Balcony Environmental Monitoring & Plant Recommendation System Using IoT and Machine Learning

In recent years, smart agriculture and home gardening have gained attention due to growing concerns about environmental sustainability, food security, and resource optimization. This paper presents an integrated Smart Gardening System that leverages Internet of Things (IoT) technology and machine learning to offer real-time crop recommendations and environmental condition monitoring. The system utilizes an ESP32 microcontroller connected to DHT11 and soil moisture sensors to capture real-time data on temperature, humidity, and soil wetness. These values are transmitted using the MQTT protocol to a Flask-based web server that processes and stores the information.A machine learning model RandomForestClassifier), trained on a dataset containing twelve sequential readings per sensor, is employed to suggest the top five crops best suited to the current environment. Additionally, the system monitors plant health by comparing real-time readings against predefined optimal thresholds for selected plant species. When deviations are detected, immediate alerts are generated, enabling timely user intervention. The system offers a user-friendly interface for both crop recommendation and monitoring and is deployed on cloud platforms such as Render for accessibility. This work demonstrates the potential of combining IoT and AI to enhance small-scale gardening and urban agriculture practices.