Sustainable precision agriculture: an autonomous approach to soil sensing and sapling tree management

Abstract

In modern urban forestry and precision agriculture, the successful adaptation of seedlings and saplings to evolving soil and microenvironmental conditions is crucial for their survival and growth. This research investigation introduces an autonomous agricultural robot that uses artificial intelligence (AI) and machine learning (ML) techniques to monitor soil quality and identify plant illnesses, with the goal of improving crop management and sustainable practices. The suggested system collects and processes real-time data on essential soil factors such as pH, conductivity, humidity, temperature, and nutrient levels. A normalization-based methodology is used to calculate a soil damage level (SDL), allowing for an accurate assessment of soil health by comparing real-time data against predefined reference values for crops such as rose, guava, and tomato. The system’s AI-based plant disease detection module, leveraging the YOLOv11 deep learning model, effectively classifies plant leaves into categories—healthy, scab, rust, and multiple disease— and generates corresponding health scores. The results of the study illustrate the system’s capacity to identify soil deficiencies and diagnose plant diseases with high accuracy, allowing for early intervention and precision treatment techniques. Our Objective is to optimize plant growth environments by addressing nutrient deficiencies and improving planting practices through the integration of AI-driven automation. This research contributes to the advancement of precision agriculture by providing a robust, autonomous system capable of delivering actionable insights for soil and crop management, ensuring enhanced productivity and sustainability. The ultimate goal is to optimize the growth environment by identifying and rectifying soil deficiencies and analyzing Soil Damage Level while generating a health score for the plants, ensuring the quality of saplings through precise planting methods.