Abstract

Agricultural industry plays a major role in the process of economic

development as well as the Gross Domestic Product of India. The lack of scientific
approaches to soil fertility has become a major challenge for the industry. Since
most of the farmers are not familiar with the concepts of soil nutrients, they tend to
start their cultivations by assuming myths and assumptions. The project aims at
suggesting the best crop based on the soil fertility and also recommends a fertilizer
plan to minimize the amount of fertilizers that are needed. The project developed a
cross- platform web application to suggest the best crops according to available
soil fertility. Further, a fertilizer plan will be suggested on the basis of the contents
of NPK Nitrogen (N), Phosphorus (P) and Potassium (K) values to optimize
fertilizer usage in order to increase profitability and avoid soil degradation.

Keywords: Crop Recommendation, Fertilizer Recommendation, Machine

Learning, Agriculture.

Introduction
Farming is one of the major sectors that influences a country’s economic
growth.

In countries like India, the majority of the population is dependent on

agriculture for their livelihood. Many new technologies, such as Machine
Learning and Deep Learning, are being implemented into agriculture so that
it is easier for farmers to grow and maximize their yield.

In this project, I present a website in which the following applications are

implemented; Crop recommendation and Fertilizer recommendation
respectively.

1. In the crop recommendation application, the user can provide the soil
data from their side and the application will predict which crop should
the user grow.
2. For the fertilizer recommendation application, the user can input the
soil data and the type of crop they are growing, and the application
will predict what the soil lacks or has excess of and will recommend
improvements.

Literature Survey
Sr. No. Title & year Author Description Advantage

In this paper, we
have proposed a
model that can
Soil Classification
using Machine Sk Al Zaminur predict soil series
Rahman, with land type and Easy to use
Learning Methods
Kaushik according to and Time
1. and Crop Chandra Mitra, prediction it can consuming.
Suggestion Based S.M. Mohidul
suggest suitable
on Soil Series Islam
crops. Using
(2018)
Machine learning
Algorithms.

By using an
automated system
implementing
Automated Soil machine vision,
Classification and M van Rooyen, more accurate Easy to use and
2. Identification Using N Luwes, results can be Time
Machine Vision ( E Theron achieved and test consuming.
2017 ) durations can be
decreased dramati-
cally.

In Rajasthan there
are various types of
soil available:
Soil Classification sandy, saline,
Hemant
& Characterization alkaline, calcareous Easy to use and
Kumar
3. Using Image soil are also Time
Sharma,
Processing present, we can consuming.
Shiv Kumar
(2018) classify the soil by
image processing
method in which
we can see the
 color, energy, HSV
etc.
.
This paper explains
support vector
machine based
classification of the
Performance of
soil types. Soil
SVM Classifier Sunitha.k , Easy to use and
classification
4. For Image Based Dr.S.Padmav Time
includes steps like
Soil Classification ati consuming.
image acquisition,
(2016)
image
preprocessing,
feature extraction
and classification
Motivation:
India is a nation in which agriculture plays a prime role. The prosperity of
the farmers prospers the nation. Thus our system would help farmers in
sowing the right seeds based on soil requirements to increase productivity
and acquire profit. As a result, farmers can plant the right crop that will
increase the yield and also increase the overall productivity of the nation.
Agricultural productivity mainly depends upon the soil condition which in
turn depends upon nutrients present in the soil. Based on soil analysis,
crops should be recommended to the farmers to increase crop productivity
and in turn, increase the financial status of the farmers. Also, farmers face
huge losses due to wrong fertilizer uses, we are also building fertilizer
recommendation systems which will help farmers choose the right fertilizer.

Objectives:
● Agriculture is a business with risk and reliable crop yield prediction is
vital for decisions related to agriculture risk management.

● The vision of meeting the world's food demands for the increasing
population throughout the world is becoming more important in these
recent years.

● Eventually, it helps in achieving ZERO hunger.

● Predictions could be used by crop managers to minimize losses when

unfavorable conditions may occur.

Problem Statement:
Currently there is no such a system to find out crops and their disease so
farmers get lost in farming and there is not a proper gaudiness to farmer to
take which crop in that weather. Our system will easily find out the crop by
using image processing concepts and machine learning concepts. We are
collecting soil data sets to find crops.

Proposed System:
The aim of the proposed system is to help farmers to cultivate crops for
better yield. The crops selected in this work are based on important crops
from selected locations.

The selected crops are Rice, Jowar, Wheat, Soyabean, and Sunflower,
Cotton, Sugarcane, Tobacco, Onion, Dry Chili etc.

There are 2 process in proposed work:

● Crop Yield Prediction: Crop Yield Prediction can be done using crop
yield data, nutrients and location data. These inputs are passed to
Random Forest and Support Vector Machine algorithms. These
algorithms will predict crops based on present inputs.
● Fertilizer Recommendation: Fertilizer Recommendation can be done
using fertilizer data, crop and location data. In this part suitable crops
and required fertilizer for each crop is recommended.

Third Party applications are used to get Weather information, Temperature

information as well as Humidity and rainfall.

