Innovations in Agricultural Forecasting: A Multivariate Regression Study on Global Crop Yield Prediction

TL;DR

This study compares six regression models, including unconventional ones, to predict crop yields across 37 developing countries, achieving high accuracy with the Random Forest model using UN and World Bank data.

Contribution

It introduces a novel comparison of diverse regression models, including unconventional approaches, for global crop yield prediction using comprehensive international datasets.

Findings

Random Forest achieved r2 of 0.94 in yield prediction

Unconventional models outperformed traditional deep learning approaches

Key parameters significantly impact crop yield variations

Abstract

The prediction of crop yields internationally is a crucial objective in agricultural research. Thus, this study implements 6 regression models (Linear, Tree, Gradient Descent, Gradient Boosting, K Nearest Neighbors, and Random Forest) to predict crop yields in 37 developing countries over 27 years. Given 4 key training parameters, insecticides (tonnes), rainfall (mm), temperature (Celsius), and yield (hg/ha), it was found that our Random Forest Regression model achieved a determination coefficient (r2) of 0.94, with a margin of error (ME) of .03. The models were trained and tested using the Food and Agricultural Organization of the United Nations data, along with the World Bank Climate Change Data Catalog. Furthermore, each parameter was analyzed to understand how varying factors could impact overall yield. We used unconventional models, contrary to generally used Deep Learning (DL) and Machine Learning (ML) models, combined with recently collected data to implement a unique approach in our research. Existing scholarship would benefit from understanding the most optimal model for agricultural research, specifically using the United Nations data.