• Mallela Poojitha
• Mrs V Subhasini

Soil fertility assessment is vital for sustainable agriculture, influencing crop yield and resource management. Traditional evaluation methods involving manual sampling and laboratory testing are time-consuming, costly, and spatially limited. To overcome these challenges, this study presents a Gradient Boosting Model (GBM)–based framework for soil fertility prediction using multi-parameter data, including pH, temperature, humidity, soil moisture, and NPK levels. The dataset undergoes normalization and label encoding, with hyperparameter tuning via Grid Search Cross-Validation. The optimized GBM model classifies soil into Infertile, Moderately Fertile, and Highly Fertile categories, achieving high accuracy by capturing non-linear parameter interactions. Experimental results show that the proposed model outperforms traditional threshold-based methods, providing a scalable, data-driven solution for precision agriculture and improved soil management.

SOIL FERTILITY ASSESSMENT USING GRADIENT BOOSTING MODEL BASED ON PH AND NUTRIENT LEVELS

"SOIL FERTILITY ASSESSMENT USING GRADIENT BOOSTING MODEL BASED ON PH AND NUTRIENT LEVELS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 11, page no.a540-a546, November-2025, Available :http://www.jetir.org/papers/JETIR2511063.pdf

"SOIL FERTILITY ASSESSMENT USING GRADIENT BOOSTING MODEL BASED ON PH AND NUTRIENT LEVELS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 11, page no. ppa540-a546, November-2025, Available at : http://www.jetir.org/papers/JETIR2511063.pdf