Related Experiment Video
Updated: Jul 30, 2026
11:12
Protocols for Investigating the Host-tissue Distribution, Transmission-mode, and Effect on the Host Fitness of a Densovirus in the Cotton Bollworm
Published on: April 12, 2017
Detection of cotton crops diseases using customized deep learning model
Hafiz Muhammad Faisal1, Muhammad Aqib2, Saif Ur Rehman1
1University Institute of Information Technology (UIIT), PMAS-Arid Agriculture University Rawalpindi, Rawalpindi, 46300, Pakistan.
Scientific Reports
|March 29, 2025
Summary
This study explores deep learning models for detecting cotton diseases, crucial for agricultural economic growth. The ResNet152 model demonstrated superior performance in identifying diseases, offering an efficient solution for crop protection.
Area of Science:
- Agricultural Science
- Computer Science
- Artificial Intelligence
Background:
- The agricultural sector faces significant economic losses due to cotton crop diseases.
- Early and accurate disease detection is vital for mitigating these losses and ensuring economic stability.
- Artificial intelligence (AI) and deep learning (DL) offer promising solutions for advanced agricultural monitoring.
Purpose of the Study:
- To evaluate the effectiveness of various state-of-the-art deep learning models for recognizing cotton plant diseases.
- To identify the most efficient and accurate DL model for practical application in cotton disease detection.
- To contribute to the protection of cotton crops and support economic growth in the agricultural sector.
Main Methods:
- Collection and preprocessing of real-world cotton disease image data.
- Implementation and comparison of multiple deep learning models: VGG16, DenseNet, EfficientNet, InceptionV3, MobileNet, NasNet, and ResNet.
- Experimental analysis to determine the performance of each model in disease recognition.
Main Results:
- The ResNet152 model exhibited the highest performance among all tested deep learning models.
- The study confirmed the potential of deep learning for accurate and efficient cotton disease identification.
- Preprocessing techniques were applied to enhance the input data for the deep learning models.
Conclusions:
- Deep learning, particularly the ResNet152 model, provides a robust and efficient approach for cotton disease recognition.
- Implementing advanced AI technologies can significantly improve crop protection strategies and reduce economic losses in agriculture.
- This research supports the integration of AI in agriculture for sustainable crop management and economic prosperity.
