Agri Tech: An AI-Powered Multilingual Farmer Advisory System for Smart Agricultural Decision-Making

Swayamdip Devendra ChaurpagarDepartment of Computer Science and Engineering, Shri Sai College of Engineering & Technology, Bhadrawati, Chandrapur (M.S.), IndiaSomnath Anna KadamDepartment of Computer Science and Engineering, Shri Sai College of Engineering & Technology, Bhadrawati, Chandrapur (M.S.), IndiaHarsh Vinod KolarkarDepartment of Computer Science and Engineering, Shri Sai College of Engineering & Technology, Bhadrawati, Chandrapur (M.S.), IndiaYash Purushottam BokdeDepartment of Computer Science and Engineering, Shri Sai College of Engineering & Technology, Bhadrawati, Chandrapur (M.S.), IndiaSnehal M. ChaudhariAssistant Professor, Department of Computer Science and Engineering, Shri Sai College of Engineering & Technology, Bhadrawati, Chandrapur (M.S.), India

Vol 10 No 5 (2026): Volume 10, Issue 5, May 2026 | Pages: 116-120

International Research Journal of Innovations in Engineering and Technology

OPEN ACCESS | Research Article | Published Date: 09-05-2026

doi Logo doi.org/10.47001/IRJIET/2026.105015

Abstract

Agriculture forms the backbone of India's economy, supporting over 58% of the rural population and contributing approximately 17% to the national GDP. Despite its significance, the agricultural sector remains severely underserved by modern technology, leaving millions of farmers without timely access to critical crop advisory services, weather guidance, market pricing intelligence, or disease diagnostics. Agri Tech is a comprehensive, AI-powered multilingual farmer advisory system designed to bridge this gap by integrating multiple intelligent modules into a single accessible platform. The system leverages advanced Natural Language Processing (NLP), machine learning-based crop recommendation algorithms, satellite and API-sourced weather forecasting, computer vision for plant disease detection, and real-time mandi price retrieval through government agricultural data APIs. Key features include a conversational AI chatbot supporting Hindi, Marathi, and English; a crop recommendation engine utilizing soil parameter analysis with ensemble learning; a weather alert system for proactive agricultural planning; a plant leaf disease detection module using Convolutional Neural Networks (CNN); a government scheme navigator providing personalized scheme recommendations; and a smart marketplace connecting farmers directly with buyers. Experimental evaluations demonstrate strong accuracy across all modules. The crop recommendation model achieves 97.2% accuracy using a Random Forest classifier trained on NPK-soil dataset. The plant disease CNN model achieves 96.8% classification accuracy across 38 disease classes. Agri Tech is deployed as a cross-platform mobile and web application, designed for usage on low-bandwidth rural networks with multilingual voice and text interfaces. This system represents a significant step toward democratizing agricultural intelligence for the 150+ million smallholder farmers of India.

Keywords

Agri Tech, AI Farmer Advisory, Crop Recommendation, Plant Disease Detection, NLP Chatbot, Mandi Price API, Government Schemes, Smart Agriculture, Multilingual Interface, CNN, Random Forest, Precision Farming


Citation of this Article

Swayamdip Devendra Chaurpagar, Somnath Anna Kadam, Harsh Vinod Kolarkar, Yash Purushottam Bokde, & Snehal M. Chaudhari. (2026). Agri Tech: An AI-Powered Multilingual Farmer Advisory System for Smart Agricultural Decision-Making. International Research Journal of Innovations in Engineering and Technology - IRJIET, 10(5), 116-120. Article DOI https://doi.org/10.47001/IRJIET/2026.105015

References
  1. S. P. Mohanty, D. P. Hughes, and M. Salathé, "Using Deep Learning for Image-Based Plant Disease Detection," Frontiers in Plant Science, vol. 7, p. 1419, 2016.
  2. K. P. Ferentinos, "Deep learning models for plant disease detection and diagnosis," Computers and Electronics in Agriculture, vol. 145, pp. 311–318, 2018.
  3. S. Ramesh and D. Vydeki, "Recognition and classification of paddy leaf diseases using Optimized Deep Neural network with Jaya algorithm," Information Processing in Agriculture, vol. 6, no. 2, 2019.
  4. A.Jha, R. Garg, and M. Yadav, "AgriBot: A Multilingual NLP-Based Chatbot for Agricultural Advisory in India," Proceedings of ICTCS 2020, Springer, 2020.
  5. N. Narayanan, "Digital Inclusion and Agricultural Welfare Schemes: A Study of Awareness Gaps," Economic and Political Weekly, vol. 54, no. 32, 2019.
  6. A.Howard et al., "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications," arXiv:1704.04861, 2017.
  7. D. Hughes and M. Salathé, "An open access repository of images on plant health to enable the development of mobile disease diagnostics," arXiv:1511.08060, 2015.
  8. T. Chen and C. Guestrin, "XGBoost: A Scalable Tree Boosting System," ACM KDD, 2016.
  9. L. Breiman, "Random Forests," Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
  10. Government of India, "PM-KISAN: Direct Income Support to Farmers," Ministry of Agriculture and Farmers Welfare, PIB Report, 2022.
  11. ICAR Annual Report 2022-23, Indian Council of Agricultural Research, New Delhi.
  12. National Sample Survey Office (NSSO), "Situation Assessment of Agricultural Households," Ministry of Statistics and Programme Implementation, India, 2019.