Dr. Silvia Aparicio, a researcher associated with the Universidad Internacional Iberoamericana (International Iberoamerican University, UNIB), in collaboration with international experts, has developed a customized deep learning model for the early detection of diseases in cotton crops. This advance promises to significantly improve agricultural productivity and reduce economic losses associated with diseases in these crops.
Cotton is an essential crop in many economies, especially in regions such as South Asia, where it is a major source of income and employment. However, diseases affecting cotton can cause yield losses of up to 80%, negatively impacting the economy and food security.
Traditionally, disease detection in crops has relied on manual inspections by farmers and experts, a process that can be subjective and prone to error. In addition, these inspections require significant time and resources, limiting their effectiveness in preventing large-scale outbreaks.
This study introduces an innovative approach by applying deep learning models for the automatic identification of diseases in cotton. Unlike previous methods, this model uses advanced algorithms that analyze images of crops to detect early signs of disease with high accuracy.
To develop this model, researchers collected a dataset of images of cotton crops affected by various diseases. These images were preprocessed and used to train several deep learning models, including VGG16, DenseNet, EfficientNet, InceptionV3, MobileNet, NasNet, and ResNet. After extensive evaluation, the ResNet152 model proved to be the most effective, achieving superior accuracy in disease detection.
The results of the study are promising. The ResNet152 model not only accurately identified the diseases present in the test images, but also showed a remarkable ability to differentiate between different types of diseases, which is crucial for implementing specific and effective control measures.
The implementation of this deep learning model in agriculture has significant implications. It enables faster and more accurate disease detection, facilitating early interventions that can save crops and reduce economic losses. In addition, by automating the detection process, resources are optimized and crop management efficiency is improved.
If you would like to learn more about this study, click here.
To read more research, check out the UNIB repository.
The International Iberoamerican University (UNIB) offers scholarships for the Master's Degree in Strategic Management in Information Technology. This program provides professionals with the skills and abilities necessary to manage executive positions and lead organizational change projects using ICTs or advise companies that want to become more competitive in new businesses. Join the business development movement by studying our master's program and prepare to take your career to the next level!