Intelligent Farming: Ai-driven Insights And Support

• Author(s):

  K.Ravikumar | M.Nithishkumar | S.Karthikeyan | K.Sanchay | V.Gokul

• Keywords:

  Intelligent Farming, Recommendation System, Random Forest, Support Vector Machine (SVM), Logistic Regression, Chatbot.

• Abstract:

  Agriculture Remains A Cornerstone Of Livelihoods In Countries Like India, Yet Farmers Often Struggle With Crop Selection And Nutrient Management Due To Limited Access To Data-driven Guidance. This Paper Introduces An Intelligent Farming Framework That Harnesses Artificial Intelligence (AI) To Deliver Actionable Insights For Crop Selection And Fertilizer Recommendations. By Integrating Machine Learning (ML) Models—Random Forest, Naïve Bayes, Support Vector Machine (SVM), And Logistic Regression—with A Majority Voting Ensemble, The System Predicts Suitable Crops Based On Soil And Environmental Factors With High Accuracy. Additionally, A Rule-based Approach Provides Fertilizer Suggestions By Analysing Nutrient Deficiencies. A Unique Chatbot, Powered By Google Gemini, Enhances User Interaction By Offering General Farming Advice While Deliberately Avoiding Responses Related To The System’s Pre-existing Crop And Fertilizer Tools To Maintain Modularity. Furthermore, A ResNet9-based Plant Disease Classification System Identifies 38 Disease Categories From Leaf Images With Near-perfect Test-set Accuracy, Enabling Early Detection. Experimental Results Demonstrate That The Random Forest Model Achieves A Peak Accuracy Of 99%, Outperforming Other Learners. This AI-driven Solution Empowers Farmers With Reliable, Accessible Support To Optimize Yields And Reduce Losses.

---

Other Details

• Paper id:

  IJSARTV11I4103005

• Published in:

  Volume: 11 Issue: 4 April 2025

• Publication Date:

  2025-04-05

Download Article