SMART CROP RECOMMENDATION SYSTEM

SMART CROP RECOMMENDATION SYSTEM

Abstract— India, with its predominantly is the broadest economic sector and plays a
agrarian economy, faces significant most important role in the overall
challenges in optimizing crop selection due development of the country. More than 60%
to diverse climatic conditions, soil of the land in the country is used for
variations, and fluctuating market demands. agriculture in order to suffice the needs of
A large segment of the farming community 1.4 billion people Thus adopting new
lacks access to scientific methods and data- agriculture technologies is very important.
driven tools, resulting in suboptimal crop Current agriculture is highly dependent on
yields and economic losses. This paper technology and focuses on obtaining large
presents a machine learning-based crop profits from selected hybrid crops, which
prediction system designed to assist farmers destroy the soil's physical and biochemical
in making informed decisions about crop properties in the long run. This will be leads
selection. By analyzing parameters such as the farmers of our country towards profit.
soil composition, weather patterns,
Prior crop prediction and crop prediction
moisture levels, and historical yield data,
was performed on the basis of farmers
the system recommends the most suitable
experience on a particular location. The
crops for a given field. The integration of
crop is the significant factor contributing in
machine learning enables the identification
agricultural monetary. The crop depends on
of complex patterns and correlations,
multiple factors such as climatic,
enhancing the accuracy of predictions. This
geographic, and financial elements. It is
approach not only improves crop
difficult for farmers to decide when and
productivity and profitability but also
which crops to plant. Farmers are unaware
supports sustainable agricultural practices.
of which crop to grow, and what is the right
The study underscores the importance of
time and place to start due to uncertainty in
data science in modern farming and its
climatic conditions. They will prefer the
potential to transform traditional
prior or neighborhood or more trend crop in
agricultural methods. The system aims to
the surrounding region only for their land
empower farmers with actionable insights,
and they don't have enough of knowledge
ultimately contributing to food security and
about soil nutrients content such as
economic resilience in India.
nitrogen, phosphorus, potassium in the
I I. INTRODUCTION land. Considering all these problems takes
into the account we designed the system
Agriculture has an extensive history in
using a machine learning for betterment of
India. Agriculture is one of the important
the farmer. Machine learning (ML) is a
occupation practiced in India. India being a
game changer for agriculture sector.
nation of millions of villages so it employs
a large share of population in rural areas. It Machine learning is the part of artificial
intelligence, has emerged together with
bigdata technologies and high-
performance computing to create new
 SMART CROP RECOMMENDATION SYSTEM

opportunities for data intensive science in Rahul katarya [4] describes the different
the multidisciplinary agro technology machine learning methods used for
domain. The designed system will accelerating crop yield. In this paper they
recommend the most suitable crop for gone through different artificial intelligence
particular land. Based on weather techniques such as machine learning
parameter and soil content such as Rainfall, algorithm, big data analysis for precision
Temperature, Humidity and pH. They are agriculture. They explain about crop
collected from Government website and recommender system using KNN,
KAGGLE. The system takes the required Ensemble-based Models, Neural networks,
input ...etc.
from the farmers or data set such as III. PROPOSED SYSTEM
Temperature, Humidity and pH. This all
The Proposed system will predict the most
inputs data applies to machine learning
suitable crop for particular land based on
predictive algorithms like logistic
soil contents and weather parameters such
regression and Decision tree to identify the
as Temperature, Humidity, soil PH and
pattern among data and then process it as
Rainfall.
per input conditions. The system
recommends the crop for the farmer and
also recommends the amount of nutrients to
be add for the predicted crop.
II. LITERATURE SURVE
Ashwani kumar Kushwaha[2] describes
crop yield prediction methods and a suggest
suitable crop so that it will improve the
profit for the farmer and quality of the
agriculture sector. In this paper for crop
yield prediction they obtain large volume
data, it’s been called as big data (soil and
weather data) using Hadoop platform and
agro algorithm. Hence based repository
data will predict the suitability crop for
particular condition and improvement crop
quality.
Girish L [3] describe the crop yield and rain
fall prediction using a machine learning Figure 1. Architecture of the proposed
method. In this paper they gone through a system.
different machine learning approaches for
the prediction of rainfall and crop yield and The Architecture of the proposed system
also mention the efficiency of a different consists of various
machine learning algorithm like liner blocks as shown in the fig (1) as follows
regression, SVM, KNN method and
decision tree. In that algorithm they The crop prediction system follows a
conclude that SVM have the highest systematic and structured workflow, as
efficiency for rainfall prediction. illustrated in Figure 1, to assist farmers in
identifying the most suitable crop for
cultivation based on environmental and soil
 SMART CROP RECOMMENDATION SYSTEM

