An Artificial Intelligence Approach to Prediction of Corn Yields under Extreme Weather Conditions Using Satellite and Meteorological Data

Nari Kim,Kyung-Ja Ha,Yang-Won Lee,Morang Huh,Jaeil Cho,Sang-Il Na,Chan-Won Park,Jaiho Oh

doi:10.3390/app10113785

Abstract

This paper describes the development of an optimized corn yield prediction model under extreme weather conditions for the Midwestern United States (US). We tested six different artificial intelligence (AI) models using satellite images and meteorological data for the dominant growth period. To examine the effects of extreme weather events, we defined the drought and heatwave by considering the characteristics of corn growth and selected the cases for sensitivity tests from a historical database. In particular, we conducted an optimization for the hyperparameters of the deep neural network (DNN) model to ensure the best configuration for accuracy improvement. The result for drought cases showed that our DNN model was approximately 51–98% more accurate than the other five AI models in terms of root mean square error (RMSE). For the heatwave cases, our DNN model showed approximately 30–77% better accuracy in terms of RMSE. The correlation coefficient was 0.954 for drought cases and 0.887–0.914 for heatwave cases. Moreover, the accuracy of our DNN model was very stable, despite the increases in the duration of the heatwave. It indicates that the optimized DNN model can provide robust predictions for corn yield under conditions of extreme weather and can be extended to other prediction models for various crops in future work.

Highlights

Since the 18th century, greenhouse gas emissions have been increasing as a result of industrialization and other human activity, leading to global warming and climate change
The multivariate adaptive regression spline (MARS), Support vector machine (SVM), Random forest (RF), extremely randomized tree (ERT), and training, the data set of was used for validation
0.954 in the blind tests, which indicates the suitability of our approach for crop yield prediction under extreme weather conditions

Summary

Introduction

Since the 18th century, greenhouse gas emissions have been increasing as a result of industrialization and other human activity, leading to global warming and climate change. According to the Intergovernmental Panel on Climate Change (IPCC) Fifth Assessment Report (AR5), global average temperatures would rise by approximately 3.7 ◦ C around the end of the 21st century because of global warming. The frequency of high temperatures will increase further [1]. Global climate change causes a variety of extreme weather conditions, such as drought, heat and cold waves, and heavy rain, which have broad impacts on ecosystems and human society. Extreme weather phenomena have become increasingly frequent; it is difficult to predict due.

Methods

Results

Conclusion