Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2026
|
| Subjects: | |
| Online Access: | https://doi.org/10.5281/zenodo.19661900 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- Crop yield prediction plays a prime role in modern agriculture to help farmers enhance planning, optimize resource usage, and ensure food security. Traditional crop yield prediction methods include manual observation, historical trends, and expert knowledge, which may be time-consuming and inconsistent, with reduced accuracy for rapidly changing environmental conditions. This work presents a holistic machine-learning-based approach for accurate crop yield prediction based on diverse agricultural datasets. The proposed system integrates key parameters like weather patterns, soil characteristics, satellite imagery, and historical crop performance to construct predictive models capable of capturing both linear and complex nonlinear relationships. Linear Regression, Decision Trees, Random Forests, and Artificial Neural Networks are employed for pattern analysis to produce dependable yield forecasts. The system hence improves the accuracy of prediction using real-time environmental inputs, data-driven algorithms, and precision farming to help farmers make informed decisions about planting, irrigation, and harvest times. This paper discusses the methodology, model selection, technological framework, and possible impacts of machine-learning-based crop yield prediction systems on sustainable agricultural practices and future smart-farming applications.