AgriAdvisor: AI-Enabled Decision Support System for Crop Planning, Disease Diagnosis and Pesticide Management

Abstract

Agriculture plays a vital role in ensuring food security and economic stability worldwide. Farmers often face challenges in selecting suitable crops, identifying plant diseases, predicting crop yield, and obtaining accurate weather information. To address these issues, this paper presents AgriAdvisor, an AI-enabled smart farming system that integrates Crop Recommendation, Plant Disease Detection, Yield Prediction, and Weather Monitoring into a unified web-based platform. The proposed system utilizes machine learning and deep learning techniques, including XGBoost for crop recommendation, Convolutional Neural Networks (CNN) for disease detection, and Gradient Boosting Regression for yield prediction. A Streamlit-based interface allows farmers to access all services through a single dashboard. Experimental results demonstrate that the proposed system achieves high prediction accuracy and provides reliable decision support for modern precision agriculture.

Introduction

The text presents AgriAdvisor: An AI-Enabled Smart Farming System, a web-based intelligent agriculture platform designed to improve farming decisions using Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL). The system addresses major agricultural challenges such as poor crop selection, plant diseases, uncertain weather conditions, and inaccurate yield prediction.

AgriAdvisor integrates multiple modules:

• Crop Recommendation: Uses soil and environmental parameters to suggest suitable crops using the XGBoost Classifier.
• Yield Prediction: Estimates crop production using a Gradient Boosting Regressor based on crop type, area, rainfall, fertilizer usage, and temperature.
• Plant Disease Detection: Uses a ResNet50-based CNN model trained on the PlantVillage dataset to identify diseases from leaf images and recommend pesticides.
• Weather Monitoring: Provides real-time weather information to support farm planning.

The literature review highlights previous research showing that ML improves crop recommendation and yield prediction, while DL-based CNN models provide accurate plant disease detection. However, existing solutions mostly focus on individual agricultural tasks, creating a need for an integrated smart farming platform.

The methodology involves:

1. Data Acquisition – collecting crop, yield, and plant disease datasets.
2. Data Preprocessing – cleaning data, handling missing values, normalizing inputs, and preparing images.
3. Model Development – training ML and DL models with an 80:20 train-test split.
4. Model Evaluation – measuring performance using accuracy, precision, recall, F1-score, MSE, RMSE, MAE, and R² score.

The system is implemented using Python, TensorFlow, Keras, XGBoost, Gradient Boosting, and Streamlit. It provides a user-friendly interface where farmers can access crop recommendations, disease diagnosis, yield estimates, pesticide suggestions, and weather updates.

Conclusion

The proposed AgriAdvisor: AI-Enabled Smart Farming System successfully integrates Crop Recommendation, Disease Detection, Yield Prediction, Pesticide Recommendation, and Weather Monitoring into a unified agricultural decision-support platform. The system utilizes XGBoost for crop recommendation, Gradient Boosting Regressor for yield prediction, and a ResNet50-based Convolutional Neural Network (CNN) for plant disease detection. Experimental results demonstrated that the developed models provide accurate and reliable predictions, enabling farmers to make informed decisions regarding crop selection, disease management, and productivity enhancement. The integration of real-time weather information further improves the practicality and effectiveness of the system.By combining machine learning, deep learning, and web technologies within a user-friendly Streamlit application, AgriAdvisor contributes to precision agriculture and sustainable farming practices. In the future, the system can be enhanced by incorporating IoT-based sensor data,advanced weather forecasting, fertilizer recommendation modules, and multilingual support to provide more comprehensive and intelligent agricultural assistance.

References

[1] J.-J. Liu, H. Wu, and I. Riaz, “Advanced Technologies for Smart Fertilizer Management in Agriculture: A Review,” IEEE Access, vol. ? (2025), doi: 10.1109/…/11105387. [Online]. Available: https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=11105387 [2] E. Aldhahri, A. A. Almazroi, M. H. Alkinani, N. Ayub, E. A. Alghamdi and N. F. Janbi, “Smart Farming: Enhancing Urban Agriculture Through Predictive Analytics and Resource Optimization,” Available: https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=10843189 [3] I. Ahmed, G. Habib and P. K. Yadav, “An approach to identify and classify agricultural crop diseases using machine learning and deep learning techniques,” Proc.Int. Conf. Emerging Smart Computing and Informatics (ESCI), Pune, India, 1-3 March 2023, pp. 1-6. [Online]. Available: https://www.researchgate.net/publication/370150161_An_Approach_to_Identify_and_Classify_Agricultural_Crop_Diseases_Using_Machine_Learning_and_Deep_Learning_Techniques. [4] M. Mustofa, “Optimization of Pesticide Spray Using AI Techniques,” IEEE Access, vol. ?, no. ?, p p . ? , 2 0 2 4 , d o i : 1 0 . 1 1 0 9 / … / 1 1 1 0 5 3 8 7 . [ O n l i n e ] . A v a i l a b l e : https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=11105387 [5] R. Rani, J. Sahoo, S. Bellamkonda, S. Kumar and S. K. Pippal, “Role of Artificial Intelligence in Agriculture:An Analysis and Advancements With Focus on Plant Diseases, IEEE Access , Available:https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber= [6] J. O. Betancourt, “A Computational Framework for Precise Aerial Agricultural Spraying Optimization,” Univ. / technical report / conference ( 2024 ) . [ Online]. Available: https://msol.berkeley.edu/wp-content/uploads/2024/04/205.pdf [7] J. Xu, “Collaborative orchard pesticide spraying routing problem: optimization and algorithms,” Journal of Cleaner Production, 2024. [ Online]. Available ( publisher link/ abstract): https://www.sciencedirect.com/science/article/abs/pii/S0959652624018778 [8] M. K. Senapaty, A. Ray, and N. Padhy, “A Decision Support System for Crop Recommendation Using Machine Learning Classification Algorithms,” Agriculture, vol. 14, no. 8, 2024. [Online]. Available: https://www.mdpi.com/2077-0472/14/8/1256 [9] J. Xu, “Collaborative orchard pesticide spraying routing problem: optimization and algorithms,” Journal of Cleaner Production, 2024. [ Online]. Available ( publisher link/ abstract).https://www.sciencedirect.com/science/article/abs/pii/S0959652624018778 [10] A. Soussi, et al., “Smart Sensors and Smart Data for Precision Agriculture,” Sensors, vol. 24, no. 8, 2024. [Online]. Available: https://www.mdpi.com/1424-8220/24/8/2647

Copyright

Copyright © 2026 Bandi Rachana, Mr. G. Narasimham. 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.