Empowering coffee farming using counterfactual recommendation based RNN driven IoT integrated soil quality command...

Area of Science:

• Agricultural Science
• Environmental Science
• Computer Science

Background:

• Traditional soil monitoring is labor-intensive and prone to errors, hindering optimal coffee cultivation.
• Maintaining healthy soil is critical for coffee plant growth, quality, and yield.
• There is a need for advanced systems to monitor and manage soil fertility effectively.

Purpose of the Study:

• To develop and evaluate an AI-based IoT system for real-time soil health monitoring in coffee plantations.
• To enhance soil fertility management for increased crop yield and quality.
• To promote sustainable agricultural practices by optimizing resource utilization.

Main Methods:

• Utilized Internet of Things (IoT) sensors to collect real-time soil data (temperature, moisture, pH, nutrients) and weather parameters.
• Implemented a Recurrent Neural Network (RNN) and Gated Recurrent Unit (GRU) model for data analysis and prediction of soil conditions and crop hazards.
• Developed a wireless cloud platform for data transmission and a mobile application for farmer accessibility.

Main Results:

• The RNN-IoT approach demonstrated enhanced accuracy and efficiency compared to traditional soil monitoring methods.
• The system effectively predicted soil conditions and potential crop hazards.
• Optimized irrigation and fertilization strategies were recommended, leading to reduced water and fertilizer usage.

Conclusions:

• The proposed RNN-IoT methodology significantly improves soil health monitoring and management in coffee cultivation.
• This AI-driven system supports sustainable agriculture by minimizing environmental impact and maximizing resource efficiency.
• Enhanced data accessibility and AI-driven recommendations empower farmers for better decision-making and crop management.