Researchers from the Universitat Politècnica de València (UPV) have developed a mobile application for the early detection of diseases and pests in orange trees. The digital tool enables growers to identify infections before they spread to other trees. It has achieved a diagnostic accuracy rate of 99.58% for common citrus diseases such as melanosis, black spot, canker, and greening.
“With this research, we have aimed to develop an accessible tool for citrus farmers, specifically for oranges, that will allow them to improve their harvests and the productivity of their crops,” said Jaime Lloret, professor in the UPV’s Department of Communications.
The main objective of the tool is to help growers analyze tree health and detect diseases early to reduce economic losses.
© Universitat Politècnica de València
Technical features and operation
The new application offers improvements over previous models. It consumes fewer computational resources, does not require internet access or server connectivity, and can operate directly from a smartphone. Users can upload photos of oranges and leaves directly into the app for analysis.
The software runs on multiple operating systems, including iOS, Android, Windows, Linux, and Raspberry Pi. A second version has been developed for personal computers and Raspberry Pi systems, designed for use in large plantations. This version can automatically send diagnostic results to users by email each day.
Artificial intelligence training
The app’s detection system is based on deep learning, a form of artificial intelligence that uses neural networks to recognize patterns and make predictions. It was trained using a catalog of 5,073 standardized images of citrus leaves and fruit. After an initial training phase, the model was fine-tuned to improve accuracy.
As a result, the model can distinguish oranges from other fruits, determine whether an orange is healthy, and identify any of the eight leaf and fruit diseases or pests for which it has been trained.
Next phase: Integration with robotics
Following these results, the UPV team plans to expand the tool’s applications. “The next phase consists of incorporating the app in robots and intelligent drones that will diagnose various diseases and fruit spots. In addition, we will combine the software with irrigation systems, fertilization, and gas sensor networks, which will allow us to identify other problems in the plantations,” the researchers said.
The research was funded by the Ministry of Science and Innovation of the Government of Spain.
For more information:
Universitat Politècnica de València
Tel: +34 96 387 70 00
Email: [email protected]
www.upv.es
link