气候变化领域集成服务门户(CCPortal): Maize yield and nitrate loss prediction with machine learning algorithms

CCPortal

DOI	10.1088/1748-9326/ab5268
	Maize yield and nitrate loss prediction with machine learning algorithms
	Shahhosseini M.; Martinez-Feria R.A.; Hu G.; Archontoulis S.V.
发表日期	2019
ISSN	17489318
卷号	14 期号:12
英文摘要	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. © 2019 The Author(s). Published by IOP Publishing Ltd.
英文关键词	Machine learning; Maize yield; Meta-models; Nitrate loss; Prediction
语种	英语
scopus关键词	Adaptive boosting; Crops; Cultivation; Decision support systems; Decision trees; Errors; Forecasting; Information use; Learning systems; Mean square error; Nitrates; Random forests; Regression analysis; Accurate prediction; Coupling simulation; Decision support tools; Maize yield; Management scenarios; Meta model; Nitrate loss; Relative mean square errors; Machine learning; agricultural management; crop production; crop yield; cropping practice; decision making; decision support system; genotype-environment interaction; machine learning; maize; nitrate; Zea mays
来源期刊	Environmental Research Letters
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/154299
作者单位	Department of Industrial and Manufacturing Systems Engineering, Iowa State University, Ames, IA, United States; Department of Agronomy, Iowa State University, Ames, IA, United States; Department of Earth and Environmental Sciences, Michigan State University, East Lansing, MI, United States
推荐引用方式 GB/T 7714	Shahhosseini M.,Martinez-Feria R.A.,Hu G.,et al. Maize yield and nitrate loss prediction with machine learning algorithms[J],2019,14(12).
APA	Shahhosseini M.,Martinez-Feria R.A.,Hu G.,&Archontoulis S.V..(2019).Maize yield and nitrate loss prediction with machine learning algorithms.Environmental Research Letters,14(12).
MLA	Shahhosseini M.,et al."Maize yield and nitrate loss prediction with machine learning algorithms".Environmental Research Letters 14.12(2019).