Supervisor
Dr. Muhammad Iqbal
Subject
Computer Science
Abstract
This project developed a machine learning solution to predict cereal yield in South America using FAOSTAT agricultural data. The objective was to estimate yield in kg/ha for rice, maize, and wheat based on variables such as country, crop type, year, harvested area, producer price, pesticide use, and nutrient indicators.
The project followed the CRISP-DM methodology, covering business understanding, data understanding, data preparation, modelling, evaluation, and deployment. Several regression models were tested, including Random Forest, Gradient Boosting, AdaBoost, XGBoost, KNN, and SVR.
The models were evaluated using MAE, MSE, RMSE, and R² score. The results showed that tree-based ensemble models performed best, with the tuned XGBoost model selected as the final model. A Streamlit dashboard was also developed as a prototype to demonstrate how users could input agricultural variables and receive a predicted yield value.
The final XGB Balanced Tuned model achieved an R² score of 0.96, MAE of 347.93 kg/ha, and RMSE of 491.07 kg/ha.
Date of Award
2026
Full Publication Date
2026
Access Rights
open access
Document Type
Undergraduate Project
Resource Type
bachelor thesis
Recommended Citation
Oliveira, V., & Ferreira Dumas, K.
(2026) Machine Learning System for Cereal Yield Prediction in South America. CCT College Dublin.
DOI: https://doi.org/10.63227/652.299.146