Agricultural Based Decisions: AGRODEC Web Application

Abstract

Farmers no longer have to travel large distances in order to obtain agricultural knowledge. With agriculture playing such a vital role as a source of income in one of the world\'s most populated countries, making the lives of farmers easier is a must. India is the world\'s largest producer of pulses (25 percent of global output), consumer (27 percent of global consumption), and importer (25 percent of worldwide imports) (14 percent). As these data show, agriculture contributes a significant portion of our country\'s GDP. As a result, AGRODEC acts as a reference for farmers, advising them on which crops would be most beneficial at certain seasons of the year and soil pH levels.

Introduction

I. INTRODUCTION

In today’s Technology driven world everyone is utilizing technology for their development then why agriculture should fall behind. To close the gap between technology and farmers AGRODEC acts as a bridge so that farmers can make the most out of the harvest. As we know today's climatic conditions are changing rapidly and farmers cannot keep track of it, so AGRODEC predicts the crop which is best suited for the farm based on present day soil parameters. We take a few parameters as input and send it to the model for it to predict the crop. Thus the crop is suited for the  soil and will give more harvest as compared to the crop harvested in the farm which has been sowed from ancestors as a tradition.

AGRODEC visualizes the rainfall of the past 10 years so that farmers can get the idea of what exactly can be expected in the monsoon season and be prepared with necessary resources for saving the crop.

This system also gives a statistical approach to the farmers' crop sale made in a year, to understand which crop is more beneficial and which one is not. Also, Indian agricultural land percentage is also displayed so that researchers and agricultural students can focus on the unirrigated land and can take necessary steps to make that land productive.

II. SOFTWARE

A. Crop Prediction

Precision agriculture is very popular these days. Precision agriculture is a modern agricultural technology that analyses data such as soil characteristics, soil types, crop production data, and meteorological conditions to recommend the best crop for maximum yield and profit to farmers. Farmers will be able to make more informed decisions about their farming approach with this technique. Predicting the best crop for cultivation is an important component of agriculture, and machine learning algorithms have become increasingly important in such precisions in the  recent years.

The overall procedure of the crop prediction model is depicted in Figure 1. The input data, i.e. the dataset, is initially pre-processed to discover missing values, remove redundant data, and standardize the data. The data is then trained for the model once it has been preprocessed. Using the sklearn library, the dataset is separated into training and test data.

After the dataset has been partitioned, the crop prediction model is built using a variety of machine learning algorithms. For the prediction, the algorithm with the highest accuracy is used. As a result, after preprocessing the data, the model was trained into a training set using the Random Forest Classifier technique.

B. Data Visualization

Data visualization is the graphical representation of information and data. By using visual elements like charts, graphs, and maps, data visualization tools provide an accessible way to see and understand trends, outliers, and patterns in data.

AGRODEC uses data visualization to show the user about the real time data analysis of Rainfall which has occurred over the past years, it also gives a brief description of the crop sales done in a year through bar charts and Pie charts.

C. Rainfall Analysis

Rainfall is a very important segment of the farming industry, therefore AGRODEC uses the dataset which contains rainfall that occurred over the past years to analyze the amount of rainfall occurring in each state of India. 

We have used data visualization to show the rainfall occurring in each state in those particular years, which can be used for gathering resources to save the crop from excessive rain or various strategies can be adopted for excessive or less monsoon rain.

V. ACKNOWLEDGEMENTS

We would like to express our gratitude to our teacher, Prof. Amol Dande as well as our Principal Dr.Ravande who gave us this golden opportunity to work on this Project ‘AGRODEC’ which has helped us in developing our skills in various fields like Web Application using Machine Learning and Streamlit . Last but not the least we would like to thank our parents and our friends who helped in the development and completion of this Project.

VI. FUTURE ENHANCEMENTS

1. We will implement the project in the form of web application, application and website so it can be utilized by all.
2. We want to implement this in all native languages.
3. We want to bring all agricultural students and farmers together with the use of this technology for the betterment of farming.
4. Crop prediction with more accuracy and updated dataset.
5. Rainfall prediction so that farmers can grow the required crop accordingly.
6. Price Prediction of the crop, which focuses on farmer benefit and consumer benefit as well.

