Crop Recommendation and Yield Prediction Based on Geographical Location with Web Interface

Abstract

Agriculture is crucial in maintaining the global economy and food security. Yet, farmers sometimes have difficulty choosing the most appropriate crops and estimating yield prospects because of the varying climatic conditions, soil types, and availability of resources. This project seeks to overcome this difficulty through designing an internet-based intelligent crop recommendation and yield prediction system using geographical location information. The system involves integrating machine learning algorithms with geospatial information to study environmental factors like soil, temperature, rain, and humidity. By using past agricultural data and current weather inputs, the model prescribes best crops based on geographical locations and forecasted yields. The system is implemented via a simple web-based interface, through which farmers and stakeholders can feed location-specific inputs and receive insights immediately. This methodology not only improves farmers\' decision-making but also helps in precision agriculture, optimization of resources, and sustainable farming. The modular design provides scalability and flexibility to accommodate various regions and crops, thus making the system a valuable instrument in contemporary agritech solutions.

Introduction

Agriculture remains a vital economic sector, especially in developing countries, but conventional farming faces challenges such as poor crop selection, yield instability, and climate variability. To address the increasing global food demand and promote sustainable farming, this project develops a smart system that suggests optimal crops and predicts yields based on geographical and environmental data, accessible through a user-friendly web interface.

The system integrates data science, machine learning, and web development, using inputs like soil nutrients, weather conditions, and location to provide farmers with tailored crop recommendations and yield forecasts. This empowers farmers to make informed decisions, reduce costs, improve productivity, and minimize environmental harm.

Literature Review:
Various studies have employed machine learning algorithms (Decision Trees, Random Forest, SVM, LSTM) and IoT sensors to build crop recommendation and yield prediction systems, highlighting the importance of real-time data, geospatial information, and regional customization.

Proposed Methodology:
The system includes modules for user input and geolocation retrieval, data preprocessing, crop recommendation via supervised ML models (with Random Forest performing best), yield prediction using regression models (XGBoost/Linear Regression), and a responsive web interface built with Flask and ReactJS. Feature extraction and model deployment use cloud-based, containerized environments for scalability and continuous learning.

Results:
The web application successfully predicts crop yields and recommends suitable crops based on environmental parameters. Sample outputs demonstrate accurate yield forecasting and effective crop suggestions (e.g., muskmelon), proving the system’s practical utility for farmers and agricultural planners.

Conclusion

In this work, an overall scheme for smart crop suggestion and yield estimation was presented and applied successfully using machine learning techniques within a web-based application that is easy to use. The system uses major agriculture-related parameters like temperature, rainfall, nutrients in the soil, and pesticide application combined with geospatial data to suggest results and predictions accurately. By utilizing actual-world datasets and leveraging efficient preprocessing and model training strategies, the system provides accurate results that can considerably benefit farmers and agricultural planners to make well-informed decisions.The bi-functional capability of crop suggestion and yield prediction enables users to choose the most ideal crop for cultivation and estimate the probable output based on environmental as well as geographical conditions. The application of the model on a web-based system provides ease of access, scalability, and real-time usage, making it a viable answer to the needs of current agriculture. The visual interfaces provide more ease of interaction and minimize the complexity involved with data-based systems.Future development could also involve integrating real-time weather APIs, satellite data, and geographically specific soil testing results to further enhance the accuracy of the system. Including multilingual capability and mobile usability would also render the system farmer-friendly. On the whole, the system outlined here offers a worthwhile step towards precision agriculture and sustainable farming methods

References

[1] R. K. Jadhav, P. P. Malkar, and A. V. Khandekar, “Crop yield prediction using machine learning algorithms,” in 2021 6th International Conference for Convergence in Technology (I2CT), IEEE, pp. 1–4 [2] K. M. Patil and R. Kumar, “Recommendation of crop yield using machine learning algorithms,” International Journal of Engineering Research & Technology (IJERT), vol. 9, no. 5, pp. 352–356, 2020. [3] D. Bhagat, A. Patil, and S. Bakale, “Agriculture crop prediction using machine learning: A review,” in 2019 IEEE International Conference on Smart Structures and Systems (ICSSS), pp. 1–3 [4] S. B. Patil and B. S. Thorat, “Early detection of pests using image processing and IoT for agricultural crops,” in 2019 International Conference on Communication and Electronics Systems (ICCES), IEEE, pp. 1–6 [5] A. Singh and A. Jain, “Crop yield prediction and efficient use of fertilizers,” International Journal of Scientific & Engineering Research, vol. 9, no. 5, pp. 188–192, 2018 [6] A. D. Shirsath and S. K. Mungmode, “Machine learning approach for crop recommendation,” in 2020 International Conference on Emerging Smart Computing and Informatics (ESCI), IEEE, pp. 488–491 [7] N. V. Chavan and S. N. Deshmukh, “Web based crop recommendation system using machine learning approach,” International Research Journal of Engineering and Technology (IRJET), vol. 7, no. 6, pp. 2341–2346, 2020. [8] A. Tripathi and M. J. Sinha, “Crop prediction using machine learning approach,” in 2018 International Conference on Computing, Power and Communication Technologies (GUCON), IEEE, pp. 750–753. [9] M. Jadhav, P. Jadhav, and N. Mohite, “Smart farming using web technologies and machine learning,” International Journal of Computer Applications, vol. 975, no. 8887, pp. 36–40, 2019 [10] P. P. Raut and M. A. Khan, “Crop recommendation system for precision agriculture,” in 2019 International Conference on Smart Systems and Inventive Technology (ICSSIT), IEEE, pp. 1121–1124 [11] A. Rani and A. P. Yadav, “Crop recommendation based on soil parameters using ML algorithms,” in 2021 11th International Conference on Cloud Computing, Data Science & Engineering (Confluence), IEEE, pp. 548–553. [12] R. S. Garge and S. A. Aher, “Soil nutrient based crop prediction using decision tree,” International Journal of Innovative Research in Computer and Communication Engineering, vol. 6, no. 4, pp. 4753–4757, 201

Copyright

Copyright © 2025 Dundigalla Sai Satvik, Degala Sri Ram, Perrumalla Akhilesh, K. Victor. 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.