• SARANYA.S
• SRIPONBALA.K
• SARANGAM SAI INDU
• SWATHI.A
• J.S.SOWMIYA

Expert guidance is often necessary for farmers to achieve higher yields and minimize fertilizer loss since they typically have limited control over fertilizer use. The impact of rainfall on nutrient loss is also significant, with moderate rainfall at the right time being beneficial for nutrient penetration into the soil and dissolution of dry fertilizers. However, excessive rainfall can result in runoff and increase the risk of losing vital nutrients such as manganese (Mn), phosphorus (P), boron (B), nitrogen (N), and potassium (K) from the soil. To address this issue, we have proposed a nutrient recommendation framework that utilizes a revised version of the random forest algorithm and time-series data to analyze rainfall patterns and crop fertility. The method predicts the optimal nutrient quantity required for different crops and provides customized recommendations to farmers based on local conditions. By adopting this approach, farmers can enhance soil fertility, improve crop growth, and reduce the risk of leaching and runoff.

Random Forest, Crop Yield, Leeching, Nutrient recommendation, Fertilization, Decision making.

"Machine Learning Based Nutrition Recommendation System for Soil Fertilization", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.f172-f177, May-2023, Available :http://www.jetir.org/papers/JETIR2305527.pdf

"Machine Learning Based Nutrition Recommendation System for Soil Fertilization", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. ppf172-f177, May-2023, Available at : http://www.jetir.org/papers/JETIR2305527.pdf