Weather-Based Crop Recommendation Using Machine Learning Survey |
Author(s): |
| Rohit More , Zeal Polytechnic, Pune; Nisha Taware, Zeal Polytechnic, Pune; Parth Kank, Zeal Polytechnic, Pune; Ganesh Ranjane, Zeal Polytechnic, Pune; Shrushti Waghmare, Zeal Polytechnic, Pune |
Keywords: |
| Crop Recommendation, Machine Learning, Random Forest, Soil Nutrients, Weather, Rainfall Risk, Precision Agriculture |
Abstract |
|
Crop selection depends on soil nutrients, soil pH, temperature, humidity, rainfall, season, and local growing conditions. Machine-learning methods can combine these variables to recommend crops from historical agricultural data. This survey reviews machine-learning approaches used for crop recommendation and related agricultural prediction, including classifier-based systems, soil and weather data integration, and sensor-supported decision tools. Random Forest and boosting methods are promising candidates, but performance on a static dataset does not guarantee reliable results in a different region or season. The paper identifies practical considerations involving regional validation, rainfall variability, interpretability, and input-data quality. It then describes a proposed Weather-Based Crop Recommendation System with rainfall-scenario comparison, understandable soil guidance, and image-quality checks for uploaded land or soil photographs. Photographs are intended for quality screening only and cannot reliably replace measured values for nitrogen, phosphorus, potassium, or pH. The proposed system remains a design for future implementation and has not yet been experimentally validated. |
Other Details |
|
Paper ID: IJSRDV14I90021 Published in: Volume : 14, Issue : 9 Publication Date: 01/12/2026 Page(s): 24-26 |
Article Preview |
|
|
|
|
