Predicting county level corn yields using deep, long, short-term memory models in the Corn Belt

Date
2018-01-01
Authors
Jiang, Zehui
Major Professor
Advisor
Dermot J. Hayes
Committee Member
Journal Title
Journal ISSN
Volume Title
Publisher
Altmetrics
Authors
Research Projects
Organizational Units
Economics
Organizational Unit
Journal Issue
Series
Department
Economics
Abstract

Having an accurate corn yield prediction is useful because it provides information about production and equilibrium post-harvest futures price prior to harvest. A publicly available corn yield prediction can help address emergent information asymmetry problems and, in doing so, improve price efficiency on futures markets. This paper is the first to predict corn yield using Long Short-Term Memory (LSTM), a special Recurrent Neural Network method. Our prediction is only 0.83 bushel/acre lower than actual corn yields in the Corn Belt, and is more accurate than the pre-harvest prediction from the USDA. And more importantly, our model provides a publicly available source that will contribute to eliminating the information asymmetry problem that arises from private sector crop yield prediction.

Comments
Description
Keywords
Citation
DOI
Source