1.
Purnima Baagdi
– Assistant Professor, Department of Computer Science, Sardar Vallabhbhai Global University (CPICA), Ahmedabad, Gujarat, India.
2.
Vishal Dahiya
– Director iMCA & Research Supervisor, Sardar Vallabhbhai Global University (CPICA), Ahmedabad, Gujarat, India.
3.
Madhavi Dave
– Project Manager – IoT Security & Research Co-Supervisor, DIASVPCoE, Gujarat University, Ahmedabad, Gujarat, India.
Abstract
Sustainable agriculture is essential for ensuring food security and economic stability in emerging economies, where farmers often face significant challenges due to imbalanced nutrient management and limited access to expert guidance. Nutrient imbalance can severely affect crop health. It is a major constraint to achieving long-term sustainability in agriculture. This approach addresses agricultural “tensions” arising from nutrient imbalances, resource constraints, and increasing food demand. This study proposes how an intelligent supervised learning framework can identify macronutrients like nitrogen (N), phosphorus (P), potassium (K), and the micronutrients (zinc (Zn), iron (Fe), manganese (Mn), copper (Cu), calcium (Ca), and sulphur (S)) deficiencies using soil and environmental factors. Machine Learning algorithms such as Support Vector Machine (SVM), Random Forest (RF), and Artificial Neural Network (ANN) are generally used to classify nutrient imbalances based on measurable soil and environmental factors. The study demonstrates that hybrid supervised machine learning systems can improve nutrient monitoring by increasing prediction accuracy, which will directly improve crop health. Integrating the above-mentioned techniques with agriculture promotes sustainable crop management by enabling early deficiency detection, site-specific fertilisation, and well-organised input use. The proposed framework serves as a foundation for developing adaptive data-driven decision-support systems in sustainable farming.
