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{192661,
        author = {Anushka Mali and Akanksha Kadam and Khushbu Narkhede and Prof. Shehnaz Siddique},
        title = {Deep Learning-Based Estimation of Micronutrient Deficiency in Crops},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {9},
        pages = {2911-2915},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=192661},
        abstract = {Plant health is a critical factor in agricultural productivity, and nutrient deficiencies can lead to significant reductions in crop yield and quality. Early detection of such deficiencies is essential for effective crop management and sustainable farming practices. This paper presents an automated deep learning–based approach for detecting nutrient deficiencies in plants through leaf image analysis. The proposed system focuses on economically important crops, namely banana, bottle gourd, cucumber, maize, and rice.
In the proposed methodology, the input leaf image is divided into smaller blocks, each of which is processed using a set of Convolutional Neural Networks (CNNs) trained to detect specific nutrient deficiencies. A winner-take-all strategy is employed to determine the dominant deficiency at the block level, and these outputs are subsequently combined using a Multi-Layer Perceptron (MLP) to generate a final classification for the entire leaf. The system identifies deficiencies of key nutrients such as nitrogen (N), phosphorus (P), potassium (K), magnesium (Mg), iron (Fe), and calcium (Ca) based on visible symptom patterns.
To improve robustness and adaptability across different crops and environmental conditions, transfer learning techniques are incorporated. Experimental results demonstrate that the proposed CNN-based model outperforms traditional Artificial Neural Networks (ANNs) and other deep learning architectures, including DenseNet-121, in terms of classification accuracy. The proposed system provides a fast, accurate, and cost-effective solution for nutrient deficiency detection, reducing reliance on manual inspection and supporting precision fertilizer management for sustainable agriculture.},
        keywords = {Plant Nutrient Deficiency Detection, Leaf Image Analysis, Convolutional Neural Networks, Deep Learning, Transfer Learning, Precision Agriculture, Computer Vision, Sustainable Agriculture},
        month = {February},
        }