AgriGrowth: An AI-Powered Organic Farming Assistant for Soil Analysis, Crop Recommendation, and Market Intelligence

Abstract

Agriculture remains a fundamental sector supporting the global economy and food security. Despite technological progress,farmerscontinuetoface significantchallengessuchasdecliningsoilfertility, impropercropselection,insufficient access to agricultural expertise, and fluctuating market prices. These challenges often result in reduced crop productivity and economic instability for farmers. To address these issues, this research proposes Agri Growth, an intelligent farming assistant designed to integrate artificial intelligence with modern digital technologies to support sustainable agricultural practices.The Agri Growth platformprovidesfarmerswithacomprehensivedecision-supportsystemthatincludessoilnutrientanalysis,croprecommendation, marketintelligence,andexpertagriculturalguidance.Thesystem analysessoilparametersincludingNitrogen(N), Phosphorus (P), Potassium (K), and pH values using machine learning algorithms to recommend suitable crops and fertilizers. Additionally, the platform integrates real-time agricultural market price information to help farmers determine optimal selling strategies. An AI- powered chatbot is incorporated to provide farmers with instant answers to agricultural queries and best farming practices.The system is developed using Fast API for backend processing, React for the frontend interface, and machine learning models implemented using Python libraries such as Scikit-Learn and Pandas. Experimental evaluation demonstrates that the system caneffectivelyprovideaccuratecroprecommendationsandimprovedecision-makingcapabilitiesforfarmers.Theproposedsystem contributes to the advancement of smart agriculture technologies and supports the transition toward sustainable organic farming practices.

Introduction

Veg Market – Smart Agriculture & Crop Intelligence Platform is a web-based solution designed to improve agricultural decision-making by integrating AI, machine learning, and real-time market data. It addresses key problems faced by farmers such as lack of market price awareness, subjective crop quality assessment, and limited access to agricultural guidance.

The system combines three main functions: soil analysis, crop recommendation, and market intelligence. Soil analysis evaluates parameters like pH, nitrogen, phosphorus, potassium, moisture, and organic carbon to determine soil health and provide fertilizer suggestions. A Random Forest model is used to recommend suitable crops based on environmental and soil conditions using data such as temperature, rainfall, and humidity. The market intelligence module provides real-time vegetable price information by identifying nearby markets using geographic distance calculations (Haversine formula).

Additionally, the platform includes an AI-based advisory system to help farmers with cultivation practices and decision-making. The system is built using a modern architecture: a React/Next.js frontend, FastAPI backend, and machine learning models integrated through APIs.

Literature review shows that existing agricultural systems often focus on isolated functions like crop classification, disease detection, or market monitoring. The proposed platform improves upon this by combining all these features into a single unified system.

Conclusion

Agriculture remains a critical sector that requires efficient decision-making tools to improve productivity and sustainability. Farmers often face challenges such as limited accessto soilanalysis, lackof croprecommendation systems, and insufficient market price information. These challenges highlight theneed for intelligent agriculturaldecision support systems. ThisresearchpresentedtheVegMarket–SmartAgriculture &CropIntelligencePlatform,aweb-basedsystemdesigned toassist farmersthroughsoil analysis, machinelearning–based crop recommendation, and market intelligence services. The proposed platform integrates modern web technologies with machine learning models to provide farmers with actionable agricultural insights. The system evaluates soil nutrient parameters, calculates soil health scores, predicts suitable crops using a Random Forest classifier,andretrievesnearbymarketpriceinformationusing geographic distance calculations. By combining these functionalities within a single platform, the system provides farmers with a comprehensive decision support tool. Experimental evaluation demonstrated that the machine learning model achieves high accuracy in predicting suitable crops based on soil and environmental parameters. The integration of soil analysis and market intelligence further enhances the practical usefulness of the system. Overall, the Veg Market platform demonstrates how artificial intelligence and digital technologies can be applied to agriculture to improve farming efficiency, reduce crop loss, and support better market decisions.

References

[1] S. Ramesh and B. Vishnu Vardhan, “Data mining techniques and applications to agricultural yield data,” InternationalJournalofAdvancedResearchinComputerand CommunicationEngineering,vol.4,no.1,pp.432–436,2015. [2] S. Mohanty, D. Hughes, and M. Salathé, “Using deep learningforimage-basedplantdiseasedetection,”Frontiersin Plant Science, vol. 7, pp. 1–10, 2016. [3] A. Pawara, S. Okafor, P. Surinta, L. Schomaker, and M. Wiering, “Comparing local descriptors and bags of visual words to deep convolutional neural networks for plant recognition,” International Conference on Pattern Recognition Applications and Methods, pp. 479–486, 2017. [4] R.SujathaandP.Isakki,“Astudyoncropyieldforecasting using classification techniques,” International Journal of ComputerScienceandInformationSecurity,vol.14,no.5,pp. 199–205, 2016. [5] M.KamilarisandF.X.Prenafeta-Boldú,“Deeplearningin agriculture: A survey,” Computers and Electronics in Agriculture, vol. 147, pp. 70–90, 2018. [6] S. Liakos, P. Busato, D. Moshou, S. Pearson, and D. Bochtis,“Machinelearninginagriculture:Areview,”Sensors, vol. 18, no. 8, pp. 1–29, 2018. [7] A.Esteva,B.Kuprel,R.Novoaetal.,“Dermatologist-level classification of skin cancer with deep neural networks,” Nature, vol. 542, pp. 115–118, 2017. [8] P.Mishra,A.K.Singh,andB.K.Singh,“Smartagriculture system using machine learning and IoT,” International JournalofAdvancedComputerScienceandApplications,vol. 10, no. 2, pp. 404–409, 2019. [9] M. A. Shah and S. S. Chavan, “Crop recommendation system using machine learning,” International Journal of Innovative Research in Computer and Communication Engineering, vol. 8, no. 6, pp. 3124–3129, 2020. [10] Kaur and H. Singh, “Machine learning based crop recommendation system for precision agriculture,” Procedia Computer Science, vol. 167, pp. 1250–1259, 2020. [11] S. Patil and R. S. Bhosale, “Crop prediction using machine learning algorithms,” International Journal of Scientific Research in Computer Science, Engineering and Information Technology, vol. 5, no. 2, pp. 189–194, 2019. [12] J.Wolfert, L. Ge, C. Verdouw, and M. J. Bogaardt, “Big data in smart farming – Areview,” Agricultural Systems, vol. 153, pp. 69–80, 2017. [13] H. T. Kung, C. H. Chen, and J. H. Lin, “A machine learning approach for crop recommendation system,” IEEE International Conference on Artificial Intelligence and Data Processing, pp. 1–6, 2019. [14] Kamilaris and F. X. Prenafeta-Boldú, “Deep learning applications in agriculture,” Computers and Electronics in Agriculture, vol. 147, pp. 70–90, 2018. [15] R.Jain,A.S.Kumar,andS.K.Singh,“Smartagriculture monitoring system using IoT and machine learning,” IEEE International Conference on Smart Systems and Inventive Technology, pp. 522–527, 2020.

Copyright

Copyright © 2026 Mrs. M. Suguna , Kilugu Mahesh Reddy , Pilli Venkata Venu, Somagutta Pavankumar Reddy . 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.