parameters. The major stages of the system 2 Recommendation Display: Upon

are outlined below: successful classification, the system
displays the most suitable crop
1. Start and Dataset Loading: The
recommendation to the user. This enables
system initiates by loading a
the farmer to make an informed, data-
comprehensive dataset that contains
driven decision regarding crop selection.
historical agricultural data, including soil
characteristics, temperature, humidity, and End: The system concludes the process
pH levels. after presenting the recommendation or the
error message.
2. Data Pre-processing: In this stage,
the dataset undergoes cleaning and 3. Crop Prediction:
preparation. This includes handling missing
A flowchart is simply a graphical
values, removing inconsistencies, and
representation of steps. It shows steps in
normalizing data to ensure accuracy and
sequential order and is widely used in
quality. Pre-processing is a crucial step to
presenting the flow of algorithms,
enhance the performance of machine
workflow or processes. Typically, a
learning models.
flowchart shows the steps as boxes of
3. Sensor Data Collection: The various kinds, and their order by connecting
system reads real-time environmental them with arrows. It originated from
inputs such as temperature, humidity, and computer science as a tool for representing
soil pH values. These parameters are algorithms and programming logic but had
essential for accurate crop extended to use in all other kinds of
recommendation, as they directly influence processes. Nowadays, flowcharts play an
crop growth and yield. extremely important role in displaying
information and assisting reasoning. They
4. Prediction Using Machine
help us visualize complex processes, or
Learning Algorithm: The pre-processed
make explicit the structure of problems and
data is fed into a machine learning (ML)
tasks. A flowchart can also be used to define
model, which has been trained on historical
a process or project to be implemented.
agricultural datasets. The model processes
the input parameters and predicts a crop
index that represents the most suitable crop
for the current conditions.
5. Crop Classification and
Validation: The predicted crop index is
evaluated to verify its validity. If the index
corresponds to a known crop class, the
system proceeds to the next step. If the
input

1 the prediction is invalid, the system

displays an error message indicating
invalid readings.

Figure 2. Flow chart

 SMART CROP RECOMMENDATION SYSTEM

3.1. Crop Recommendation: To ensure the reliability of predictions, the

system includes a validation mechanism
Based on predicted rainfall, soil contents
that checks whether the input parameters
and weather parameters the system will
fall within acceptable ranges. If the values
recommend the most suitable crop for
are valid, the system proceeds to classify
cultivation. This system also provides
the crop and display the result. If the inputs
details about required fertilizers like
are outside the expected range, the system
Nitrogen(N), Phosphorus (P) and
alerts the user by displaying an error
potassium(K) in Kg per hectare and display
message indicating invalid readings.
the required seed for a cultivation in Kg per
acre for recommended crop. The accuracy of crop prediction is
influenced by the quality of data and the
This system as contain some other feature
performance of the machine learning
such as display the current market price and
model. Therefore, data preprocessing plays
approximated yield in quintal per acre for
a vital role in eliminating noise and
recommended crop. Those all details will
inconsistencies. Additionally, the system
helps to farmers for choosing the most
may incorporate ensemble learning
profitable crop.
techniques or multiple classifiers to
improve prediction robustness.

3.2.Crop Prediction: Ultimately, the crop prediction feature

provides farmers with tailored, data-driven
The core functionality of the proposed recommendations. This not only aids in
system lies in its ability to accurately optimal crop selection but also contributes
predict the most suitable crop for to improved agricultural yield, profitability,
cultivation based on environmental and and sustainability.
soil-related parameters. This prediction is
achieved through the integration of
machine learning algorithms that analyse IV. EXPERIMENTAL OUTCOME
various features including temperature,
The proposed system recommends the best
humidity, and soil pH values. These inputs
suitable crop for particular land by
are collected in real-time or derived from
considering parameters as annual rainfall,
historical datasets and are essential for
temperature, humidity and soil pH. Among
modelling the complex relationships
these parameters annual rainfall is predicted
between crop requirements and
by system itself by using previous year data
environmental conditions.
with SVM algorithm and other parameters
The prediction process begins with the are have to be entered by the user. In the
system receiving input values either output section the system displays a
through sensors or user input. These values suitable crop, required seeds/acre, market
are then passed through a trained machine price and approximate yield of the
learning model that has learned patterns recommended crop and also the system
from historical agricultural data. The model takes NPK values in the input section to
utilizes classification algorithms to assign a display the required NPK for the
crop label to the input set, effectively recommended crop.
identifying which crop would yield the best
results under the given conditions.
SMART CROP RECOMMENDATION SYSTEM

IIV. CONCLUSION AND FUTURE

SCOPE

CONCLUSION:
Presently our farmers are not effectively
using technology and analysis, so there may
be a chance of wrong selection of crop for
cultivation that will reduce their income. To
reduce those type of loses we have
developed a farmer friendly system with
GUI, that will predict which would be the
best suitable crop for particular land and
this system will also provide information
about required nutrients to add up, required
seeds for cultivation, expected yield and
market price. So, this makes the farmers to
take right decision in selecting the crop for
cultivation such that agricultural sector will
be developed by innovative idea.
FUTURE SCOPE:
We have to collect all required data by
giving GPS locations of a land and by
taking access from Rain forecasting system
of by the government, we can predict crops
by just giving GPS location. Also, we can
develop the model to avoid over and under
crisis of the food.

REFERENCES
1. Prof. D.S. Zingade ,Omkar Buchade
,Nilesh Mehta ,Shubham Ghodekar
,Chandan Mehta “Crop Prediction
System using Machine Learning”.
2. Ashwani kumar Kushwaha,
Swetabhattachrya “crop yield
prediction using agro algorithm in
hatoop”.
3. Girish L, Gangadhar S, Bharath T
R, Balaji K S, Abhishek K T “Crop
Yield and Rainfall Prediction in
Tumakuru District using Machine
Learning”.
 SMART CROP RECOMMENDATION SYSTEM

4. Rahul Katarya, Ashutosh Raturi, 7. Himani Sharma, Sunil Kumar “A

Abhinav Mehndiratta, Abhinav Survey on Decision Tree
5. Thapper “Impact of Machine 8. Algorithms of Classification in Data
Learning Techniques in Precision Mining”.
Agriculture”. 9. Pavan Patil, Virendra Panpatil, Prof.
6. Pijush Samui, Venkata Ravibabu Shrikant Kokate “Crop Prediction
Mandla, Arun Krishna and Tarun System using Machine Learning
Teja “Prediction of Rainfall Using Algorithms”.
Support Vector Machine and
Relevance Vector Machine”.