Corn Yield Prediction with Ensemble CNN-DNN
No Thumbnail Available
Date
2021-01-01
Authors
Major Professor
Advisor
Committee Member
Journal Title
Journal ISSN
Volume Title
Publisher
Authors
Person
Shahhosseini, Mohsen
Doctorate Student / Research Assistant
Person
Hu, Guiping
Affiliate Associate Professor
Research Projects
Organizational Units
Organizational Unit
Organizational Unit
Industrial and Manufacturing Systems Engineering
The Department of Industrial and Manufacturing Systems Engineering teaches the design, analysis, and improvement of the systems and processes in manufacturing, consulting, and service industries by application of the principles of engineering. The Department of General Engineering was formed in 1929. In 1956 its name changed to Department of Industrial Engineering. In 1989 its name changed to the Department of Industrial and Manufacturing Systems Engineering.
Journal Issue
Is Version Of
Versions
Series
Department
AgronomyIndustrial and Manufacturing Systems EngineeringSustainable AgricultureBioeconomy Institute (BEI)
Abstract
We investigate the predictive performance of two novel CNN-DNN machine learning ensemble models in predicting county-level corn yields across the US Corn Belt (12 states). The developed data set is a combination of management, environment, and historical corn yields from 1980 to 2019. Two scenarios for ensemble creation are considered: homogenous and heterogenous ensembles. In homogenous ensembles, the base CNN-DNN models are all the same, but they are generated with a bagging procedure to ensure they exhibit a certain level of diversity. Heterogenous ensembles are created from different base CNN-DNN models which share the same architecture but have different hyperparameters. Three types of ensemble creation methods were used to create several ensembles for either of the scenarios: Basic Ensemble Method (BEM), Generalized Ensemble Method (GEM), and stacked generalized ensembles. Results indicated that both designed ensemble types (heterogenous and homogenous) outperform the ensembles created from five individual ML models (linear regression, LASSO, random forest, XGBoost, and LightGBM). Furthermore, by introducing improvements over the heterogenous ensembles, the homogenous ensembles provide the most accurate yield predictions across US Corn Belt states. This model could make 2019 yield predictions with a root mean square error of 866 kg/ha, equivalent to 8.5% relative root mean square and could successfully explain about 77% of the spatio-temporal variation in the corn grain yields. The significant predictive power of this model can be leveraged for designing a reliable tool for corn yield prediction which will in turn assist agronomic decision makers.
Comments
This article is published as Shahhosseini, Mohsen, Guiping Hu, Saeed Khaki, and Sotirios V. Archontoulis. "Corn Yield Prediction With Ensemble CNN-DNN." Frontiers in Plant Science 12 (2021): 709008.
DOI: 10.3389/fpls.2021.709008.
Copyright 2021 Shahhosseini, Hu, Khaki and Archontoulis.
Attribution 4.0 International (CC BY 4.0).
Posted with permission.