E-Agri Kit Using Deep Learning and Machine Learning

Abstract

For farmers major challenge is getting high production with higher yield due to improper guidance of getting higher yield and crops with different diseases. In the proposed method web application is prepared using Django framework.Our paper presents an agriculture aid application which is developed and designed to help the farmers. As Agriculture was the key development inthe rise of sedentary human civilization, whereby farming of domesticated species created food surpluses that enabled people to live in cities. And it will be difficult for a person to identify every crop just by lookingat the leaves and along with that selling the crop for suitable and affordable prices is difficult to a farmer. We there overcomes this all problems we create an application where we are developing an algorithm that detects thetypeofcropbygivingtheinputimageand also creating a platform where an investor can invest into a crop by funding into a crop which is given by a farmer and where farmer can sell their crops to buyers with the rates that which are suitable with the crop.

Introduction

The text explains that agriculture faces major challenges such as unpredictable weather, crop diseases, poor soil quality, and limited farmer expertise, leading to reduced productivity—especially for small-scale farmers relying on traditional methods. These conventional practices are often slow and inaccurate, making them insufficient for modern agricultural needs.

Advancements in Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL)—particularly Convolutional Neural Networks (CNNs)—offer effective solutions for crop identification, disease detection, and yield prediction using image and environmental data. However, existing tools are limited, as they usually focus only on disease detection and lack integrated support for farmers, including market access and financial assistance.

To address these gaps, the proposed E-Agri Kit is an all-in-one platform that combines crop diagnosis, decision support, market connectivity, and investment opportunities. Farmers can upload leaf images for disease detection, receive fertilizer recommendations, and predict crop yield. The system also includes a marketplace for direct selling to buyers and an investment module that connects farmers with potential investors.

The literature survey highlights key advancements such as data augmentation (e.g., LeafGAN), hybrid CNN-transformer models, efficient lightweight models for mobile use, and the importance of feature optimization for real-time performance. It also emphasizes challenges like dataset bias, lack of real-world data, and the need for explainable and deployable systems.

The proposed system consists of four modules—Admin, Farmer, Investor, and Buyer—each providing specific functionalities like profile management, crop monitoring, funding, and trading. Overall, the E-Agri Kit aims to bridge the gap between traditional farming and digital agriculture by improving crop health, increasing productivity, reducing losses, and enabling better economic outcomes through smart, integrated, and accessible technology.

Conclusion

This user-friendly application is prepared to help different users from farming filed. Proposed web application helps for farmers, investors and buyers to easily access the application and improve the growth. This proposed application has 4 modules as system module, investor module, farmer module, buyer module. System module has different features such as approval of different users, Get information from investor, check information received, Automatic Disease prediction using DL, Crop yield Logout. Investor module has below features as View crop information, View farmer messages ,View funds.

References

[1] Salka,T.D.,Hanafi,M.B.,Rahman,S. M. S. A. A., et al., “Plant leaf disease detection and classification using convolution neural networks model: a review,” Artificial Intelligence Review,vol.58,articleno.322,2025.SpringerLink [2] Shettigere Krishna, M., Machado, P., Otuka, R. I., Yahaya, S. W., dos Santos, F. N., &Ihianle, I. K., “Plant Leaf Disease Detection Using Deep Learning: A Multi-DatasetApproach,”MDPI,2025.MDPI [3] Hamed,B.S.,Hussein,M.M.,&Mousa,A. M., “Plant Disease Detection Using Deep Learning,” International Journal of Intelligent Systems and Applications (IJISA),Vol.15,No.6,pp.38–50,2023.MECS Press+1 [4] Ullah, N., Khan, J. A., Almakdi, S., Alshehri, M. S., Al Qathrady, M., El- Rashidy, N., El-Sappagh, S., & Ali, F.,“An effective approach for plant leaf diseases classification based on a novel DeepPlantNetdeeplearningmodel,”FrontiersinPlantScience,2023.Frontiers [5] Thakur, P. S., Khanna, P., Sheorey, T., & Ojha, A., “Explainable vision transformer enabled convolutional neural network for plant disease identification: PlantXViT,” preprint (arXiv), 2022. arXiv [6] Nandi, R. N., Palash, A. H., Siddique, N., &Zilani, M. G., “Device-friendly Guava fruit and leaf disease detection using deep learning,” preprint (arXiv), 2022. arXiv [7] Tugrul, B., Elfatimi, E., &Eryigit, R., “Convolutional Neural Networks in DetectionofPlantLeafDiseases:A Review,”Agriculture,vol.12,no.8,1192, 2022.MDPI [8] Shoaib,M.,Shah,B.,El-Sappagh,S.,Ali, A., Ullah, A., Alenezi, F., Gechev, T., & Hussain, T., “An advanced deep learning models-based plant disease detection: A review of recent research,” Frontiers in Plant Science, 2023. Frontiers [9] Kolluri, J., Dash, S. K., & Das, R., “Plant Disease Identification Based on Multimodal Learning,” International Journal of Intelligent Systems and ApplicationsinEngineering,2024.IJISAE [10] “LeafGAN: An Effective Data Augmentation Method for Practical Plant Disease Diagnosis,” Cap, Q. H., Uga, H., Kagiwada, S., &Iyatomi, H., preprint (arXiv), 2020.

Copyright

Copyright © 2026 Dr. K. Rajendra Prasad, Alampally Ramadevi, Pani Renuka, Chittela Poojitha. 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.