Artificial Intelligence-Based Crop Recommendation and Disease Detection System

Abstract

Agriculture plays a huge role in India. It keeps a ton of people employed and pumps a lot into the economy. Still, farmers run into all sorts of issues. They struggle with picking the right crops. Optimizing fertilizers is another headache. And spotting diseases early in crops. All that leads to lower yields and worn-out soil. This study brings in an AI setup that pulls together crop suggestions, better fertilizer use, and disease spotting all in one package. It looks at soil stuff like nitrogen levels, phosphorus, potassium, pH balance, and how moist the ground is. Then it factors in things like the weather, temperature, rainfall too. From there, it suggests the best crop and fertilizer mix. Machine learning handles the predictions for crops and fertilizers pretty accurately. For diseases, it uses deep learning with these CNN models to check leaf pictures and classify problems. The whole thing is meant to help farmers, whether they are pros or just starting out. They can make smarter choices based on data. That boosts yields, cuts down on wasted fertilizer, and keeps disease losses in check. Overall, this AI way of doing things pushes agriculture toward being smarter, more sustainable, with tech right in the mix.

Introduction

Agriculture remains a major global sector but farmers face challenges in selecting crops, applying fertilizers, and detecting plant diseases due to reliance on traditional intuition-based methods. Machine learning (ML) and deep learning (DL) provide data-driven solutions, analyzing soil parameters (N, P, K, pH, temperature, humidity, rainfall) for crop recommendations and using CNN models like ResNet50 and EfficientNetV2 for disease detection. Ensemble ML models such as XGBoost and Random Forest improve prediction accuracy and robustness.

This study proposes a hybrid system integrating three key modules: crop recommendation, plant disease detection, and fertilizer optimization. The crop module uses ML algorithms on environmental and soil datasets, while the disease module leverages DL on leaf images from the PlantVillage dataset. Data preprocessing, augmentation, normalization, and training with transfer learning enhance model performance. The models were deployed on a web-based platform using Python Flask, providing farmers with easy-to-use interfaces for crop selection and disease identification without relying on sensors.

Results showed high accuracy: XGBoost excelled in crop recommendation, while CNN models achieved over 95% accuracy in disease detection. The integrated system demonstrates a scalable, data-driven, and accessible approach to precision agriculture, supporting informed decisions for improved yield and sustainable farming.

Conclusion

This research theyre proposing sets up a framework thats all about data. It mixes machine learning with deep learning stuff for recommending crops, spotting plant diseases, and suggesting fertilizers. The system does a good job predicting which crops fit best. It picks out diseases from pictures of leaves too. And it suggests fertilizers looking at soil nutrients and what the crop needs. They used ensemble models like Random Forest and XGBoost. Those got about 99 percent accuracy on crop prediction. EfficientNetV2 hit 97 percent for classifying diseases. The fertilizer part helps with decisions. It optimizes how nutrients get used and boosts soil health. You know, overall this hybrid model seems efficient and accurate. It offers a sustainable way for precision agriculture these days.

