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{206492,
        author = {Manish Shriwas and Dr. Khushi Sindhi},
        title = {AI-Driven Smart Farming for Precision Agriculture: An Edge-IoT and Deep Learning Framework for Sustainable Crop Management},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {2},
        pages = {1815-1818},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206492},
        abstract = {Modern agriculture faces severe challenges due to climate volatility, resource depletion, and skyrocketing global food demands. Traditional agricultural practices fail to optimize resources, leading to water wastage, over-fertilization, and delayed disease identification. To solve these critical problems, this paper introduces a novel, end-to-end AI-driven smart farming framework designed specifically for precision agriculture. The proposed architecture integrates an Edge-Internet of Things (IoT) deployment with advanced Non-Orthogonal Multiple Access (NOMA) communication channels to ensure high-throughput, low-latency data streaming from heterogeneous sensors. At the core of our cloud layer, a deep learning hybrid model comprising a Convolutional Neural Network coupled with Long Short-Term Memory and an integrated Self-Attention Mechanism (CNN-LSTM-Attn) is deployed for joint soil parameter estimation, disease classification, and crop yield forecasting. Experimental validations demonstrate that our framework outperforms conventional models, achieving a crop health prediction accuracy of 98.4%, an F1-score of 97.9%, and a significant 58% reduction in network response time compared to baseline IoT configurations. Furthermore, the embedded NOMA power allocation strategy yields a 45% improvement in network lifetime and energy efficiency, establishing this approach as a highly scalable solution for large-scale sustainable smart farming infrastructure.},
        keywords = {Precision Agriculture, Deep Learning, Internet of Things (IoT), NOMA, Edge Computing, Smart Irrigation, CNN-LSTM.},
        month = {July},
        }