SMART FERTILIZER TYPE RECOMMENDATION ENGINE USING CROP AND SOIL PARAMETER INPUT

Abstract

Agriculture plays a vital role in economic development and food security, where
proper soil nutrient management is essential for achieving high crop productivity and
maintaining soil health. However, many farmers rely on traditional practices for
fertilizer application without considering the actual nutrient requirements of the soil.
This often leads to excessive or inappropriate fertilizer usage, resulting in soil
degradation, increased costs, and reduced crop yield. To address this issue, there is a
need for an intelligent system that can recommend suitable fertilizers based on
scientific analysis of soil and crop conditions.
This project, titled “Smart Fertilizer Type Recommendation Engine Using Crop and
Soil Parameter Input,” proposes a machine learning-based solution to recommend the
most appropriate fertilizer for specific agricultural conditions. The system analyzes
key parameters such as temperature, moisture, rainfall, soil pH, nitrogen, phosphorus,
potassium levels, carbon content, soil type, and crop type to determine the optimal
fertilizer choice.
Data preprocessing techniques, including data cleaning, encoding of categorical
variables, and feature selection, are applied to prepare the dataset for model training.
Various machine learning algorithms such as Decision Tree, Random Forest, and
Logistic Regression are used to build and evaluate the predictive model. These
models learn the relationship between soil conditions, crop requirements, and suitable
fertilizers to provide accurate recommendations