References

[1] P. A. Krishna, N. Padhy, and A. Patnaik, “Applying Machine Learning for Sustainable Farm Management,” Engineering Proceedings, vol. 67, no. 73, pp. 1–8, 2024. [2] S. Kapoor, I. Aggarwal, and A. K. Ray, “Smart Agriculture Farming Using Harvestify Web App,” Proceedings of the AECE Conference, pp. 542–546, 2022. [3] [3] R. Kumar and N. Shukla, “Plant Disease Detection and Crop Recommendation Using CNN and Machine Learning,” Proceedings of the 2022 International Mobile and Embedded Technology Conference (MECON), Noida, India, Mar. 10–11, 2022, pp. 168–172. [4] N. Patil, S. Kelkar, M. Ranawat, and M. Vijayalakshmi, “Krushisahyog: Plant Disease Identification and Crop Recommendation Using Artificial Intelligence,” Proceedings of the 2021 2nd International Conference for Emerging Technology (INCET), Belagavi, India, May 21–23, 2021, pp. 1–6. [5] M. Choudhary, R. Sartandel, A. Arun, L. Ladge, S. Hiranwal, and G. Mathur, “Crop Recommendation System and Plant Disease Classification Using Machine Learning for Precision Agriculture,” Proceedings of the Artificial Intelligence and Communication Technologies Conference, Jaipur, India, Aug. 6, 2022, pp. 39–49. [6] D. Gosai, C. Raval, R. Nayak, H. Jayswal, and A. Patel, “Crop Recommendation System Using Machine Learning,” International Journal of Scientific Research in Computer Science, Engineering and Information Technology, vol. 7, pp. 558–569, 2021. [7] P. Bandara, T. Weerasooriya, T. Ruchirawya, W. Nanayakkara, M. Dimantha, and M. Pabasara, “Crop Recommendation System,” International Journal of Computer Applications, vol. 975, p. 8887, 2020. [8] S. K. Apat, J. Mishra, K. S. Raju, and N. Padhy, “An Artificial Intelligence-Based Crop Recommendation System Using Machine Learning,” Journal of Scientific and Industrial Research (JSIR), vol. 82, pp. 558–567, 2023. [9] M. Garanayak, G. Sahu, S. N. Mohanty, and A. K. Jagadev, “Agricultural Recommendation System for Crops Using Different Machine Learning Regression Methods,” International Journal of Agricultural and Environmental Information Systems (IJAEIS), vol. 12, pp. 20–30, 2021. [10] R. K. Rajak, A. Pawar, M. Pendke, P. Shinde, S. Rathod, and A. Devare, “Crop Recommendation System to Maximize Crop Yield Using Machine Learning Technique,” International Research Journal of Engineering and Technology (IRJET), vol. 4, pp. 950–953, 2017. [11] S. Kiruthika and D. Karthika, “Professional Crop Recommendation System Using a Weight-Based LongTerm Memory Approach,” Measurement: Sensors, vol. 27, p. 100722, 2023. [12] D. H. Patel, K. P. Shah, R. Gupta, N. K. Jadav, S. Tanwar, B. C. Neagu, S. Attila, F. Alqahtani, and A. Tolba, “Blockchain-Based Crop Recommendation System for Precision Farming,” Agronomy, vol. 13, p. 2642, 2023. [13] V. K. Soni and P. Soni, “Plant Disease Prediction Using Machine Learning,” Mathematics, Statistics and Engineering Applications, vol. 71, pp. 9739–9747, 2022. [14] T. Domingues, T. Brandão, and J. C. Ferreira, “Machine Learning for Detection and Prediction of Crop Diseases and Pests: A Comprehensive Survey,” Agriculture, vol. 12, p. 1350, 2022. [15] S. Mohanty, A. L. Subramanian, and R. R. Nayak, “Artificial Intelligence in Agriculture: Opportunities, Challenges and the Road Ahead,” Journal of Agricultural Science, vol. 12, no. 7, pp. 45– 56, 2020. [16] “Future Farms - Small & Smart: A Review Challenges In Big Data” in the International Conference on Intelligent Computing & Networking (IC-ICN 2023) by Prof. Vijay Rakhade, Mr. Akash A. Howladar. [17] Kaggle, “Crop Recommendation Dataset,” [Online]. Available: https://www.kaggle.com/datasets/atharvaingle/croprecommendation-dataset. [Accessed: Sept. 17, 2025]. [18] Kaggle, “PlantVillage Disease Classification Dataset,” [Online]. Available: https://www.kaggle.com/datasets/emmarex/plantdisease. [Accessed: Sept. 17, 2025]. [19] “A Review On Using Android Application For A Modern Farming Techniques” By Mr. Akash A. Howladar, Prof. Ashish B. Deharkar , Prof. Vijay M. Rakhade, in International Journal of Advanced Research in Computer and Communication Engineering(IJARCCE), ISSN (O) 2278-1021, ISSN (P) 2319-594 [20] Wolfert, S., Ge, L., Verdouw, C., & Bogaardt, M.-J. (2017). Big Data in Smart Farming – A Review. Agricultural Systems, 153, 69–80. [21] Dey, R., & Kumar, R. (2021).Crop Recommendation System Using Machine Learning Algorithms. International Journal of Computer Applications, 183(25), 28–32. [22] Sharma, N., Singh, A., & Singh, A. (2021). Fertilizer Recommendation System for Precision Agriculture Using Machine Learning. Journal of Physics: Conference Series, 1714(1), 012021. [23] Hughes, D., & Salathé, M. (2015). An Open Access Repository of Images on Plant Health to Enable the Development of Mobile Disease Diagnostics. arXiv:1511.08060. (PlantVillage Dataset) [24] Mohanty, S. P., Hughes, D. P., & Salathé, M. (2016). Using Deep Learning for Image-Based Plant Disease Detection. Frontiers in Plant Science, 7, 1419. [25] Singh, V., & Misra, A. K. (2017). Detection of Plant Leaf Diseases Using Image Segmentation and Soft Computing Techniques. Information Processing in Agriculture, 4(1), 41–49.

Copyright

Copyright © 2025 Prof. Vishwajeet K. Barbudhe, Chaitanya Dhawade, Susmit Shingne, Neha Zope, Sakshi Ghanwat. 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.