Enhanced Hydroponic Farming with Crop Suitability Prediction

Abstract

Hydroponics, a soil-less cultivation technique, offers efficient resource utilization and enhanced crop yields. However, precise water quality control is essential to ensure optimal nutrient absorption and successful crop growth. This research paper presents a comprehensive IoT-based water quality monitoring system specifically designed for hydroponics, incorporating pH, turbidity, and temperature sensors. The system can acquire data from sensors, data processing, and data visualization in real time. The sensor data is seamlessly transmitted from Arduino to ESP8266 and securely stored on the ThingSpeak cloud platform. Utilizing web scraping techniques, the collected data is extracted from ThingSpeak and seamlessly integrated into a user-friendly website. On the website, a machine learning (ML) model, trained on required data, automatically processes the realtime sensor readings and performs crop suitability predictions. The system enables continuous and automated monitoring of key water quality parameters, ensuring optimal conditions for hydroponic crop growth. The deployed ML model demonstrates remarkable performance in predicting water suitability for different crops. The model provides real-time predictions on the website by utilizing the data, empowering hydroponic farmers with data-driven insights to optimize crop selection based on water quality. To evaluate the system’s efficacy, extensive experimentation, and validation have been conducted using hydroponic setups with various crop types.