| _version_ | 1866902292658126848 |
|---|---|
| author | Saranya R, Nishanth Kumar A, Albert Samuel I |
| author_facet | Saranya R, Nishanth Kumar A, Albert Samuel I |
| contents | <p>Agriculture is a vital sector in the economy of India, providing employment to a large population. However, many farmers<br>face productivity challenges due to improper crop selection that does not align with soil requirements. Precision agriculture<br>addresses this issue by analyzing characteristics of a soil, types of soil, and information of crop yield to recommend the most<br>suitable crops. This approach enhances productivity by reducing the cultivation of non-suitable crops and improving resource<br>efficiency. Additionally, predicting agricultural productivity is essential in forecasting agriculture output using historical data,<br>including temperature, relative humidity, soil pH, rainfall, and cultivated area. A system of recommendations employing an<br>ensemble technique with voting methods, utilizing K-Nearest Neighbor (KNN) and Random Forest (RF), enhances accuracy and<br>efficiency in crop selection. This method ensures data-driven decision-making, optimized resource utilization, and improved<br>agricultural outcomes, contributing to sustainable farming practices. A comparison of both methods indicates the approach's<br>resilience and dependability, with Random Forest outperforming in managing complex, non-linear interactions within the data.<br>The suggested system intends to provide farmers with actionable insights, reduce crop failure risks, and enhance precision<br>agriculture by implementing AI-driven methodologies.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_16750615 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Intelligent Agriculture: Enhancing Crop Choice with Machine Learning and Predictive Analytics Saranya R, Nishanth Kumar A, Albert Samuel I <p>Agriculture is a vital sector in the economy of India, providing employment to a large population. However, many farmers<br>face productivity challenges due to improper crop selection that does not align with soil requirements. Precision agriculture<br>addresses this issue by analyzing characteristics of a soil, types of soil, and information of crop yield to recommend the most<br>suitable crops. This approach enhances productivity by reducing the cultivation of non-suitable crops and improving resource<br>efficiency. Additionally, predicting agricultural productivity is essential in forecasting agriculture output using historical data,<br>including temperature, relative humidity, soil pH, rainfall, and cultivated area. A system of recommendations employing an<br>ensemble technique with voting methods, utilizing K-Nearest Neighbor (KNN) and Random Forest (RF), enhances accuracy and<br>efficiency in crop selection. This method ensures data-driven decision-making, optimized resource utilization, and improved<br>agricultural outcomes, contributing to sustainable farming practices. A comparison of both methods indicates the approach's<br>resilience and dependability, with Random Forest outperforming in managing complex, non-linear interactions within the data.<br>The suggested system intends to provide farmers with actionable insights, reduce crop failure risks, and enhance precision<br>agriculture by implementing AI-driven methodologies.</p> |
| title | Intelligent Agriculture: Enhancing Crop Choice with Machine Learning and Predictive Analytics |
| url | https://doi.org/10.5281/zenodo.16750615 |