Crop Yield Prediction and Recommendation System using Machine Learning

Abstract

Crop production plays a crucial role in ensuring food security and economic stability, especially in agriculture-dependent countries. However, farmers often face significant challenges due to unpredictable climatic conditions, soil variability, and lack of scientific guidance, which leads to reduced crop productivity and financial losses. To address these challenges, this project proposes an intelligent Crop Yield Prediction and Recommendation System using Machine Learning techniques. The system utilizes advanced algorithms such as Linear Regression and Random Forest to analyze agricultural data and predict crop yield based on key parameters including soil nutrients (Nitrogen, Phosphorus, Potassium), temperature, rainfall, humidity, and soil pH. Linear Regression is employed to identify relationships between environmental factors and yield, while Random Forest enhances prediction accuracy by handling non-linear patterns and complex interactions among features. The system incorporates data preprocessing techniques such as data cleaning, normalization, and feature selection to improve model performance and reliability. In addition to yield prediction, the proposed system provides crop recommendations by analyzing environmental suitability and predicts potential profit by considering market prices and production costs.

Introduction

Agriculture is highly dependent on environmental factors such as soil nutrients, weather, and climate variability, but traditional farming often lacks precise predictive tools. To address this, the proposed system uses machine learning to analyze historical and real-time agricultural data and provide data-driven recommendations.

The system collects inputs like soil NPK values, temperature, rainfall, humidity, and pH, then preprocesses and analyzes them using Linear Regression and Random Forest models. These models predict crop yield and identify suitable crops for given conditions. It also includes a profit prediction module that estimates financial returns based on yield, market prices, and cultivation costs.

A key feature is the integration of weather forecasting, which helps farmers anticipate risks like drought or excessive rainfall and plan accordingly. The system is built with a secure login and role-based access control, ensuring safe and authorized usage for farmers, administrators, and experts.

The output is presented through a user-friendly dashboard that shows crop recommendations, yield predictions, weather updates, and profit estimates. Overall, the system supports intelligent, efficient, and economically beneficial farming decisions by combining machine learning, predictive analytics, and real-time data.

Conclusion

The proposed Crop Yield Prediction and Recommendation System presents an intelligent and comprehensive solution for modern agricultural challenges by integrating machine learning techniques with environmental and economic data analysis. The system effectively utilizes parameters such as soil nutrients, temperature, rainfall, humidity, and soil pH to generate accurate crop yield predictions and recommend the most suitable crops for specific conditions, thereby supporting data-driven decision-making in agriculture. In addition to yield prediction, the inclusion of weather forecasting enables users to anticipate climatic changes and take preventive actions, reducing risks associated with unpredictable environmental factors. The system also incorporates a profit prediction module that analyzes market prices and cultivation costs, allowing farmers to evaluate the economic feasibility of crop selection and improve financial planning. The implementation of a secure login mechanism ensures controlled access and data protection, while the interactive dashboard provides a clear and organized visualization of predictions, recommendations, and analytical insights, making the system accessible even to non-technical users. Furthermore, the integration of a human-in-the-loop approach ensures that users retain full control over decision-making by allowing them to review

References

[1] Jehangir, Muhammad, et al. \"Crop yield prediction using machine learning algorithms.\" IEEE Access 8 (2020): 86802-86814. [2] Khaki, Saeed, and Lizhi Wang. \"Crop yield prediction using deep neural networks.\" Frontiers in Plant Science 10 (2019): 621. [3] Pantazi, Xanthoula E., et al. \"Precision agriculture using machine learning and deep learning techniques.\" Computers and Electronics in Agriculture 151 (2018): 63-74.. [4] Kamilaris, Andreas, and Francesc X. Prenafeta-Boldú. \"Deep learning in agriculture: A survey.\" Computers and Electronics in Agriculture 147 (2018): 70-90. [5] Rajput, D. S., et al. \"A survey on crop yield prediction using machine learning approaches.\" International Journal of Advanced Research in Computer Science 9, no. 3 (2018): 698-70 [6] Singh, Ashutosh, et al. \"Machine learning-based crop recommendation system for precision agriculture.\" IEEE International Conference on Computing, Communication and Automation (2020): 1-6. [7] Jirat Pasuksmit, Jayalakshmi, T., and A. Santhakumaran. \"Statistical normalization and feature selection techniques for crop yield prediction.\" International Journal of Computer Applications 75, no. 7 (2013): 1-5. [8] Rashina Elavarasan, D., et al. \"Crop prediction using machine learning approaches.\" IEEE International Conference on Emerging Smart Computing and Informatics (2020): 1-6. [9] Ramesh, D., and B. Vishnu Vardhan. \"Analysis of crop yield prediction using data mining techniques.\" International Journal of Computer Science and Mobile Computing 4, no. 5 (2015): 462-469. [10] Mihir Jakkaraju. \"Modeling AI-Human Weather-based crop yield prediction using machine learning.\" International Journal of Engineering Research & Technology 9, no. 5 [11] Pal, Dheeraj Sharma, A., et al. \"Soil nutrient-based crop recommendation using machine learning.\" IEEE International Conference on Intelligent Systems and Green Technology (2019): 45-50. [12] S., Bharat Misra, and C. D. Singh. \"Machine learning approach for forecasting crop yield based on climatic parameters.\" IEEE International Conference on Computer Communication and Informatics (2014): 1-5.). [13] P., et al. \"An intelligent crop recommendation system using machine learning.\" International Journal of Recent Technology and Engineering 8, no. 2 (2019): 123-128. [14] Chlingaryan, A., et al. \"Machine learning approaches for crop yield prediction and nitrogen status estimation.\" Computers and Electronics in Agriculture 151 (2018): 61-69. [15] Mo, Dutta, S., et al. \"Smart agriculture system using IoT and machine learning.\" IEEE Internet of Things Journal 8, no. 3 (2021): 1642-1653.

Copyright

Copyright © 2026 U. Mohammed Abuthahir, S. Makivasagam, S. Sangamithra. 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.