Sheti Mitra - An Interactive System to Predict Crop Yield Along with Profit and Loss to Help Farmers Using Machine Learning

Abstract

Agriculture plays a crucial role in the economic development of many countries, especially where farming is the primary source of livelihood. Farmers often face difficulties in selecting suitable crops, predicting crop yield, identifying plant diseases at an early stage, and estimating financial outcomes such as profit or loss. To address these challenges, this study presents Sheti Mitra, an interactive machine learning–based system designed to assist farmers in making informed agricultural decisions. The proposed system integrates crop recommendation, crop yield prediction, and plant disease detection into a single platform. The system utilizes image processing and deep learning techniques to detect diseases from leaf images using Convolutional Neural Networks (CNN), while crop recommendation and yield prediction are performed using machine learning algorithms such as Random Forest. Environmental parameters including soil nutrients, temperature, humidity, and rainfall are analyzed to determine the most suitable crop and estimate expected yield. Additionally, the system provides an estimation of profit or loss based on predicted yield and crop market factors, helping farmers plan their agricultural activities effectively. A web-based interface built using HTML, CSS, and JavaScript interacts with a Flask-based backend that processes user inputs and generates predictions using trained models. By combining disease detection with crop and yield prediction, the proposed system offers a comprehensive decision-support tool for farmers. The implementation demonstrates that machine learning techniques can significantly improve agricultural productivity and reduce risks associated with crop selection and disease management. This system aims to support smart farming practices and promote sustainable agricultural development.

Introduction

Agriculture is vital for the global economy and food security, but farmers face challenges such as climate change, soil degradation, pests, plant diseases, and unstable market prices. To address these issues, the proposed system integrates machine learning and deep learning to support data-driven farming decisions. Technologies like Random Forest and Convolutional Neural Networks (CNNs) are used to provide crop recommendation, crop yield prediction, plant disease detection, and profit–loss estimation in a single intelligent platform.

Machine learning models analyze environmental factors such as soil nutrients, temperature, rainfall, humidity, and pH to recommend suitable crops and predict yield. Deep learning techniques, especially CNNs, are used for automated plant disease detection from leaf images. This helps in early identification of diseases, reducing crop damage and losses. The system also estimates potential financial outcomes by combining predicted yield with market trends.

The problem statement highlights that many farmers rely on traditional methods, lack technological support, and do not have access to integrated systems that combine crop recommendation, disease detection, yield prediction, and financial analysis. Existing systems usually focus on only one of these aspects, creating the need for a unified solution.

The objectives of the project include developing an intelligent system for crop recommendation, yield prediction, early disease detection, and profit–loss estimation using machine learning techniques.

The literature survey reviews important research in plant disease detection using deep learning. Studies show that CNN-based models achieve very high accuracy (around 99%) in classifying plant diseases. Recent research also focuses on lightweight models for edge devices, enabling real-time disease detection in agricultural fields.

The proposed system, named “Sheti Mitra”, is a web-based decision-support platform developed using HTML, CSS, JavaScript, and Flask. It allows farmers to input environmental data and upload leaf images. The system uses machine learning models for crop recommendation and yield prediction, and CNNs for disease detection. Data preprocessing and feature scaling improve model performance. Overall, the system aims to improve agricultural productivity, reduce financial risk, and support sustainable farming through an integrated intelligent solution.

Conclusion

The proposed system “Sheti Mitra – An Interactive System to Predict Crop Yield Along with Profit and Loss to Help Farmers Using Machine Learning” demonstrates how modern machine learning and deep learning technologies can be effectively applied to support smart agricultural practices. The system integrates multiple functionalities such as crop recommendation, crop yield prediction, and plant disease detection into a single interactive web-based platform. By analyzing environmental parameters including soil nutrients, temperature, humidity, rainfall, and soil pH, the system is capable of recommending the most suitable crop and predicting the expected crop yield using machine learning algorithms such as Random Forest. In addition, the plant disease detection module utilizes Convolutional Neural Networks to accurately identify diseases from leaf images and provide appropriate treatment suggestions to farmers. The implementation results show that the system can provide reliable predictions with high accuracy, enabling farmers to make better agricultural decisions and reduce potential crop losses. Furthermore, the user- friendly interface ensures that farmers can easily access the system and obtain real-time insights without requiring technical expertise. Overall, the proposed system contributes to improving agricultural productivity, supporting data-driven farming practices, and helping farmers estimate potential profit or loss before cultivation, thereby promoting more efficient and sustainable agricultural management.

