A robust hydroponic system for horticulture farming using deep learning, IoT, and mobile application.

Area of Science:

• Agricultural Technology
• Smart Farming Systems
• Hydroponics

Background:

• Limited farmer literacy poses challenges for adopting advanced hydroponic farming techniques in Bangladesh.
• There is a need for user-friendly systems to assist farmers in monitoring and operating smart hydroponic setups.

Purpose of the Study:

• To introduce a robust hydroponic system with automatic guidelines, monitoring, and disease detection.
• To enhance the convenience and reduce stress in the hydroponic cultivation process for farmers.

Main Methods:

• Hardware implementation utilizing WeMos controllers for system operation.
• Disease detection integrated using a Deep Learning model.
• Development of a mobile application for sensor data analysis and automated alerts.

Main Results:

• The system achieved a high disease detection accuracy of 98.5%.
• Approximately 80% of surveyed farmers reported the system as beneficial for cultivation, usability, and monitoring.

Conclusions:

• The proposed system significantly enhances the operational efficiency and sustainability of hydroponic farming.
• The technology shows potential for improved resource management and effective disease prevention strategies in agriculture.