Survey on Crop Price Prediction and Recommendation Using Machine Learning and Weather Forecasting

Abstract

This document is a model and instructions for using a new farming method called \"Farming with Machine Learning\". Using regression algorithms and decision trees, farmers can be provided with clear information to make informed decisions. The main purpose of this document is to support farmers by providing powerful tools to unravel the complexities of farming, improve crop selection and improve well-managed management. Project ideas include creating a website that integrates with technology to provide farmers with a better farming experience. Based on extensive data analysis and recommendations from key meetings, this document provides guidelines for ushering in a new era of good agriculture and solving good problems.

Introduction

I. INTRODUCTION

Agriculture is the mainstay of the Indian economy and contributes to the country's gross domestic product while providing livelihoods to millions of people. However, although farmers play an important role, they still face many problems that hinder their success and limit the development of the economy.

Unpredictable weather conditions that cause erratic rainfall and extreme temperatures pose a threat to agriculture and often result in crop failure, business and financial losses for farmers. In addition, low education levels lead to further challenges as many farmers lack the knowledge and resources needed to use modern agricultural practices and technologies. In addition, the use of advanced technology faces problems due to the high cost of purchasing and using new equipment and language problems affecting access to information.

Together, these factors inhibit farmers' ability to implement new agricultural practices. In these challenges, AgriVenture acts as a beacon of hope by providing innovative solutions to meet the needs of Indian farmers. By integrating technologies such as neural networks and real-time weather data through the use of programming interfaces (APIs), AgriVenture provides farmers with predictability and intelligence.

The AgriVenture website provides farmers with access to valuable resources and tools designed to improve agriculture. The website was developed using the MERN framework (such as MySQL, Express.js, React.js and Node.js) to provide farmers with an intuitive and user-friendly platform to point and use. 

A key feature of the AgriVenture platform is the crop price prediction, which uses advanced techniques to predict market trends and help farmers to improve profits. AgriVenture enables farmers to maximize profits and reduce risks in the agricultural industry by providing real-time updates on products.

In addition, AgriVenture also provides crop recommendations that use machine learning algorithms to recommend optimal crops based on region, season and previous crops. AgriVenture aims to improve agriculture and promote permaculture practices by guiding farmers in crop selection.

Additionally, AgriVenture has integrated weather forecast APIs into its platform to provide farmers with accurate and timely information about weather conditions and future climate.

Their ability to influence crop yields. AgriVenture helps reduce and protect agriculture by helping farmers manage climate-related risks. AgriVenture enables farmers to maximize profits and reduce risks in the agricultural industry by providing real-time updates on products.

II. COMPARATIVE ANALYSIS OF EXISTING LITERATURE PAPERS

Table 1: Literature Survey Comparison

III. EXISTING SYSTEM

The current crop forecasting method in Rajasthan, India, has used various algorithms and models, but their results are questionable. Some focus on just five products and use techniques such as support vector machine (SVM), gradient descent, and short-term memory (LSTM) [1], but perhaps will not produce good results. Others use k nearest neighbour (KNN), SVM, and random forest algorithms [11], but their predictive capabilities may be limited. Additionally, some applications are limited to only 85% accuracy by focusing on small crops and using low-impact methods such as Naive Bayes, Vector Space Models (VSM), and Decision Trees [2]. Additionally, Gaussian Naive Bayes, logistic regression, and support vector machine have been used to recommend crops based on environmental factors [6], but their practical implications are still unclear.

A. Limitations of Existing Systems

1. Coverage limited to only a handful of crops, disregarding the diverse agricultural landscape of Rajasthan, India.
2. Lack of consideration for the broader regional variability in environmental conditions, potentially limiting the applicability of predictions.
3. Utilization of simplistic modelling approaches, potentially overlooking crucial factors influencing crop yields.
4. Questionable reliability and accuracy of predictions, raising doubts about the practical utility of these systems for stakeholders.

IV. PROPOSED SYSTEM

The system has been developed to integrate various machine learning technologies to improve agriculture in Maharashtra and focuses on crop price prediction, crop advice and weather forecasts. Using the power of machine learning algorithms, the system will provide farmers with better information about crop prices, helping them make informed decisions. Additionally, the system will analyze environmental information and provide recommendations for planting crops based on conditions such as soil quality and weather. Additionally, with the client's web design using the MERN (MySQL, Express.js, React.js, and Node.js) stack and Tailwind CSS for the UI, the system will become easily accessible and easy to use for farmers. Processing data from the MySQL database, the scope of the system will be limited to selected crops in the state of Maharashtra to provide effective and relevant results for urban farmers.

