AI-Based Farmer Query Support and Advisory System

Abstract

Agriculture plays a vital role in the economic development of India; however, farmers continue to face several challenges such as limited access to expert agricultural guidance, crop diseases, pest infestations, and unpredictable weather conditions. Many farmers rely on traditional practices or delayed advisory services, which often results in low productivity and financial losses. To overcome these challenges, this project proposes an AI-Based Farmer Query Support and Advisory System, called Kisan Mitra, which provides intelligent, real-time agricultural assistance using modern artificial intelligence techniques. The proposed system allows farmers to submit their crop-related queries through a mobile application using text input, voice input, or crop images. The system utilizes Natural Language Processing (NLP) to understand farmers’ questions and Machine Learning (ML) models to generate accurate and relevant advisory responses. For crop disease diagnosis, image-based analysis is performed using Convolutional Neural Networks (CNNs) to identify diseases and recommend appropriate treatments. Additionally, the system integrates weather forecasting services to provide location-based alerts and climate-aware farming recommendations. The application is developed using Flutter for the frontend and Python with FastAPI for the backend, ensuring a user-friendly interface and efficient system performance. A database is maintained to store farmer profiles, crop details, and query history. The system also supports multilingual interaction, making it accessible to farmers from different regions. By offering timely, accurate, and cost-effective agricultural guidance, the AI-Based Farmer Query Support and Advisory System reduces dependency on traditional advisory services, improves decision-making, and promotes sustainable farming practices.

Introduction

Agriculture plays a vital role in the Indian economy, serving as the primary livelihood for a large population. However, farmers face major challenges such as crop diseases, pest infestations, climate variability, lack of timely expert advice, and limited awareness of modern farming practices. Traditional agricultural extension services often fail due to delays, geographical barriers, and shortage of experts, leading to reduced productivity and economic losses.

To address these challenges, the project proposes an AI-Based Farmer Query Support and Advisory System, named Kisan Mitra, designed to provide intelligent, real-time, and personalized agricultural guidance through a user-friendly digital platform.

Problem Statement

Farmers often lack access to timely, accurate, and context-aware advisory services. Existing systems provide generic information, suffer from language barriers, delayed responses, and limited scalability. There is a need for a multilingual, intelligent, and real-time advisory system capable of understanding natural language queries and delivering personalized recommendations.

Proposed Solution

The proposed system leverages:

• Artificial Intelligence (AI)

• Machine Learning (ML)

• Natural Language Processing (NLP)

• Convolutional Neural Networks (CNNs)

• Weather API Integration

• IoT Sensor Data

Key Functionalities

1. AI-Powered Query Response

   • Farmers submit queries via text, voice, or images.

   • NLP models interpret queries and classify them into domains (crop disease, irrigation, fertilizers, pest control, market queries).

   • Personalized responses are generated using a structured agricultural knowledge base.

2. Image-Based Crop Disease Detection

   • CNN models analyze plant images.

   • Detects diseases using convolution operations and Softmax classification.

   • Suggests appropriate treatments.

3. Weather-Based Advisory

   • Integrates real-time weather data (temperature, rainfall, humidity).

   • Provides climate-aware recommendations and alerts.

4. Sensor-Integrated Monitoring

   • IoT sensors (e.g., soil moisture, temperature) collect field data.

   • Data visualized through a dashboard.

   • Generates threshold-based alerts for irrigation and crop safety.

5. Responsive Web & Mobile Interface

   • Built using technologies like ReactJS and Node.js/Flask.

   • Multilingual and voice-enabled features.

   • Designed for scalability and accessibility.

Literature Review Insights

Previous research includes:

• Rule-based expert systems (limited adaptability)

• ML models for crop yield prediction (Decision Trees, SVM, Random Forest)

• CNN-based plant disease detection (high accuracy but image-dependent)

• NLP-based agricultural chatbots (often lack contextual awareness)

However, existing systems typically focus on isolated tasks rather than providing an integrated, intelligent advisory platform. The proposed system bridges this gap by combining query understanding, disease detection, and environmental analytics into one unified framework.

Methodology

The system follows six major stages:

1. Data Collection

   • Agricultural datasets, expert advisories, soil data, weather records.

2. Preprocessing

   • Tokenization, stop-word removal, lemmatization.

   • TF-IDF feature extraction.

   • Word embeddings and multilingual processing.

3. Query Classification

   • Supervised ML models classify queries into advisory categories:

     C=f(Q)C = f(Q)C=f(Q)

4. Advisory Engine

   • Hybrid ML + rule-based inference.

   • Cosine similarity for response matching:

     Similarity=A⋅B??A?? ??B??Similarity = \frac{A \cdot B}{||A|| \, ||B||}Similarity=??A????B??A⋅B?

