Hybrid Intelligence for Field-Scale Soil Analysis and Crop Advisory Using Embedded Sensors and Machine Learning

This work provides the design and development of a portable soil testing system utilizing artificial intelligence (AI) and machine learning (ML) capabilities for real-time soil analysis and crop suggestion. It uses a series of sensors to measure the essential soil parameters of pH, moisture, temperature, electrical conductivity, and macronutrients-nitrogen (N), phosphorus (P), and potassium (K). These sensor data are processed in a microcontroller-based system and analyzed by applying ML algorithms in order to assess the fertility and categorize the soil. A rule-based system integrated with a Random Forest Regressor provides dynamic, explainable crop recommendation using soil condition, environmental conditions, and past data trends. Users can view real-time sensor data in a web-based visualization, monitor history, and receive AI-driven crop advisory support through a web-based dashboard. This field-friendly device is rugged, low in cost, and oriented towards the requirements of smallholder producers. Field experiments using 500 soil samples also exhibit high conformity to a commercial soil tester, as the respective RMSEs are 2.26 mg/kg for nitrogen, 1.90 mg/kg for phosphorus, 1.97 mg/kg for potassium, and 0.60 for pH. The deployed ML model had an R2 value of 0.978 in test data. These findings validate the system’s accuracy, dependability, and potential to facilitate sustainable, data-based decision-making in precision agriculture.