References

[1] Shawon, S. M., et al., “Crop Yield Prediction Using Machine Learning: An Extensive Review,” Smart Agricultural Technology, 2024. [2] Jabed, M. A., et al., “Crop Yield Prediction in Agriculture Using Machine Learning and Deep Learning: A Systematic Review,” Heliyon, 2024. [3] Nikhil, U. V., et al., “Machine Learning-Based Crop Yield Prediction Using Weather and Soil Data,” Computers, 2024. [4] Rastogi, P., et al., “Early Disease Detection in Plants Using Convolutional Neural Networks,” Procedia Computer Science, 2024. [5] Sajitha, P., et al., “A Review of Machine Learning and Deep Learning Techniques for Plant Disease Detection,” Artificial Intelligence in Agriculture, 2024. [6] Trivedi, P., et al., “Plant Leaf Disease Detection and Classification Using Deep Learning Models,” Open Agriculture Journal, 2024. [7] Hukkeri, G. S., et al., “Classification of Various Plant Leaf Diseases Using EfficientNet Architecture,” Open Agriculture Journal, 2024. [8] Iftikhar, M., et al., “Plant Disease Management Using Enhanced CNN Models,” Artificial Intelligence Review, 2024. [9] Cho, O. H., “Evaluation of Machine Learning Approaches for Detecting Leaf Diseases in Agriculture,” Legume Research, 2024. [10] Agarwal, J., et al., “Plant Disease Detection Using Convolutional Neural Networks,” 2024. [11] Rahman, K. N., et al., “Real-Time Monitoring System for Plant Leaf Disease Detection Using Deep Learning,” Smart Agricultural Systems, 2025. [12] Lionel, B. M., et al., “Comparative Study of Machine Learning Models for Crop Yield Prediction,” Springer Agriculture Journal, 2025. [13] Hernández, G. C., et al., “Predictive Models Based on Artificial Intelligence for Crop Yield Estimation,” Agriculture (MDPI), 2025. [14] Saha, S., et al., “Precision Agriculture for Improving Crop Yield Predictions Using Machine Learning,” Frontiers in Agronomy, 2025. [15] Fariz, T. K. N., et al., “Hybrid Artificial Intelligence Model for Crop Yield Prediction,” Smart Agriculture Technology, 2025. [16] Kheir, A. M. S., et al., “Smart Plant Disease Diagnosis Using Multiple Deep Learning Models,” Artificial Intelligence in Agriculture, 2025. [17] Yasin, K., et al., “Deep Learning Architectures for Plant Disease Detection: A Comprehensive Review,” Plant Science Journal, 2025. [18] Devarajan, D., et al., “AI-Based Real-Time Plant Disease Diagnosis Using Deep Learning,” Plant Methods, 2026. [19] Yan, Y., et al., “Crop Yield Time-Series Prediction Using Hybrid Machine Learning Models,” 2025. [20] Yewle, A. D., et al., “Multi-Modal Data Fusion and Deep Ensemble Learning for Crop Yield Prediction,” 2025. [21] Gupta, A., et al., “Agri-GNN: Graph Neural Network Framework for Crop Yield Prediction,” 2023. [22] Mena, F., et al., “Adaptive Fusion of Multi-View Remote Sensing Data for Crop Yield Prediction,” 2024. [23] Patidar, S., et al., “Crop Yield Prediction Using Machine Learning Techniques,” Agricultural Informatics Journal, 2023. [24] Mohanty, S. P., Hughes, D., and Salathé, M., “Using Deep Learning for Image-Based Plant Disease Detection,” Frontiers in Plant Science. [25] Kamilaris, A., and Prenafeta-Boldú, F., “Deep Learning in Agriculture: A Survey,” Computers and Electronics in Agriculture. [26] Liakos, K. G., et al., “Machine Learning in Agriculture: A Review,” Sensors Journal. [27] Jeong, J. H., et al., “Random Forest-Based Crop Yield Prediction Model Using Climate Data,” Agricultural Systems. [28] Zhang, S., et al., “Deep Learning-Based Plant Disease Detection Using Leaf Images,” IEEE Access. [29] Hossain, M. S., et al., “Deep Convolutional Neural Networks for Plant Disease Recognition,” Computers and Electronics in Agriculture. [30] Ghosal, S., et al., “Automated Plant Disease Detection Using Deep Learning,” Plant Methods.

Copyright

Copyright © 2026 Bangar Sakshi Laxman, Bangar Shraddha Prabhakar, Chaudhari Sanika Sampat, Prof. Thorat Sonam. 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.