Optimized Crop Disease Identification in Bangladesh: A Deep Learning and SVM Hybrid Model for Rice, Potato, and Corn

Area of Science:

• Agricultural Science
• Computer Science
• Machine Learning

Background:

• Crop diseases significantly threaten Bangladesh's agricultural sector and food security.
• Timely and accurate disease identification is crucial for sustainable food production.

Purpose of the Study:

• To develop a hybrid deep learning model for identifying three specific crop diseases in Bangladesh.
• To improve computational efficiency and accuracy in precision agriculture.

Main Methods:

• A hybrid model integrating EfficientNetB0 for feature extraction and Support Vector Machines (SVM) for classification was developed.
• The model was trained and tested on data for late blight in potatoes, brown spot in rice, and common rust in corn.

Main Results:

• The proposed hybrid model achieved a high accuracy of 97.29%.
• Comparative analysis showed superior performance over individual models like CNN, VGG16, ResNet50, Xception, Mobilenet V2, Autoencoders, Inception v3, and EfficientNetB0.

Conclusions:

• The hybrid EfficientNetB0-SVM model demonstrates superior performance for crop disease identification.
• This approach offers a promising solution for enhancing precision agriculture and ensuring food security in Bangladesh.