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{204939,
        author = {Dr. Ganesh Gorakhnath Taware and Ms. Shital Avinash Jedhe},
        title = {Deep Learning-Based Earthworm Health Monitoring and Vermicompost Quality Recognition for Smart Organic Farming},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {4717-4731},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204939},
        abstract = {The vermicomposting process is environmentally friendly and sustainable as it involves transforming organic waste into fertilizer rich in nutrients through the biological processes of earthworms. The health status of the earthworms and the quality of the vermicompost are two very essential parameters that affect the effectiveness and sustainability of the vermicomposting process. The traditional methods used to evaluate vermicompost quality and earthworm health involve laboratory testing and visual inspection, which are time-consuming, subjective, and often unsuitable for large volumes of vermicompost. This paper proposes an automatic system for vermicompost quality assessment and earthworm health monitoring using deep learning algorithms. To boost dataset diversity and improve generalization, additional techniques, such as rotation, flipping, zooming, and brightness adjustment, were used alongside image cropping and scaling for augmentation. Three deep learning approaches, such as CNN, CNN-SVM, and ABCNN, were applied and evaluated in the research. Indicators such as accuracy, precision, recall, and F1-score were among the most common performance metrics. Based on the experimental results, the proposed attention-based approach was more effective at learning discriminative visual features of earthworm morphology and vermicompost properties than other approaches. The proposed architecture will facilitate sustainable organic farming by enabling intelligent monitoring of vermicomposting.},
        keywords = {Vermicomposting, Earthworm Health Monitoring, Vermicompost Quality Assessment, Deep Learning, Transfer Learning, Convolutional Neural Network (CNN), CNN-SVM, Attention-Based CNN, Image Classification, Smart Agriculture, and Computer Vision.},
        month = {June},
        }