Automated Greenhouse using IoT and CNN

This project aims to develop a comprehensive solution that can monitor the greenhouse environment and detect diseases in tomato plants using a combination of sensors, machine learning, and mobile application technology. The greenhouse monitoring system consisted of sensors such as temperature, humidity, light, and soil moisture sensors, connected to the NodeMCU ESP8266 microcontroller. The CNN model was trained on a dataset of tomato plant images and deployed on the Google Cloud Platform. The mobile application was developed using Flutter and designed to capture images of the tomato plants, send them to the Firebase cloud platform, and receive predictions from the CNN model. The key findings of the project showed that the developed system was able to monitor the greenhouse environment and detect diseases in tomato plants with high accuracy. The CNN model achieved an accuracy of 95% in disease detection, and the mobile application provided a user-friendly interface for remote monitoring. The importance of this domain lies in the need for sustainable and efficient agricultural practices to feed the growing population, and the use of technology in agriculture can improve crop yields, reduce resource usage, and minimize the impact on the environment. This project demonstrates the potential of technology in agriculture and provides a solution to one of the major challenges faced by farmers.