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{204422,
        author = {NAMITHA A R and Shridhar V and Ranjith Kumar BG and Abhishek BR},
        title = {NEXT GENERATION PLANT MANAGEMENT AND DISEASE DETECTION USIND ADVANCE DEEP LEARNING},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {3479-3486},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204422},
        abstract = {Pathogens of plants always major culprits for agricultural productivity losses at a misguided food system, food systems that are already at risk in many regions due to the scarcity of necessary timely intervention by experts. A Next, Generation Plant Management System is thus proposed through this paper to add a hybrid deep learning and context, aware advisory integration for accurate disease detection and smart remedy generation. Specifically, a Hybrid Mobile Vision Transformer (MobileViT) model with lightweight architecture that stacks convolutional neural networks for local features extraction and uses transformers for global context modelling have been utilized to solve multi, class classification of plant diseases. The model has been trained on the Plant Village dataset containing 38 classes of diseases and has produced 96.3% classification accuracy alongside high precision and recall values. In order not to leave the patients unattended after diagnosis, an attention equipped Sequence, to, Sequence (Seq2Seq) LSTM model has been used for generating structured, step, by, step treatment instructions, which complies with a BLEU scoring of 0.72 and factual accuracy of 94%. Besides biotic, plant growth is highly influenced by abiotic factors. Therefore, a Smart Plant Manager can serve as a helpful aid underpinned by weather and geolocation real, time data to help growers with the formulation of context, aware preventive alerts and cultivation strategies. The entire solution is housed in a Flask web server delivering 2 to 3 seconds per image output. The empirical findings reported an incredible prowess, scalability, and the effectiveness of the proposed AI, driven agricultural decision, support system that is designed to be practically usable.},
        keywords = {Plant Disease Detection, MobileViT, Vision Transformer, Seq2Seq LSTM, Deep Learning, Precision Agriculture, Smart Farming, Computer Vision, Agricultural Decision Support System.},
        month = {June},
        }