Comparing Deep Neural Network and Econometric Approaches to Predicting the Impact of Climate Change on Agricultural Yield

22 Pages Posted: 17 Jan 2020

See all articles by Michael P. Keane

Michael P. Keane

University of New South Wales

Timothy Neal

UNSW Australia Business School, School of Economics

Date Written: January 15, 2020

Abstract

Predicting the impact of climate change on crop yield is difficult, in part because the production function mapping weather to yield is high dimensional and nonlinear. We compare three approaches to predicting yields: (i) deep neural networks (DNNs), (ii) traditional panel-data models, and (iii) a new panel-data model that allows for unit and time fixed-effects in both intercepts and slopes in the agricultural production function - made feasible by a new estimator developed by Keane and Neal (2020) called MO-OLS. Using U.S. county-level corn yield data from 1950-2015, we show that both DNNs and MO-OLS models outperform traditional panel data models for predicting yield, both in-sample and in a Monte Carlo cross-validation exercise. However, the MO-OLS model substantially outperforms both DNNs and traditional panel-data models in forecasting yield in a 2006-15 holdout sample. We compare predictions of all these models for climate change impacts on yields from 2016 to 2100.

Keywords: Climate Change, Crop Yield, Panel Data, Machine Learning, Neural Net

Suggested Citation

Keane, Michael P. and Neal, Timothy, Comparing Deep Neural Network and Econometric Approaches to Predicting the Impact of Climate Change on Agricultural Yield (January 15, 2020). UNSW Economics Working Paper 2020-02, Available at SSRN: https://ssrn.com/abstract=3521260 or http://dx.doi.org/10.2139/ssrn.3521260

Michael P. Keane

University of New South Wales ( email )

Sydney, NSW
Australia

Timothy Neal (Contact Author)

UNSW Australia Business School, School of Economics ( email )

High Street
Sydney, NSW 2052
Australia

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
71
Abstract Views
339
rank
394,994
PlumX Metrics