OKONKWO, MICHAEL IFECHUWKU (2025) CROP YIELD PREDICTION SYSTEM USING MACHINE LEARNING A PROJECT SUBMITTED IN PARTIAL FUFILMENT OF THE REQUIREMENTS FOR THE AWARD OF BACHELOR OF SCIENCES (BSc) DEGREE OF COMPUTER SCIENCE. Other thesis, GODFREY OKOYE UNIVERSITY, ENUGU.
![[img]](https://eprints.gouni.edu.ng/style/images/fileicons/text.png) |
Text
REPO168.docx Download (5MB) |
Abstract
Agriculture is the backbone of Nigeria's economy, yet farmers face significant challenges in predicting crop yields due to unpredictable weather, soil variability, and limited access to advanced tools. This study addresses these challenges by developing a Crop Yield Prediction System using machine learning. The system leverages historical and real-time data, including soil nutrients (N, P, K), pH levels, temperature, rainfall, and crop type, to forecast yields accurately. The system employs regression models such as Linear Regression, Decision Tree, and Random Forest, with the latter demonstrating the highest accuracy (R² = 0.953). Real-time weather data is integrated via the OpenWeatherAPI, and the system is deployed as a user-friendly web application using Flask and Bootstrap. Key features include user authentication, personalized dashboards, and graphical visualization of historical predictions. The system was evaluated using Nigerian agricultural data, demonstrating its potential to enhance decision-making for farmers, policymakers, and agricultural officers. By improving yield predictability and resource optimization, this research contributes to sustainable farming practices and food security in Nigeria.
| Item Type: | Thesis (Other) |
|---|---|
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Faculty of Natural and Applied Sciences |
| Depositing User: | Uchenna Eneogwe |
| Date Deposited: | 03 Jul 2026 13:32 |
| Last Modified: | 03 Jul 2026 13:32 |
| URI: | http://eprints.gouni.edu.ng/id/eprint/5876 |
Actions (login required)
 |
View Item |