Conclusion

The proposed framework gives farmers a help to decide which crop will produce the maximum benefit based on soil’s present conditions. We aim to bring agricultural students and farmers together so they both can help each other in better understanding the soil and crops. We aim to make all the agricultural land in India into cultivating land as most of the agricultural land is not used properly, so by highlighting the region and taking help of researchers we can turn that land into cultivating land. We have listed agricultural research centers by using Map and pinpoint locations of the states in India. A farmer can contact them with a phone call and can get his/her doubts cleared regarding the soil or crops. Last but not the least, we have given farmers a tool to visualize what earning and Investment has been made in a year on the crop so they can understand more about the crop being harvested. A small quiz to get to know the crop completely so if no resources are available then also the user should know few details about the crop.

References

[1] Girish L, Gangadhar S, Bharath T R, Balaji K S, Abhishek K T “Crop Yield and Rainfall Prediction in Tumakuru District using Machine Learning”. [2] R. Katarya, A. Raturi, A. Mehndiratta and A. Thapp, \"Impact of Machine Learning Techniques in Precision Agriculture,\" 2020 3rd International Conference on Emerging Technologies in Computer Engineering: Machine Learning and Internet of Things (ICETCE), 2020, pp. 1-6, doi: 10.1109/ICETCE48199.2020.9091741. [3] Doshi, Aastha and Anuradha Chopade. “Predictive Agriculture Using Data Analysis and Machine Learning.” (2021). [4] C. N. Vanitha, N. Archana and R. Sowmiya, \"Agriculture Analysis Using Data Mining And Machine Learning Techniques,\" 2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS), 2019, pp. 984-990, doi: 10.1109/ICACCS.2019.8728382. [5] R. Medar, V. S. Rajpurohit and S. Shweta, \"Crop Yield Prediction using Machine Learning Techniques,\" 2019 IEEE 5th International Conference for Convergence in Technology (I2CT), 2019, pp. 1-5, doi: 10.1109/I2CT45611.2019.9033611. [6] Dash, Yajnaseni, Saroj K. Mishra, and Bijaya K. Panigrahi. \"Rainfall prediction for the Kerala state of India using artificial intelligence approaches.\" Computers & Electrical Engineering 70 (2018): 66-73. [7] Singh, Gurpreet, and Deepak Kumar. \"Hybrid Prediction Models for Rainfall Forecasting.\" 2019 9th International Conference on Cloud Computing, Data Science & Engineering (Confluence). IEEE, 2019. [8] Kaushik Dutta, Gouthaman. P .”Rainfall Prediction using Machine Learning and Neural Network.” International Journal of Recent Technology and Engineering (IJRTE) ISSN: 2277-3878, Volume-9 Issue-1, May 2020. [9] Moulana Mohammed, Roshitha Kolapalli, Niharika Golla, Siva Sai Maturi. ”Prediction Of Rainfall Using Machine Learning Techniques.” INTERNATIONAL JOURNAL OF SCIENTIFIC & TECHNOLOGY RESEARCH VOLUME 9, ISSUE 01, JANUARY 2020. [10] Prof. D.S. Zingade ,Omkar Buchade ,Nilesh Mehta ,Shubham Ghodekar ,Chandan Mehta “Crop Prediction System using Machine Learning”. [11] Ashwani kumar Kushwaha, Swetabhattachrya “crop yield prediction using agro algorithm in hatoop”. [12] Girish L, Gangadhar S, Bharath T R, Balaji K S, Abhishek K T “Crop Yield and Rainfall Prediction in Tumakuru District using Machine Learning”. [13] Rahul Katarya, Ashutosh Raturi, Abhinav Mehndiratta, Abhinav Thapper “Impact of Machine Learning Techniques in Precision Agriculture”. [14] Pijush Samui, Venkata Ravibabu Mandla, Arun Krishna and Tarun Teja “Prediction of Rainfall Using Support Vector Machine and Relevance Vector Machine”. [15] Himani Sharma, Sunil Kumar “A Survey on Decision Tree Algorithms of Classification in Data Mining”. [7] Pavan Patil, Virendra Panpatil, Prof. Shrikant Kokate “Crop Prediction System using Machine Learning Algorithms”.

Copyright

Copyright © 2022 Rupeshwar Maheshwar Rao, Priyanka Udaynath Jha, Riya Anushil Goyal, Amol Dande. 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.