Mohan Babu University, Tirupati, AP

Student and Faculty Perspectives on the Development of the System:

This innovative project is led by Phanindrareddy Dhanireddy, a second-year Computer Science Engineering (CSE) student, with dedicated contributions from Y. Deekshitha, R. Sailaja, and B. Varshitha, who are currently in their third year of CSE. The team worked under the guidance and mentorship of Dr. N. Padmaja, who played a key role in shaping the project's research direction and technical execution.

Phanindrareddy Dhanireddy shared, "Our goal was to go beyond basic disease detection. We wanted a system that could also detect pest issues and nutrient deficiencies using advanced AI and hyper-spectral data, offering farmers a proactive tool for managing their crops efficiently."
Y. Deekshitha, one of the third-year contributors, explained, "What makes this system powerful is its ability to pick up early indicators that are invisible to the naked eye. Farmers get alerts before any visible damage appears, which makes a big difference in yield quality."

R. Sailaja added, "Identifying nutrient deficiencies early can save entire crops. Our AI model was trained on diverse conditions to ensure accurate classification between diseases, pests, and deficiencies."

B. Varshitha emphasized the integration effort: "Combining hardware, AI models, and user-friendly applications was a big challenge, but seeing the results and potential impact on farmers makes it worth it."

Dr. N. Padmaja, the faculty mentor, remarked, "This project highlights how student innovation, when properly guided, can lead to impactful solutions. The fusion of hyper-spectral technology with AI in agriculture opens up new possibilities for scalable, real-time crop management."

How the System Works to Predict Pre-Disease Conditions, Pests, and Nutrient Deficiencies:
The system uses drone-mounted hyper-spectral cameras to collect high-resolution spectral data across crop fields. These data are analyzed using AI models trained to detect and distinguish disease presence, pest infestations, and nutrient deficiencies before physical symptoms manifest. The output is processed into actionable insights and delivered to farmers through a mobile or web-based interface.

This early warning system enables farmers to act immediately with targeted solutions, whether it's applying the right nutrients, using pest control measures, or preparing for disease management—all before the problem spreads.

Benefits to Agriculture and Farmers:
Preventive Control: Enables timely intervention before crops suffer major damage.
Multi-Stress Detection: Identifies diseases, pests, and nutrient issues in a single scan.
Reduced Chemical Usage: Promotes sustainability by reducing excessive chemical treatments.
Increased Yield & Quality: Healthier crops lead to better harvests and profits.
Accessible Technology: Bridges the gap between cutting-edge research and practical farming needs.

Conclusion:
The Agriculture Pre-Disease Prediction and Management System Using Drones with Hyper-Spectral Method is a breakthrough solution that showcases how student innovation, guided by expert mentorship, can address real-world agricultural challenges. With Phanindrareddy Dhanireddy from 2nd year CSE leading the charge and strong contributions from Y. Deekshitha, R. Sailaja, and B. Varshitha from 3rd year CSE, this AICTE Lab project combines research, technology, and field applicability.

Mentored by Dr. N. Padmaja, the system's ability to detect diseases, pests, and nutrient deficiencies before they visibly appear marks a major advancement in smart farming. Its recognition by Business World highlights the potential of academic innovation in driving societal impact and revolutionizing traditional agriculture.