CarePlantify: Agentic AI for Smart Crop Advisory Using CNN and Gemini Vision

Main Article Content

Pankaj Vaishnav

Abstract

— A majority of small and marginal farmers in India continue to rely on traditional knowledge and local intermediaries for critical decisions related to crop selection, pest management, and fertiliser use. These practices frequently lead to reduced crop yields, excessive input costs, and environmental degradation. This paper presents a Smart Crop Advisory System that integrates Agentic AI and Generative AI (GenAI) with Convolutional Neural Networks (CNN) and Gemini Vision for plant disease detection, soil-test-based fertiliser recommendation, and multilingual conversational support.


The core novelty lies in an agentic decision pipeline where an uploaded leaf image is processed in parallel by a fine-tuned CNN model for high-accuracy classification and Gemini Vision for contextual visual reasoning. The AI agent fuses these outputs to deliver a grounded crop health advisory that balances quantitative precision with qualitative explainability. The system further addresses specific regional needs by providing real-time, location-specific, and voice-enabled advisory in languages including Hindi, Rajasthani, and Punjabi, Experimental evaluation demonstrates that the CNN model achieves a classification accuracy of 98.3% on plant diseases, while the fertiliser recommendation engine attains an accuracy of 94.7% against laboratory-validated prescriptions. The agentic architecture enables autonomous multi-step task execution with a 95.5% success rate and an average response time of 4.1 seconds, significantly reducing farmer decision-making latency.

Article Details

Section

Articles

Author Biography

Pankaj Vaishnav

Department of Computer Science and Engineering

Geetanjali Institute of Technical Studies (GITS) Dabok, Udaipur, India

References

[1] NABARD, “All India Rural Financial Inclusion Survey 2021–22,” Na- tional Bank for Agriculture and Rural Development, Mumbai, India, 2022.

[2] R. Bhavana and S. Kumar, “Impact of ICT-based crop advisory services on yield improvement among smallholder farmers in India,” Journal of Agricultural Extension, vol. 24, no. 3, pp. 112–121, 2021.

[3] L. G. Goswami, C. Kavadia, R. Sharma, L. Khandelwal and M. Sagotia, “Potato plant disease detection using CNN,” in Proc. 3rd Int. Conf. on Multi-Disciplinary Application and Research Technologies (ICMART- 2024), GITS, Udaipur, India, May 2024, pp. 252–260.

[4] S. B. Jadhav et al., “Utilizing CNN transfer learning for soybean disease classification: A comparative study,” Journal of Agricultural Informatics, vol. 9, no. 1, pp. 17–26, 2018.

[5] J. Liu et al., “Deep learning approaches for plant disease and pest detection: A comprehensive review,” Plant Disease Detection Journal, vol. 15, no. 2, pp. 45–56, 2019.

[6] D. Zhang et al., “DENS-INCEP: A deep transfer learning approach for rice disease detection,” International Journal of Agricultural Engineer- ing and Technology, vol. 13, no. 4, pp. 112–124, 2020.

[7] Ajay Maru, Ajay Kumar Sharma, Mayank Patel, “Hybrid Machine Learning Classification Technique for Improve Accuracy of Heart”, Proceedings of the Sixth International Conference on Inventive Computation Technologies [ICICT 2021], 2021, IEEE Xplore Part Number: CFP21F70-ART; ISBN: 978-1-7281-8501-9, pp. 1107-1110

[8] P. Bedi et al., “Plant disease detection using hybrid CNN-CAE model,”

Computers in Biology and Medicine, vol. 139, 2021.

[9] A. N. Rathod et al., “Exploring methods for leaf disease recognition: An image processing perspective,” Journal of Agricultural Technology, vol. 7, no. 3, pp. 88–97, 2017.

[10] N. Rashmi et al., “Machine learning methods for plant disease identifica- tion: A comprehensive analysis,” International Journal of Plant Science and Agricultural Technology, vol. 5, no. 2, pp. 32–41, 2021.

[11] Sharma, A., M. Patel, and M. Tiwari. "A comparative study to detect fraud financial statement using data mining and machine learning algorithms." International Research Journal of Engineering and Technology (IRJET) 6.8 (2019): 1492-1495.

[12] S. Kumar et al., “A comprehensive survey of plant leaf diseases classi- fication utilising image processing techniques,” International Journal of Computer Applications, vol. 122, no. 4, pp. 11–16, 2015.

[13] V. Prashanthi et al., “Plant disease detection using image processing techniques to minimise harvest losses,” International Journal of Inno- vative Technology and Exploring Engineering, vol. 9, no. 5, pp. 1401– 1407, 2020.

[14] S. Yao et al., “ReAct: Synergizing reasoning and acting in language models,” in Proc. ICLR, 2023.

[15] Patel, M., Aggarwal, A. & Kumar, A. Investigation of Cracking Susceptibility and Porosity Formation and Its Mitigation Techniques in Laser Powder Bed Fusion of Al 7075 Alloy. Met. Mater. Int. 29, 2358–2373 (2023). https://doi.org/10.1007/s12540-023-01387-w

[16] Google DeepMind, “Gemini: A family of highly capable multimodal models,” Technical Report, 2023.

[17] ICAR, “Soil Health Management: Soil Testing and Fertiliser Recom- mendation Guidelines,” Indian Council of Agricultural Research, New Delhi, 2020.