<p>In current era, precision agriculture is known for facilitating resource-efficient and sustainable production of food in presence of climatic uncertainty and increasing global demands. The proposed study proposes a novel hybrid framework integrating cloud, edge computing, Artificial Intelligence (AI) and Internet-of-Things (IoT). The uniqueness of the proposed model is towards optimizing the input management and irrigation system in agricultural field by integrating reinforcement learning, Hierarchical Model Predictive Control (H-MPC), and Synthetic Data Augmented Machine Learning (SDAM). The proposed architecture is constructed for boosting performance of predictive intelligence while leveraging edge actuation in real-time. Implemented in Python environment, the proposed model is assessed with both real-world farm dynamics and synthetically enriched dataset. Extensive benchmarking has been performed to note that proposed model offers up to 36% enhancement compared to baseline irrigation strategies. The outcome has recorded approximately 12–13% enhancement over strong cloud-based optimization baselines while it has recorded 55% improved water use efficiency and reduced energy consumption. The study findings thereby establish foundation structure towards autonomous farming 5.0 that characterizes both scalable as well as intelligent deployment in agricultural field with limited resources. The derivation of the reported study outcome is obtained from highly controlled simulation environment that should be interpreted in form of an upper limit towards system performance. However, the study considers validation on real-world via field deployment and hardware-in-the-loop as future work.</p>