AgriSmart: An AI-Powered Farming Assistant and Crop Management Platform for Precision Agriculture

Sairah Baloch; Aisha Ali; Areeba Naeem

Authors

Sairah Baloch Department of Computer Science, University of Sindh, Jamshoro, Pakistan
Aisha Ali Department of Computer Science, University of Sindh, Jamshoro, Pakistan
Areeba Naeem Department of Computer Science, University of Sindh, Jamshoro, Pakistan

Keywords:

Agricultural Chatbot, Crop Recommendation, Machine Learning, Plant Disease Detection, Smart Agriculture

Abstract

Agriculture is an area plagued with problems around crop selection, post-harvest management of plant diseases, and expert advisory knowledge at the correct time, adversely affecting the output and economics in the agriculture sector, especially in developing nations such as Pakistan. In this research, we propose Agri Smart: a modular unified knowledge-based system consisting of an integrated hybrid AI application which comprises a crop recommender system, plant disease identification system, and an intelligent multilingual farm advisory chatbot, all integrated seamlessly within a single real-time platform. We used supervised machine learning algorithms such as Extreme Gradient Boosting (Boost) for the crop recommender system, deep learning models based on YOLO for a plant disease identification system, and advanced NLP techniques for the multilingual conversational agent. The results exhibited 99% classification accuracy for the crop recommender system with 22 classes, while the plant disease identification system achieved an F1 score of 0.70 and mAP@50 of 74%, with all modules working in real time. The Agri Boot module delivered accurate contextual comprehension responses with bilingual support, ensuring farmer accessibility. Overall, Agri Smart successfully demonstrates the application of integrated AI technology.

References

Srdjan Sladojevic, Marko Arsenovic, Andras Anderla, Dubravko Culibrk, Darko Stefanovic, “Deep Neural Networks Based Recognition of Plant Diseases by Leaf Image Classification,” Comput. Intell. Neurosci., 2016, doi: https://doi.org/10.1155/2016/3289801.

Konstantinos P. Ferentinos, “Deep learning models for plant disease detection and diagnosis,” Comput. Electron. Agric., vol. 145, pp. 311–318, 20181, [Online]. Available: https://www.sciencedirect.com/science/article/abs/pii/S0168169917311742

Edna Chebet Too, Li Yujian, “A comparative study of fine-tuning deep learning models for plant disease identification,” Comput. Electron. Agric., vol. 161, pp. 272–279, 2019, doi: https://doi.org/10.1016/j.compag.2018.03.032.

V. Kale and B. N. Mohapatra, “Crop Recommendation System Using Machine Learning,” J. Eng. Technol. Ind. Appl., vol. 10, no. 48, pp. 63–68, Jul. 2024, doi: 10.5935/jetia.v10i48.1186.

“Machine Learning-Based Crop Recommendation System Using Soil and Climate Parameters.” Accessed: Mar. 14, 2026. [Online]. Available: https://www.researchgate.net/publication/396817428_Machine_Learning-Based_Crop_Recommendation_System_Using_Soil_and_Climate_Parameters

S. Iniyan, V. Akhil Varma, “Crop Yield Prediction Using Machine Learning Techniques,” Adv. Eng. Softw., vol. 175, p. 103326, 2023, doi: https://doi.org/10.1016/j.advengsoft.2022.103326.

“AI-Powered Agriculture Chatbots for Farmers.” Accessed: Mar. 14, 2026. [Online]. Available: https://www.researchgate.net/publication/381003040_AI-Powered_Agriculture_Chatbots_for_Farmers