Innovations in Agricultural Forecasting: A Multivariate Regression Study on Global Crop Yield Prediction
It addresses crop yield forecasting for agricultural research in developing countries, but is incremental as it applies standard regression methods to new data.
This study tackled global crop yield prediction by implementing six regression models on data from 37 developing countries over 27 years, finding that a Random Forest model achieved an r2 of 0.94 with a margin of error of 0.03.
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.