AGRIVISION: SUSTAINABLE FARMING ADVISOR

Abstract

Farming is a key driver of profitable activity, and improving crop selection is critical for improving creativity and sustainability. With progress or development in Artificial Intelligence (AI) and Machine Learning (ML), precision farming or cultivation has appeared as a hopeful solution. This research presents a Sustainable Farming Advisor that uses ML techniques to examine soil properties (such as soil type and pH, etc...), environmental conditions (such as temperature, humidity, season and etc...), and agronomic factors to recommend the worthiest crops for farming. The  model considers key parameters includes Soil pH, Nitrogen (N), Phosphorus (P), Potassium (K) amount, Temperature, Humidity, Rainfall, and Irrigation facilities. Machine learning algorithms, including Decision Trees, Random Forest, Support Vector Machines (SVM), and Neural Networks, are examined for classification and correct prediction to give more accuracy. The system helps farmers in making meaningful decisions to maximize yield, optimize resources, and promote sustainability. To improve productivity, the model merge pH validation, change users when the soil is too acidic or basic and provide the corrective measures, such as adding up lime or organic matter to improve soil pH for better productivity. In addition, the system reports for soil fertility exhaustions, recommend the organic fertilizers, crop rotation, and biofertilizers to maintain long-lasting fertility.. This feature  enables farmers to make correct decisions not only based on conditions but also economic workability. By integrating AI-driven intuitions or awareness, the model fills the gap between scientific recommendations and real-world farming or cultivation practices.