Dataset :
Crop Recommendation Dataset -
This dataset was built by augmenting datasets of rainfall, climate
and fertilizer data available for India.
Data fields -
● N - ratio of Nitrogen content in soil
● P - ratio of Phosphorus content in soil
● K - ratio of Potassium content in soil
● temperature - temperature in degree Celsius
● humidity - relative humidity in %
● ph - ph value of the soil
● rainfall - rainfall in mm

Methodology:
1. Decision Tree:
● The Decision Tree algorithm belongs to the family of supervised
learning algorithms. The goal of using a Decision Tree is to create
a training model that can be used to predict the class or value of the
target variable by learning simple decision rules inferred from prior
data(training data).
● Accuracy is 90.0 %
2. Gaussian Naive Bayes :
● Gaussian Naive Bayes is a variant of Naive Bayes that follows
Gaussian normal distribution and supports continuous data.
● Naive Bayes are a group of supervised machine learning
classification algorithms based on the Bayes theorem.
● Accuracy is 99.09 %

3. Logistic Regression:
● Logistic regression is basically a supervised classification
algorithm. In a classification problem, the target variable(or
output), y, can take only discrete values for a given set of
features(or inputs), X.
● Accuracy is 95.22 %

SOFTWARE AND HARDWARE REQUIREMENTS:

Software requirement:-
Sr.No Software Component Details(Technical details with Purpose)
.
1 Operating System 64bit Windows 10 and on words
2 Technology Python
3 IDE Spyder
4 Database DBSqlite

Hardware requirement:-
Sr.No Component Details(Technical details with Purpose)
.
1 System Processor Core2Duo
2 Hard Disk 150GB
3 Speed 2.4 GHz

Action Plan:
Work Task Description Duration
Literature Search Related work done for conceptual 6 weeks
data similarity
System analysis Critical analysis and comparison of 4 weeks
technologies studied and results
achieved in research
Design and Planning Modeling and design and dataset 8 weeks
searching or creation
Implementation Divided into phases
Phase A Implementation module 1 2 weeks
Phase B Implementation module 2 2 weeks
Phase C Implementation module 3 3 weeks
Phase D Implementation module 4 4 weeks
System Testing Test system quality, fix errors if any 3 weeks
and
improve if needed. Test system for
differ-
ent datasets
Intial Report Prepare and upload Initial Report 2 weeks
Final Report Prepare and upload Initial Report 2 weeks
Project Plan Execution:
Applications:
● We will use this system in Farming. This will help farmers to predict the
crop with respect to the soil.

● Farmers can also get what Fertilizer to choose.

Conclusion:
This project highlighted the limitations of current systems and their practical
usage on yield prediction. Then walks through a viable yield prediction
system to the farmers, a proposed system provides connectivity to farmers
via a web application. The web application includes multiple features that
users can leverage for the selection of a crop. The inbuilt predictor system
helps the farmers to predict the yield of a given crop. The inbuilt
recommender system allows a user exploration of the possible crops and
their yield to make more educated decisions. For yield to accuracy, various
machine learning algorithms such as Decision Tree, Gaussian Naive
Bayes, Logistic Regression, Random Forest, XGBoost were implemented
and tested on the given datasets. Results indicate that XGBoost gives the
best result.

References:

[1] S. M. PANDE, P. K. RAMESH, A. ANMOL, B. R. AISHWARYA, K.

ROHILLA and K. SHAURYA, "Crop Recommender System Using Machine
Learning Approach," 2021
[2] S. Bhanumathi, M. Vineeth and N. Rohit, "Crop Yield Prediction and
Efficient use of Fertilizers," 2020

[3] C. P. Wickramasinghe, P. L. N. Lakshitha, H. P. H. S. Hemapriya, A.

Jayakody and P. G. N. S. Ranasinghe, "Smart Crop and Fertilizer
Prediction System," 2019

[4] Arun Kumar, Naveen Kumar, Vishal Vats, “Efficient Crop Yield
Prediction Using Machine Learning Algorithms”, International Research
Journal of Engineering and Technology (IRJET)- e-ISSN: 2395-0056,
pISSN:2395-0072, Volume: 05 Issue: 06 | June-2018

[5] Nithin Singh & saurabh chaturvedi, “Weather Forecasting Using

Machine Learning”, 2019 International Conference on Signal Processing
and Communication (ICSC) Volume: 05 | DEC-2019.

[6] Aakash Parmar & Mithila Sompura, "Rainfall Prediction using Machine
Learning", 2017 International Conference on (ICIIECS) at Coimbatore
Volume: 3 | March 2017.

[7] Sachee Nene & Priya, R “Prediction of Crop yield using Machine
Learning”, International Research Journal of Engineering and Technology
(IRJET) Volume: 05 Issue: 02 | Feb-2018.

[8] Ramesh Medar & Anand M. Ambekar, “Sugarcane Crop prediction

Using Supervised Machine Learning" published in International Journal of
Intelligent Systems and Applications Volume: 3 | August 2019.