V. RESULT

The proposed system is evaluated using the dataset model, focusing on measurement accuracy with metrics such as confusion matrix and root mean square error (RMSE). These metrics play an important role in evaluating the performance of the forecasting model and identifying areas for improvement.

Conclusion

AgriVenture has become a major force in agricultural innovation, offering comprehensive services from crop price forecasting and weather forecasting. AgriVenture seamlessly integrates these resources to provide farmers with the necessary tools to make informed decisions, ultimately increasing yields and promoting permaculture practices. Additionally, AgriVenture empowers farmers to increase their income and solve agricultural problems with confidence by providing accurate cost estimates that support financial decisions, leading to better performance and increased income. With its innovative approach, AgriVenture has the potential to transform the agricultural landscape, empower farmers and bring prosperity to the future of agriculture. By expanding its operations across the country, AgriVenture can spread its benefits across different agricultural regions in India, grow more crops and use safer methods. Additionally, developing data that includes comprehensive climate data should improve forecast models and provide deeper insights into crops and markets. Additionally, integrating import and export data into a database can improve forecast accuracy and help farmers and policymakers make better decisions again. Through these advances, the framework aims to drive change in agricultural research, promoting sustainability and re-employment in agriculture.

References

[1] Agarwal, S. and Tarar, S., 2021. A hybrid approach for crop yield prediction using machine learning and deep learning algorithms. In Journal of Physics: Conference Series (Vol. 1714, No. 1, p. 012012). IOP Publishing. [2] Sajithabanu, S., Ponmalar, A., Soundari, A.G., Reshma, N.V., Sunraja, K. and Sindhumathi, R., 2022, December. Enhanced Crop Price Prediction and Forecasting System. In 2022 International Conference on Computer, Power and Communications (ICCPC) (pp. 580-585). IEEE. [3] Banda, L., Rai, A., Kansal, A. and Vashisth, A.K., 2023, May. Suitable Crop Prediction based on affecting parameters using Na¨?ve Bayes Classification Machine Learning Technique. In 2023 International Conference on Disruptive Technologies (ICDT) (pp. 43-46). IEEE.. [4] Raimundo, F., Gloria, A. and Sebasti ´ ao, P., 2021, May. Prediction of ˜ weather forecast for smart agriculture supported by machine learning. In 2021 IEEE World AI IoT Congress (AIIoT) (pp. 0160- 0164). IEEE. [5] Jaybhaye, N., Tatiya, P., Joshi, A., Kothari, S. and Tapkir, J., 2022, January. Farming Guru:- Machine Learning novation for Smart Farming. In 2022 4th International Conference on Smart Systems and Inventive Technology (ICSSIT) (pp. 848-851). IEEE. [6] Kusumasri, B., Srilakshmi, V., Satyavada, S. and Kiran, G.U., 2023, February. Crop Recommendation Application using Ensemble Classifiers. In 2023 2nd Edition of IEEE Delhi Section Flagship Conference (DELCON) (pp. 1-7). IEEE. [7] Kavita, M. and Mathur, P., 2020, October. Crop yield estimation in India using machine learning. In 2020 IEEE 5th International Conference on Computing Communication and Automation (ICCCA) (pp. 220-224). IEEE. [8] Kamath, P., Patil, P., Shrilatha, S. and Sowmya, S., 2021. Crop yield forecasting using data mining. Global Transitions Proceedings, 2(2), pp.402-407. [9] Mathur, P., 2021, August. Satellite-based crop yield prediction using machine learning algorithm. In 2021 Asian conference on innovation in technology (ASIANCON) (pp. 1-5). IEEE. [10] Van Klompenburg, T., Kassahun, A. and Catal, C., 2020. Crop yield prediction using machine learning: A systematic literature review. Computers and Electronics in Agriculture, 177, p.105709.tion (ICCCA) (pp. 220-224). IEEE [11] M. Gunasekaran, G. Thapaswini. A Methodology for Crop Price Prediction Using Machine Learning. 2022 IEEE 2nd International Conference on Mobile Networks and Wireless Communications (ICMNWC) [12] S. Bharghavi, Dr, Srinivasan Bagannathan, Crop Recommendation System Using Machine Learning. International Journal of Engineering Research and Technology (IJERT)

Copyright

Copyright © 2024 Sumit Done, Prajwal Jadhav, Sarthak Bornare, Tushar Dhobale, Rohan Dhalpe, Dhanashree Phalke, Dipali Kirange. 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.