Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{210761,
        author = {Muppalla Rohit and Anupoju Mohan Chandra and Duggineni Hari Charan and Dr. Metilda Florence S},
        title = {AgriBrain: A Unified Deep Learning and Reinforcement Learning-Based Intelligent System for Autonomous Smart Farming Optimization},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {6},
        pages = {2100-2108},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=210761},
        abstract = {The high rate of development in precise farming has highlighted the necessity of smart systems that can be used to combine various data streams to streamline agricultural operations. The classic smart farming systems tend to be fragmented relying on detached functions like soil checking, irrigation programs, or pest discovery. The proposed study introduces the unified AI-powered intelligent system AgriBrain that is expected to eliminate all these drawbacks by integrating IoT-based sensing with sophisticated machine learning, deep learning, and reinforcement learning methods. The system uses sensor networks based on Arduino to gather real-time data of the environment, such as soil moisture, temperature, and atmospheric conditions, and external data i.e. weather patterns and market trends. A hybrid modelling strategy has been chosen, with convolutional neural networks to do pest and disease detection, supervised learning to do crop recommendation and yield prediction, and reinforcement learning to make adaptive decisions in the area of irrigation and fertilizer planning. The processed information is inputted into a centrally located decision engine, which produces actionable information like what crops to grow, when to irrigate and blueprints of the farm layout. There are experimental analyses that show a better accuracy in decision making, less usage of the resources, and better adaptability than the more conventional rule-based systems. The suggested system would add a scalable and self-sufficient platform that incorporated sensing, forecasting and optimization into one system that will ensure effective and sustainable farming.},
        keywords = {Forest Fire Detection, Satellite Imagery, Deep Learning, Early Warning System, Remote Sensing},
        month = {November},
        }