Modeling yield response to crop management using convolutional neural networks

Abstract Predicting crop yield response to management and environmental variables is a crucial step towards nutrient management optimization. With the increase in the amount of data generated by agricultural machinery, more sophisticated models are necessary to get full advantage of such data. In this work, we propose a Convolutional Neural Network (CNN) to capture relevant spatial structures of different attributes and combine them to model yield response to nutrient and seed rate management. Nine on-farm experiments on corn fields are used to construct a suitable dataset to train and test the CNN model. Four architectures combining input attributes at different stages in the network are evaluated and compared to the most commonly used predictive models. Results show a reduction in the test dataset RMSE up to 68% when compared to multiple linear regression and up to 29% when compared to a random forest. We also demonstrate that higher variability associated with the spatial structure of the data takes the most advantage of this framework.

[1]  S. Carpenter,et al.  NONPOINT POLLUTION OF SURFACE WATERS WITH PHOSPHORUS AND NITROGEN , 1998 .

[2]  John M. Antle,et al.  Next generation agricultural system data, models and knowledge products: Introduction , 2017, Agricultural systems.

[3]  Wojciech Samek,et al.  Methods for interpreting and understanding deep neural networks , 2017, Digit. Signal Process..

[4]  Kenneth A. Sudduth,et al.  Modeling soil electrical conductivity–depth relationships with data from proximal and penetrating ECa sensors , 2013 .

[5]  Yu Sun,et al.  Multi-Input Convolutional Neural Network for Flower Grading , 2017, J. Electr. Comput. Eng..

[6]  Richard E. Plant,et al.  Spatial Data Analysis in Ecology and Agriculture Using R , 2012 .

[7]  Rajeev K Sukumaran,et al.  Prediction of sugar yields during hydrolysis of lignocellulosic biomass using artificial neural network modeling. , 2015, Bioresource technology.

[8]  James A. Taylor,et al.  Spatial Variability of Kiwifruit Quality in Orchards and Its Implications for Sampling and Mapping , 2007 .

[9]  C. Walthall,et al.  Artificial neural networks for corn and soybean yield prediction , 2005 .

[10]  A. Konopka,et al.  FIELD-SCALE VARIABILITY OF SOIL PROPERTIES IN CENTRAL IOWA SOILS , 1994 .

[11]  John P. Fulton,et al.  Integration of high resolution remotely sensed data and machine learning techniques for spatial prediction of soil properties and corn yield , 2018, Comput. Electron. Agric..

[12]  Tarmo Lipping,et al.  Crop yield prediction with deep convolutional neural networks , 2019, Comput. Electron. Agric..

[13]  Jianhua Zhu,et al.  The Spatial Pattern Characteristics of Soil Nutrients at the Field Scale , 2008, CCTA.

[14]  Oskar Marko,et al.  Portfolio optimization for seed selection in diverse weather scenarios , 2017, PloS one.

[15]  Eriola Betiku,et al.  Modeling and optimization of bioethanol production from breadfruit starch hydrolyzate vis-à-vis response surface methodology and artificial neural network , 2015 .

[16]  Lorenzo Torresani,et al.  Learning Spatiotemporal Features with 3D Convolutional Networks , 2014, 2015 IEEE International Conference on Computer Vision (ICCV).

[17]  G. Bollero,et al.  Associations between field characteristics and soybean plant performance using canonical correlation analysis , 2005, Plant and Soil.

[18]  P. Aggarwal.  Uncertainties in crop, soil and weather inputs used in growth models: Implications for simulated outputs and their applications , 1995 .

[19]  D. Rodriguez,et al.  The Origins, Implications, and Consequences of Yield-Based Nitrogen Fertilizer Management , 2019, Agronomy Journal.

[20]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[21]  Joe D. Luck,et al.  The Data‐Intensive Farm Management Project: Changing Agronomic Research Through On‐Farm Precision Experimentation , 2019, Agronomy Journal.