Predicting Soybean Yield with NDVI Using a Flexible Fourier Transform Model

Abstract We use models incorporating the normalized difference vegetation index (NDVI) derived from remote sensing satellites to improve soybean yield predictions in 10 major producing states in the United States. Unlike traditional methods that assume an ordinary least squares model applies to all observations, we allow for global flexibility in the relationship between NDVI and soybean yield by using the flexible Fourier transform (FFT) model. FFT results confirm that there is a nonlinear response of soybean yield to NDVI over the growing season. Out-of-sample predictions indicate that allowing for global flexibility with the FFT improves the predictions in time-series prediction and forecasting.

[1]  D. Good,et al.  Early Prospects for 2009 Soybean Yields in Illinois, Indiana, and Iowa , 2009 .

[2]  W. Enders,et al.  On the Use of the Flexible Fourier Form in Unit Root Tests, Endogenous Breaks, and Parameter Instability , 2014 .

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

[4]  Dwight R. Sanders,et al.  Evaluation of Selected USDA WAOB and NASS Forecasts and Estimates in Corn and Soybeans , 2014 .

[5]  Claire Marais-Sicre,et al.  Estimation of corn yield using multi-temporal optical and radar satellite data and artificial neural networks , 2017, Int. J. Appl. Earth Obs. Geoinformation.

[6]  L. M. Thompson,et al.  Weather and technology in the production of corn and soybeans , 1963 .

[7]  Shusen Wang,et al.  Crop yield forecasting on the Canadian Prairies using MODIS NDVI data , 2011 .

[8]  Joshua D. Woodard,et al.  Big data and Ag-Analytics , 2016 .

[9]  D. Lobell,et al.  Climate and Management Contributions to Recent Trends in U.S. Agricultural Yields , 2003, Science.

[10]  A. Ronald Gallant,et al.  The Fourier Flexible Form , 1984 .

[11]  Brian McConkey,et al.  Agriculture field characterization using aerial photograph and satellite imagery , 2004, IEEE Geoscience and Remote Sensing Letters.

[12]  J. Monahan.  Enumeration of elementary multi-indices for multivariate Fourier series , 1981 .

[13]  Ramesh P. Singh,et al.  Crop yield estimation model for Iowa using remote sensing and surface parameters , 2006 .

[14]  Douglas K. Bolton,et al.  Forecasting crop yield using remotely sensed vegetation indices and crop phenology metrics , 2013 .

[15]  David M. Johnson.  An assessment of pre- and within-season remotely sensed variables for forecasting corn and soybean yields in the United States , 2014 .

[16]  S. Liang,et al.  Estimating crop yield from multi-temporal satellite data using multivariate regression and neural network techniques , 2007 .

[17]  Climate and Management Contributions to Recent Trends in U.S. Agricultural Yields , 2003 .

[18]  Paul C. Doraiswamy,et al.  Spring Wheat Yield Assessment Using NOAA AVHRR Data , 1995 .

[19]  Daniel Adrian.  A model-based approach to forecasting corn and soybean yields , 2012 .

[20]  Lorenzo Bruzzone,et al.  Spiking Neural Networks for Crop Yield Estimation Based on Spatiotemporal Analysis of Image Time Series , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[21]  Chang Sik Kim,et al.  A new approach to modeling the effects of temperature fluctuations on monthly electricity demand , 2016 .

[22]  G. Timár,et al.  Crop yield estimation by satellite remote sensing , 2004 .

[23]  A. Gallant.  Advances in Econometrics: Identification and consistency in semi-nonparametric regression , 1987 .

[24]  W. Enders,et al.  A Stationarity Test in the Presence of an Unknown Number of Smooth Breaks , 2006 .

[25]  Alex J. Cannon,et al.  Crop yield forecasting on the Canadian Prairies by remotely sensed vegetation indices and machine learning methods , 2016 .

[26]  A. Ronald Gallant,et al.  Qualitative and asymptotic performance of SNP density estimators , 1996 .

[27]  S. Wallander,et al.  Testing for Specification Bias with a Flexible Fourier Transform Model for Crop Yields , 2017 .

[28]  D. Lobell,et al.  Satellite-based assessment of yield variation and its determinants in smallholder African systems , 2017, Proceedings of the National Academy of Sciences.

[29]  W. Enders,et al.  Trend-cycle decomposition allowing for multiple smooth structural changes in the trend of US real GDP , 2015 .

[30]  C. Tucker.  Red and photographic infrared linear combinations for monitoring vegetation , 1979 .

[31]  Matthew C. Hansen,et al.  Corn and Soybean Mapping in the United States Using MODIS Time‐Series Data Sets , 2007 .

[32]  F. Maselli,et al.  Integration of LAC and GAC NDVI data to improve vegetation monitoring in semi-arid environments , 2002 .

[33]  Sakariyawo Olalekan,et al.  Crop Production I , 2011 .