Artificial Intelligence (AI) is revolutionizing agriculture by enhancing productivity, sustainability, and efficiency in farming practices. This paper explores the application of advanced AI algorithms, including InceptionV3, ResNet50V2, EfficientNetB0, and MobileNet, in addressing critical agricultural challenges such as crop monitoring, disease detection, yield prediction, and resource optimization. These deep learning models leverage convolutional neural networks (CNNs) to process diverse data inputs like satellite imagery, drone-based images, and sensor data for precise decision-making. Notably, MobileNet, known for its lightweight architecture and computational efficiency, excels in real-time prediction and classification tasks, making it ideal for resource-constrained environments like mobile or edge devices used in smart farming. MobileNet is employed to classify crop health, detect pests, and predict yield outcomes with high accuracy, enabling farmers to take proactive measures. By integrating these AI models, agriculture benefits from automated systems that reduce labor costs, optimize water and fertilizer usage, and mitigate environmental impacts. This study highlights the transformative potential of AI-driven solutions in achieving sustainable agriculture and food security, with MobileNet playing a pivotal role in delivering scalable, efficient, and accurate predictions.

Keywords: Artificial Intelligence, Agriculture, Deep Learning, InceptionV3, ResNet50V2, EfficientNetB0, MobileNet, Crop Monitoring, Disease Detection, Yield Prediction, Smart Farming, Convolutional Neural Networks, Precision Agriculture, Sustainability