In the heart of Egypt, researchers have developed a cutting-edge solution that could revolutionize small-scale farming, a sector that contributes over a third of the world’s food supply. The innovation, published in *AgriEngineering*, combines artificial intelligence and the Internet of Things (IoT) to create a smart farming system that detects plant diseases and manages farm environments with remarkable precision.
At the core of this system is the MobileViT model, a lightweight deep learning algorithm that integrates vision transformer and convolutional modules. This hybrid approach allows the model to capture both global and local image features, making it highly effective in identifying plant diseases. The model was trained and tested on the Plant Village dataset, which includes 14 plant species and 38 classes of diseases. The results were impressive, with a test accuracy of 99.5% and per-class precision, recall, and f1-score ranging between 0.92 and 1.00. This performance outperformed several standard deep convolutional networks, including MobileNet, ResNet, and Inception, by 2–12%.
The system also includes an LLM-powered interactive chatbot that provides farmers with instant plant care suggestions. This feature is particularly beneficial for small-scale farmers who may not have access to agricultural experts. “This chatbot is like having a plant doctor in your pocket,” said the lead author, Mohamed Bahaa, from the Department of Electronics & Communication at Misr International University. “It can provide immediate advice based on the images and data collected, helping farmers to take timely action.”
For plant environment management, the system uses the ESP32 microcontroller, a powerful and cost-effective device that collects sensor data, controls actuators, and maintains connectivity with Google Firebase Cloud. This allows farmers to monitor and control their farm environments remotely, promoting efficient resource management and sustainable farming practices.
The system’s capabilities are integrated into a mobile application, providing users with a reliable platform for smart plant disease detection and environment management. Each system component was tested individually before being incorporated into the mobile application and tested in real-world scenarios. The results were promising, with the system proving to be a valuable tool for enhancing crop productivity and promoting sustainable farming practices.
The commercial impacts of this research are significant. Small-scale farms often face challenges such as limited access to technology, expertise, and resources. This AIoT-based solution addresses these challenges by providing a cost-effective, user-friendly, and highly accurate tool for plant disease detection and environment management. By enhancing crop productivity and promoting sustainable farming practices, this system has the potential to improve food security and farmers’ livelihoods.
This research could shape future developments in the field by demonstrating the potential of AIoT-based solutions in agriculture. As Mohamed Bahaa noted, “This is just the beginning. We believe that AIoT has immense potential in agriculture, and we hope that our work will inspire more research and development in this area.” With further development and adoption, AIoT-based solutions could become a standard tool in the agricultural sector, helping to address the challenges of food security and sustainable farming in the 21st century.