This study provides an extensive web and mobile-based application aimed at improving agriculture practice using crop suggestion, disease prediction, and farmer query answering. The system applies machine learning, image processing, and natural language processing concepts to present recommendatory information to farmers. Random
Forest is applied for crop prediction with an accuracy rate of 99.14%, while CNN is applied for disease prediction. Moreover, an expert-consulting system through real-time chat-based query resolution links farmers with experts. This technology-based solution is designed to enhance crop yield, optimize farm decisions, and increase accessibility for farmers.
Introduction
Agriculture is vital for global food security and employment, but farmers often face challenges in crop selection, disease identification, and accessing expert advice. The UPAJ system addresses these issues by integrating machine learning and AI technologies into a single platform to improve farming efficiency and sustainability.
The system includes three main modules:
Crop Suggestion – Uses a Random Forest algorithm to recommend crops based on soil data, weather, and past yields, achieving 99.14% accuracy.
Disease Detection – Employs Convolutional Neural Networks (CNN) to identify plant diseases from images with 95.2% accuracy, enabling early intervention.
Farmer Query Resolution – Provides real-time expert advice through an AI chatbot and live communication, responding in under five seconds.
Built with technologies like Node.js, MongoDB, Firebase, and IoT sensors, UPAJ offers region-specific, data-driven farming recommendations. The system has been positively received, with 92% user satisfaction, demonstrating its effectiveness in enhancing agricultural decision-making and productivity.
Conclusion
The paper introduces the Crop Suggestion, Disease Detection & Farmer Query Resolution System (UPAJ) as a holistic strategy to advance agricultural decision-making through machine learning mechanisms. Using the Random Forest
Algorithm (RFA) to generate crop suggestion and Convolutional Neural Networks (CNN) for detecting disease, the system ensures farmers get proper and evidence-based suggestions. RFA effectively examines soil characteristics, climatic conditions, and past data to recommend the best crops, maximizing productivity and sustainability. CNN, however, facilitates accurate disease detection through image processing, enabling early diagnosis and proper treatment methodologies. The real-time query resolution system also helps in filling the gap between farmers and agricultural specialists to be able toensure timely and well-informed decision-making. The integration of these technologies not only improves crop yield but also reduces losses from poor crop choice and delayed disease control. Future development of this system may involve IoT-based real-time soil monitoring, improved deep learning architectures fordisease detection, and multi-language support for wider accessibility. Through the application of AI-based solutions, UPAJ helps bring about the modernization of agriculture, equipping farmers with smart tools to make them more efficient, minimize risks, and encourage sustainable farming methods.
References
[1] Hochreiter, S., &Schmidhuber, J. (1997). Long shortterm memory. Neural computation, 9(8), 1735-1780.
[2] Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. A. (2017). Inception-v4, inception-resnet and the impact of residual connections on learning. AAAI.
[3] Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in neural information processing systems.
[4] Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32.
[5] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... &Polosukhin, I. (2017). Attention is all you need. Advances in neural information processing systems.
[6] Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT press.
[7] Redmon, J., & Farhadi, A. (2018). YOLOv3: An incremental improvement. arXiv preprint arXiv:1804.02767.
[8] Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
[9] Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2018). BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
[10] Chen, T., &Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.
[11] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. IEEE Conference on Computer Vision and Pattern Recognition.
[12] Kamilaris, A., &Prenafeta-Boldú, F. X. (2018). Deep learning in agriculture: A survey. Computers and electronics in agriculture, 147, 70-90.
[13] Mohanty, S. P., Hughes, D. P., &Salathé, M. (2016). Using deep learning for image-based plant disease detection. Frontiers in plant science, 7, 1419.
[14] Dutta, P., & Paul, S. (2019). Application of machine learning in agriculture for optimizing crop yield.
[15] Journal of Emerging Technologies and Innovative Research, 6(1), 56-64.
[16] Singh, V., & Misra, A. (2017). Detection of plant leaf diseases using image segmentation and soft computing techniques. Information Processing in Agriculture, 4(1), 41-49. Pantazi, X. E., Moshou, D., &Bochtis, D. (2019). Smart farming applications of machine learning. Current Robotics Reports, 3(1), 43-56.