the prediction accuracy. (3) Coupled with the backpropagation method, the model could reveal the extent to which weather conditions, accuracy of weather predictions, soil conditions, and management practices were able to explain the variation in the crop yields.

show abstract

“…Usually, scientists, in their environmental studies, assess multiple ML models so as to find the one that maximizes the prediction accuracy for a specific phenomenon [14][15][16][17]. They use specific ML implementations (packages, methods) and try to estimate the best hyperparameters for their models that produce the most accurate results.…”

Section: Introductionmentioning

confidence: 99%

Comparing Machine Learning Models and Hybrid Geostatistical Methods Using Environmental and Soil Covariates for Soil pH Prediction

Tziachris¹,

Aschonitis²,

Chatzistathis³

et al. 2020

IJGI

View full text Add to dashboard Cite

In the current paper we assess different machine learning (ML) models and hybrid geostatistical methods in the prediction of soil pH using digital elevation model derivates (environmental covariates) and co-located soil parameters (soil covariates). The study was located in the area of Grevena, Greece, where 266 disturbed soil samples were collected from randomly selected locations and analyzed in the laboratory of the Soil and Water Resources Institute. The different models that were assessed were random forests (RF), random forests kriging (RFK), gradient boosting (GB), gradient boosting kriging (GBK), neural networks (NN), and neural networks kriging (NNK) and finally, multiple linear regression (MLR), ordinary kriging (OK), and regression kriging (RK) that although they are not ML models, they were used for comparison reasons. Both the GB and RF models presented the best results in the study, with NN a close second. The introduction of OK to the ML models’ residuals did not have a major impact. Classical geostatistical or hybrid geostatistical methods without ML (OK, MLR, and RK) exhibited worse prediction accuracy compared to the models that included ML. Furthermore, different implementations (methods and packages) of the same ML models were also assessed. Regarding RF and GB, the different implementations that were applied (ranger-ranger, randomForest-rf, xgboost-xgbTree, xgboost-xgbDART) led to similar results, whereas in NN, the differences between the implementations used (nnet-nnet and nnet-avNNet) were more distinct. Finally, ML models tuned through a random search optimization method were compared with the same ML models with their default values. The results showed that the predictions were improved by the optimization process only where the ML algorithms demanded a large number of hyperparameters that needed tuning and there was a significant difference between the default values and the optimized ones, like in the case of GB and NN, but not in RF. In general, the current study concluded that although RF and GB presented approximately the same prediction accuracy, RF had more consistent results, regardless of different packages, different hyperparameter selection methods, or even the inclusion of OK in the ML models’ residuals.

show abstract

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

Cited by 84 publications

References 67 publications

Relating four‐day soil respiration to corn nitrogen fertilizer needs across 49 U.S. Midwest fields

Relating four‐day soil respiration to corn nitrogen fertilizer needs across 49 U.S. Midwest fields

A CNN-RNN Framework for Crop Yield Prediction

Comparing Machine Learning Models and Hybrid Geostatistical Methods Using Environmental and Soil Covariates for Soil pH Prediction

Contact Info

Product

Resources

About