Rice leaf diseases severely affect crop yield and global food security. Traditional detection methods are manual, time-consuming, and require expert knowledge. This study introduces a deep learning approach using Convolutional Neural Networks (CNNs) for accurate rice leaf disease detection and classification. A dataset of healthy and diseased leaf images was preprocessed using normalization, resizing, and augmentation to enhance model performance.The CNN model, built with convolutional layers, max-pooling, ReLU activations, and dense layers, was trained in TensorFlow with GPU support. It achieved 98.5% accuracy on the validation set, demonstrating high precision, recall, and F1-score. Comparisons with traditional classifiers confirmed its superior accuracy and robustness. This method reduces expert dependency and supports scalable, real-time field application. Future work will expand the dataset, develop mobile integration, and extend the approach to other crop diseases. The model contributes to precision agriculture by improving disease management and promoting sustainable production.