Crop Prediction using Supervised Learning

Abstract

Agriculture is a key driver of a nation's economy, supplying raw materials, employment, and essential food. In India, the world's second most populated country, a significant portion of the population depends on agriculture for their livelihood. However, farmers face numerous challenges, including crop diseases, poor soil quality, unpredictable weather, and water scarcity. Additionally, repeated cultivation of the same crops and the indiscriminate use of fertilizers deplete soil nutrients, further reducing crop yields. Modern technology adoption may minimize these issues and improve the quality and production of agriculture. In agriculture, machine learning (ML), a branch of artificial intelligence (AI), makes automation, classification, and prediction easier. It supports well-informed decision-making for food security and effective crop management by assisting in the optimization of crop selection, fertilization, and irrigation. Using the Kaggle crop recommendation dataset, this paper presents a strong machine learning architecture for crop prediction. Important input characteristics including soil pH, temperature, humidity, and nutrient levels are included in the dataset. Using classification techniques like Decision Tree (DT) and Support Vector Machine (SVM), the system identifies the most appropriate crop for a specific type of soil based on its weather and soil data. It also offers information on the amount of fertilizer, seeds, and soil nutrients needed for production. By using this system, farmers can explore new crop varieties, increase agricultural productivity, enhance profit margins, and reduce soil pollution.