Author:
Shelke Shivani Shelke,Degadwala Dr. Sheshang Degadwala
Abstract
This research presents an innovative approach for multi-class recognition of soybean leaf diseases using a Convolutional Long Short-Term Memory (Conv-LSTM) model. The model integrates the spatial learning capabilities of convolutional layers with the temporal dependencies of LSTM units, addressing the critical need for accurate disease detection in agriculture, particularly in soybean cultivation where leaf diseases significantly impact crop yield and quality. Through comparative experiments with established deep learning models such as AlexNet, VGG16, and ResNet50, the Conv-LSTM model demonstrates superior performance in terms of accuracy, precision, recall, and F1 score. By effectively capturing both spatial and temporal features in soybean leaf images, the Conv-LSTM model showcases its potential to enhance disease detection accuracy, supporting precision agriculture practices and enabling timely interventions to mitigate crop losses caused by diseases.
Reference15 articles.
1. Shrivastava, A. "Intelligent Deep Learning Technique for Cotton Leaf and Plant Disease Identification." International Journal of Intelligent Systems and Applications in Engineering, vol. 11, pp. 437–447, 2023.
2. Li, X. et al. "Machine Learning Methods for Soybean Leaf Estimation based on RGB Images." Plant Methods, vol. 19, no. 1, pp. 1–16, 2023, doi: 10.1186/s13007-023-01023-z.
3. Fagodiya, R. K., Trivedi, A., and Fagodia, B. L. "Impact of Weather Parameters on Alternaria Leaf Spot of Soybean Incited by Alternaria alternata." Scientific Reports, vol. 12, no. 1, pp. 1–10, 2022, doi: 10.1038/s41598-022-10108-z.
4. Gautam, V. et al. "Leaf Disease Assessment using a Transfer Learning-Based Artificial Intelligence Model." Sustainability (Switzerland), vol. 14, no. 20, 2022, doi: 10.3390/su142013610.
5. Barro, J. P., Neves, D. L., Del Ponte, E. M., and Bradley, C. A. "A Review of Frogeye Leaf Spot Caused by Cercospora sojina." Tropical Plant Pathology, vol. 48, no. 4, pp. 363–374, 2023, doi: 10.1007/s40858-023-00583-8.