Farmer Advisory Report Generator using Soil, Weather & Crop Data using GenAI

Abstract

Agriculture is increasingly affected by climate variability, unpredictable weather conditions, and crop diseases that reduce productivity and threaten food security. Farmers often rely on fragmented tools for monitoring weather, soil conditions, and disease detection, which leads to inefficient decision making. To address these challenges, this research presents a web-based Farmer Advisory Report Generator that integrates soil data, weather information, and crop disease detection using Artificial Intelligence (AI) and Generative Artificial Intelligence (GenAI). The proposed system collects real-time environmental data from IoT-based sensors such as NodeMCU, soil moisture sensors, and DHT11 temperature–humidity sensors. In addition, the system retrieves real-time weather and forecast data from the Open-Meteo API. Farmers can also upload crop leaf images, which are analyzed using a Convolutional Neural Network (CNN) to detect plant diseases. The detected results are processed through a Generative AI Large Language Model (LLM) such as Gemini to generate comprehensive advisory reports including disease diagnosis, treatment suggestions, and irrigation recommendations. The system integrates multiple data sources into a unified decision-support platform, enabling farmers to receive accurate, real-time, and actionable agricultural insights. The proposed approach improves early disease detection, enhances crop management, and supports data-driven farming practices for sustainable agriculture.

Introduction

Modern agriculture faces challenges from climate change, limited water resources, and crop diseases, making traditional decision-making methods insufficient. While technologies like IoT sensors, weather forecasting, and deep learning-based disease detection exist, they often operate separately, complicating farm management.

To address this, the Farmer Advisory Report Generator is proposed as an integrated web-based platform. It combines real-time IoT sensor data (soil moisture, temperature, humidity), weather forecasts from Open-Meteo, and crop disease detection using CNNs from leaf images. Outputs are processed by Generative AI models (LLMs) to generate detailed, natural-language advisory reports with disease explanations, treatment suggestions, and irrigation recommendations. The system is designed to provide farmers with unified, real-time guidance to improve productivity, reduce crop losses, and enable data-driven farm management.

The architecture consists of four layers:

1. Data Acquisition – Collects sensor data and leaf images.

2. Communication – Transfers data securely to the backend.

3. Processing – Analyzes data with CNNs and Generative AI to produce advisory reports.

4. Application – Web interface displays recommendations and environmental data to farmers, supporting multilingual output.

The system ensures security through HTTPS, session-based authentication, and data logging, enabling reliable, automated, and actionable agricultural guidance.

Conclusion

The proposed Farmer Advisory Report Generator integrates Artificial Intelligence (AI), Internet of Things (IoT), and Computer Vision to support intelligent agricultural decision-making. The system collects environmental data from IoT sensors, retrieves weather information through APIs, and analyzes crop leaf images using a CNN model. By combining these technologies, the system provides farmers with accurate and real-time insights related to crop health, soil conditions, and weather forecasts. The integration of Generative AI enables the automatic generation of advisory reports that include disease diagnosis, treatment suggestions, and irrigation recommendations. Experimental results show that the system achieves around 94% accuracy in disease detection with a fast response time. Additionally, the multilingual web interface improves accessibility, making the platform a practical and scalable solution for modern precision agriculture.

References

[1] E.-G. Talie and T. O. Oladele, “A Review of IoT-Based Smart Farming Framework,” in 2022 IEEE Nigeria 4th International Conference on Disruptive Technologies for Sustainable Development (NIGERCON), Lagos, Nigeria, 2022, pp. 1–6. [2] P. Kumar, V. P. Singh, and A. Kumar, “Weather Prediction and Agricultural Advisory Using Machine Learning,” in Smart Systems: Innovations in Computing, Singapore: Springer, 2023, pp. 315–325. [3] S. S. S. L. H. B. K., “Detection of Plant Disease Using Convolutional Neural Networks,” International Journal of Engineering and Advanced Technology (IJEAT), vol. 10, no. 5, pp. 126–130, 2021. [4] J. A. L. S. T. A. A. B. S. A. G. O. O. A. M. H. H. T. A. T., “Conceptual Applications of ChatGPT in Agriculture and Agritech Systems,” arXiv Preprint arXiv:2307.03812, 2023. [5] J. G. Arnal Barbedo, “A Review on the Main Challenges in Automatic Plant Disease Identification Based on Visible Range Images,” Biosystems Engineering, vol. 144, pp. 52–60, 2016. [6] M. A. A. Al-Ali, M. A. Anbar, and M. A. A. Al-Ali, “An Overview of Precision Farming and Smart Agriculture Technologies,” in 2020 2nd International Conference on Electrical, Control and Instrumentation Engineering (ICECIE), Kuala Lumpur, Malaysia, 2020, pp. 1–6. [7] F. K. Shaikh, Z. A. Zardari, and S. A. Zardari, “IoT-Enabled Soil Quality Monitoring for Precision Agriculture,” Computers and Electronics in Agriculture, vol. 195, p. 106822, 2022. [8] A. K. Singh, A. Singh, and D. Kumar, “AI-Driven Plant Disease Detection: A Review of Recent Research,” Journal of Plant Diseases and Protection, vol. 130, no. 1, pp. 1–17, 2023. [9] S. R. Krishna, K. S. Kumar, G. V. Kumar, and V. M. Kumar, “Smart Irrigation System Using NodeMCU and IoT,” in 2021 5th International Conference on Trends in Electronics and Informatics (ICOEI), Tirunelveli, India, 2021, pp. 1243–1248. [10] S. Bhatia, V. Kumar, and M. Kumar, “Natural Language Processing in Agriculture: A Review,” ACM Computing Surveys (CSUR), vol. 54, no. 8, pp. 1–36, 2021.

Copyright

Copyright © 2026 Omkar Shelke, Vaibhav Vavhal, Amar Varpe, Trupti Kanthale, Prof. Sunil Bangare, Prof. Shriram Kulkarni. 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.