5. Image Processing

   • CNN-based feature extraction:

     S(i,j)=∑I(i+m,j+n)K(m,n)S(i,j) = \sum I(i+m, j+n)K(m,n)S(i,j)=∑I(i+m,j+n)K(m,n)

   • Disease probability via Softmax function.

6. Integration

   • Combines Query (Q), Disease (D), and Weather (W):

     R=f(Q,D,W)R = f(Q, D, W)R=f(Q,D,W)

7. Evaluation

   • Accuracy, precision, recall, response relevance.

   • Field testing with real farmer queries.

Results and Discussion

The system demonstrated:

• High classification accuracy for common agricultural queries.

• Effective crop disease detection under controlled image conditions.

• Improved advisory relevance through weather integration.

• Reduced response time compared to traditional methods.

• User-friendly and accessible interface.

However, performance depends on:

• Internet connectivity

• Quality of datasets

• Image clarity (lighting and background affect CNN performance)

Conclusion

This project successfully presents the design and implementation of an AI-Based Farmer Query Support and Advisory System, aimed at addressing the critical challenges faced by farmers due to limited access to timely and accurate agricultural guidance. By integrating Artificial Intelligence, Machine Learning, Natural Language Processing, and image processing techniques, the system provides an intelligent and user-friendly platform for delivering real-time agricultural advice. The developed system effectively interprets farmer queries, identifies crop diseases through image-based analysis, and generates personalized recommendations by considering environmental and weather-related factors. The use of NLP techniques enables natural interaction between farmers and the system, while the application of Convolutional Neural Networks enhances the accuracy of crop disease detection. The integration of weather data further improves the relevance of the advisory responses, supporting informed decision-making in agricultural activities. Experimental evaluation demonstrates that the system is capable of delivering accurate and timely recommendations for common agricultural problems, thereby reducing dependency on traditional extension services and minimizing delays in expert consultation. The mobile-based interface ensures accessibility and ease of use, making the system suitable for farmers with varying levels of technical expertise. Although the current implementation shows promising results, its effectiveness is influenced by factors such as internet connectivity and the availability of high-quality datasets. Overall, the AI-Based Farmer Query Support and Advisory System highlights the potential of artificial intelligence in transforming agricultural support services. The project contributes toward improving crop productivity, reducing losses, and promoting sustainable farming practices. With further enhancements, the proposed system can be scaled to support a wider range of crops, regions, and languages, making it a valuable technological solution for modern smart agriculture.

References

[1] P. Jackson, Introduction to Expert Systems, 3rd ed. Boston, MA, USA: Addison-Wesley, 1999. [2] S. R. Rajeswari and K. Arunesh, “Analysing soil data using data mining classification techniques,” Indian Journal of Computer Science and Engineering, vol. 7, no. 1, pp. 17–23, 2016. [3] S. Sladojevic, M. Arsenovic, A. Anderla, D. Culibrk, and D. Stefanovic, “Deep neural networks based recognition of plant diseases by leaf image classification,” Computational Intelligence and Neuroscience, vol. 2016, pp. 1–11, 2016. [4] S. P. Mohanty, D. P. Hughes, and M. Salathé, “Using deep learning for image-based plant disease detection,” Frontiers in Plant Science, vol. 7, pp. 1–10, 2016. [5] A. Jain, A. Kumar, and S. Ranjan, “Agricultural chatbot using natural language processing,” International Journal of Computer Applications, vol. 181, no. 25, pp. 1–5, 2018. [6] R. K. Sharma and S. Singh, “ICT based agricultural advisory systems: A review,” International Journal of Advanced Research in Computer Science, vol. 9, no. 2, pp. 234–239, 2018. [7] Kamilaris and F. X. Prenafeta-Boldú, “Deep learning in agriculture: A survey,” Computers and Electronics in Agriculture, vol. 147, pp. 70–90, 2018. [8] T. Liakos, P. Busato, D. Moshou, S. Pearson, and D. Bochtis, “Machine learning in agriculture: A review,” Sensors, vol. 18, no. 8, pp. 1–29, 2018. [9] A. Wolfert, L. Ge, C. Verdouw, and M. J. Bogaardt, “Big data in smart farming – A review,” Agricultural Systems, vol. 153, pp. 69–80, 2017. [10] Ministry of Agriculture & Farmers Welfare, Government of India, “Digital agriculture initiatives in India,” 2020.

Copyright

Copyright © 2026 Nandu Naik Sabhavath, Vivekananda Musham, Manthapuram Rakesh, Padige Shivaprasad, R. Ramesh Naik, Dr. B. Venkataramana. This 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.