This paper presents a deep learning approach for plant disease recognition using leaf image classification. The proposed method employs deep convolutional neural networks (CNNs) to classify plant diseases based on leaf images. The model was trained on a dataset of 30,880 images, including 13 types of plant diseases and healthy leaves, with additional background images to improve classification accuracy. The model achieved an overall accuracy of 96.3% and a precision range of 91% to 98% for individual classes. The deep CNN was trained using the Caffe framework, with the model fine-tuned to optimize performance. The dataset was created by collecting images from various sources, preprocessing them, and augmenting them to enhance the model's ability to generalize. The model was tested using 10-fold cross-validation and achieved high accuracy in both top-1 and top-5 classification tasks. The results show that the proposed method outperforms existing techniques in plant disease recognition. The study highlights the potential of deep learning in improving the accuracy and efficiency of plant disease detection, which is crucial for sustainable agriculture and climate change mitigation. The developed model can be used as a tool for farmers and agricultural professionals to identify plant diseases and make informed decisions about pest and disease management. Future work includes expanding the dataset and improving the model's accuracy through advanced techniques. The research contributes to the field of plant disease recognition by demonstrating the effectiveness of deep learning in this application.This paper presents a deep learning approach for plant disease recognition using leaf image classification. The proposed method employs deep convolutional neural networks (CNNs) to classify plant diseases based on leaf images. The model was trained on a dataset of 30,880 images, including 13 types of plant diseases and healthy leaves, with additional background images to improve classification accuracy. The model achieved an overall accuracy of 96.3% and a precision range of 91% to 98% for individual classes. The deep CNN was trained using the Caffe framework, with the model fine-tuned to optimize performance. The dataset was created by collecting images from various sources, preprocessing them, and augmenting them to enhance the model's ability to generalize. The model was tested using 10-fold cross-validation and achieved high accuracy in both top-1 and top-5 classification tasks. The results show that the proposed method outperforms existing techniques in plant disease recognition. The study highlights the potential of deep learning in improving the accuracy and efficiency of plant disease detection, which is crucial for sustainable agriculture and climate change mitigation. The developed model can be used as a tool for farmers and agricultural professionals to identify plant diseases and make informed decisions about pest and disease management. Future work includes expanding the dataset and improving the model's accuracy through advanced techniques. The research contributes to the field of plant disease recognition by demonstrating the effectiveness of deep learning in this application.