A Hybrid CNN Bi-LSTM Framework for Multi-Class Plant Disease Detection and Health Value Estimation

aspg-31-4408-1791686768 20261011024608 American Scientific Publishing Group admin@americaspg.com American Scientific Publishing Group International Journal of Advances in Applied Computational Intelligence IJAACI 2833-5600 2026 8 1 A Hybrid CNN Bi-LSTM Framework for Multi-Class Plant Disease Detection and Health Value Estimation Janani J. Student, Department of Computer Science and Engineering, Syed Ammal Engineering College, Ramanathapuram-623501, India Gautham R. Assistant Professor, Department of Computer Science and Business System, Syed Ammal Engineering College, Ramanathapuram-623501, India Suguna C. Assistant Professor, Department of Computer Science and Business System, Syed Ammal Engineering College, Ramanathapuram-623501, India Ponni K. Assistant Professor, Department of Computer Science Engineering, Syed Ammal Engineering College, Ramanathapuram-623501, India Accurate and early identification of plant diseases is essential for ensuring sustainable agriculture and maximizing crop productivity. This paper presents a hybrid deep learning framework integrating Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) networks for multi-class plant disease detection, classification, and Plant Health Value (PHV) estimation. The proposed framework begins with a comprehensive data preprocessing pipeline involving image resizing, normalization, and augmentation to improve model robustness. The CNN module extracts critical spatial and visual features such as lesion shape, leaf texture, and color intensity, while the BiLSTM model captures temporal and sequential feature correlations to accurately learn disease progression patterns. A Decision Support System (DSS) is incorporated to compute the Plant Health Value (PHV), where PHV ranges from 0% (Healthy) to 100% (Severely Unhealthy), indicating the severity of disease infection. Additionally, the DSS generates actionable recommendations to assist in early intervention and treatment planning. Experimental results on a multi-species plant dataset demonstrate that the proposed CNN–BiLSTM hybrid model significantly improves accuracy, interpretability, and early disease prediction compared to conventional CNN based methods, offering a robust and intelligent framework for automated plant health monitoring. 2026 13 19 4408 https://creativecommons.org/licenses/by/4.0/ 10.54216/IJAACI.080103 https://www.americaspg.com/journal/31/article/4408 https://www.americaspg.com/storage/articles/manuscripts/01M332S9J84W0DEGY0S63V1094.pdf