The integration of Internet of Things (IoT) technology with deep learning has revolutionized precision agriculture, particularly within hydroponic systems. This study presents an advanced IoT-enabled crop management framework that utilizes a hybrid deep learning approach, incorporating Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Transformer models. By employing sensors to track critical environmental parameters and processing both image data and time-series information, the system facilitates predictive analytics and automated adjustments to optimize growth conditions. Comparative analysis and ablation studies validate the individual contributions of these components. The paper concludes by outlining potential advancements, such as edge computing, federated learning, and environmentally sustainable AI-driven agricultural practices.