AgriGeniusAI: Smart Agricultural Management System Using Artificial Intelligence

Abstract

The agricultural sector faces significant challenges in supply chain management, real-time advisory, and market connectivity. This paper presents \"Agri-Genius AI,\" a comprehensive, role-based agricultural management platform designed to bridge the gap between farmers, buyers, field agents, and agricultural companies. Built using a modern tech stack including React, Supabase, and Google Generative AI, the system provides customized dashboards for various stakeholders. Key features include real-time crop advisory, integrated marketplaces, logistical management, and geographic mapping using Leaflet. The proposed system enhances operational efficiency, provides proactive farmer support, and streamlines agricultural trade, thereby contributing to modern, data-driven farming practices.

Introduction

The study presents AgriGeniusAI, an intelligent digital agricultural ecosystem designed to overcome traditional farming challenges such as limited market access, inefficient communication, lack of advisory support, and dependency on intermediaries. The platform integrates artificial intelligence, e-commerce, real-time data management, and geospatial technologies to connect farmers, field officers, agricultural companies, and buyers through a single transparent system.

The platform provides farmers with AI-based crop advisory services using Generative AI, offering real-time guidance on crop health, pest control, and weather conditions. It also enables direct selling through an integrated marketplace, allowing farmers to access buyers without middlemen. Buyers benefit from transparent procurement, live inventory tracking, and automated digital invoice generation. Field officers and companies use the "Farmer Connect" framework for farmer onboarding, monitoring, logistics planning, and data-driven management.

The system is developed using modern web technologies, including React.js and Vite for a responsive frontend, Supabase for secure database management and authentication, Leaflet/React-Leaflet for farm location mapping, and jsPDF for automated document generation. Role-based dashboards ensure customized access for farmers, buyers, employees, and administrators.

The literature review highlights the importance of Explainable AI, deep learning-based crop disease detection, edge computing for rural areas, and centralized agricultural data platforms. Previous research shows that AI adoption improves farming decisions, while real-time data processing and scalable infrastructure are essential for modern agricultural management.

The methodology follows a modular architecture consisting of:

• Farmer Module: Provides AI crop advisory and direct marketplace access.
• Buyer Module: Enables produce purchasing, transparent transactions, and automated invoices.
• Employee/Admin Module: Supports farmer management, geospatial tracking, and logistics coordination.
• Cloud Data Layer: Ensures real-time synchronization between users and services.

The system was implemented in three phases: interface and database development, integration of AI and mapping APIs, and final testing with security measures such as Role-Based Access Control (RBAC).

Results demonstrate that AgriGeniusAI successfully improved agricultural workflow efficiency. The RBAC system enabled smooth user-specific dashboard access, reducing administrative effort. The AI advisory module provided accurate and actionable crop recommendations, reducing the workload on field officers. The marketplace improved transparency by enabling direct farmer-to-buyer transactions, while automated invoice generation created secure digital records.

Geospatial mapping enhanced logistics by helping teams locate farms, organize collections, and optimize transportation routes for agricultural products. Overall, the platform successfully combines AI, cloud computing, and digital marketplace solutions to create a sustainable, transparent, and efficient agricultural ecosystem. Future improvements may include regional language AI support and IoT-based sensor integration for automated farm monitoring.

Conclusion

The traditional agricultural supply chain has long been characterized by systemic inefficiencies, information asymmetry, and heavy reliance on intermediaries, which ultimately disenfranchises the primary producers. The development and deployment of the AgriGeniusAI platform successfully addresses these critical challenges by introducing a centralized, multi-role digital ecosystem. By integrating modern web technologies (React.js and Vite) with robust cloud infrastructure (Supabase), the project established a seamless and secure environment that connects farmers, field agents, buyers, and agricultural companies. The implementation of Google Generative AI fundamentally transformed the crop advisory process, providing farmers with real-time, context-aware agricultural guidance and significantly reducing the response time compared to traditional manual advisory methods. Furthermore, the embedded digital marketplace successfully facilitated direct farmer-to-buyer transactions, optimizing market access and ensuring transparent pricing. Logistical operations were greatly enhanced through the integration of geospatial mapping tools (React-Leaflet), allowing field officers to monitor farm locations visually and execute proactive \"Farmer Connect\" initiatives. Additionally, the automated invoice generation system (jsPDF) ensured that all marketplace transactions were securely documented, creating a reliable digital paper trail for procurement. In conclusion, AgriGeniusAI proves that synthesizing artificial intelligence, geospatial data, and e-commerce into a single cohesive platform is a highly viable solution for modernizing agriculture. The system not only empowers farmers with actionable intelligence and direct market access but also streamlines operational logistics for agricultural companies. Future enhancements of the platform could explore the integration of IoT-based soil sensors for automated field telemetry and the implementation of regional language models to further increase accessibility for rural farming communities.

References

[1] Supit and A. Chaudhary, “Smart Farming with explainable AI for effective agricultural decision making,” IEEE Trans. AgriFood Electron., vol. 2, pp. 112–120, Mar. 2024. [2] S. Ashok Kumar, F. Shaik, B. Yashwitha, P. Vidyavathi, A. Uma Maheswari, and P. Spurthi, “Intelligence pest detection and control in agriculture using computer vision and deep learning,” IEEE Access, vol. 13, pp. 4510–4525, Jan. 2025. [3] T. G. Manjunath, S. Gowda M. A., K. Sheelavant, Harika, I. Sriram, and M. Monika, “Real-time offline edge AI framework for sensor integrated precision agriculture,” in Proc. IEEE Int. Conf. Smart Agri. (ICSA), 2024, paper 4.2.1, pp. 89–95. [4] K.-H. Kim and W. Seok, “AI research platform for agriculture sector: Big data management and AI model development platform,” in Proc. IEEE Int. Symp. Data-Driven Agri., 2024, pp. 210–215. [5] 2024) The React website. [Online]. Available: https://react.dev/ [6] 2024) Supabase documentation. [Online]. Available: https://supabase.com/docs [7] “Google Gemini API technical documentation,” Google Cloud, Mountain View, CA, Tech. Rep. GenAI-24-01, 2024.

Copyright

Copyright © 2026 Dr. Prathiba G, Thejas B J, Prajwal S, Kavya , Sahana R, Kruthika H R. 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.