AIoT based soil nutrient analysis and recommendation system for crops using machine learning

Agriculture is indispensable to the global economy, and its growth is vital to any country's economic success. Menace changing climate, soil erosion, salinity, depletion in carrying capacity of the soil, and other environmental factors have challenged sustainable agriculture vis-a-vis the agronomic response of crops. Predicting the suitability of a crop for specific land is a challenging task as it depends on diverse climate, environmental, and soil factors. We proposed the solution to measure and analyze soil and environmental factors such as pH level, macro nutrients potassium (K), Nitrogen (N), Phosphorus (P) and humidity (h), temperature (t) and average rainfall. We utilized crop recommendation dataset from Kaggle consisting 22 crops. We build a prediction model using machine learning techniques. The models were trained on individual dataset of 20 major crops of Punjab Pakistan, using Decision Tree with AdaBoost, K-Nearest Neighbor (KNN), Decision Tree (DT), Random Forest (RF) and Support Vector Machine (SVM). The developed system compares and evaluates real-time data collected from implanted IoT-based sensors with a training dataset located in a cloud repository. Comparing the five ML models, Decision Tree with AdaBoost demonstrated the highest performance (AC: 98%). The system enables data-driven decision-making for selecting suitable crops for cultivation at specific sites through a user-friendly interface for farmers. Proposed system is non-intrusive for producing crop recommendations under diverse environmental regions and conditions, provides farmers with data-driven and valuable insights. The proposed system enables timely interventions to prevent crop loss, increasing global food security and contribute in sustainable agriculture.