Intelligent Crop

Recommendation Using
Machine Learning Approach
Guided By

Head & Faculty

info.tech

DANIEL RAJ K 210820205011

JEFRI PANDIAN P 210820205031
 DOMAIN INTRODUCTION
Machine Learning

The domain of machine learning (ML) is a

subfield of artificial intelligence (AI) that
focuses on the development of algorithms
and models that enable computers to
learn and make predictions or decisions
without being explicitly programmed.
Machine learning involves the use of
statistical techniques to allow systems to
improve their performance on a specific
task over time as they are exposed to more
data .
 Objective of the Project

Provide recommendation of The model should aim to provide

the best suitable crops in the correct and accurate predictions
area so that the farmer based on the unique characteristics
does not incur any losses of the state's soil and climate.

To build a robust model for

predicting crop Provide profit analysis of
sustainability in a specific various crops based on
state, consider soil type and previous years data.
climatic conditions.
 PROBLEM STATEMENT
Agricultural productivity in many regions is significantly hindered by the lack of
personalized and data-driven crop selection. Farmers often rely on traditional knowledge or
generalized practices without considering critical environmental and soil-related parameters
such as soil type, nutrient levels, temperature, humidity, rainfall, and pH value. This leads to
suboptimal crop yields, financial losses, and inefficient use of natural resources.

In the era of digital agriculture, there is a pressing need for an intelligent system that can
recommend the most suitable crop for cultivation based on real-time and location-specific
data. However, most existing solutions are either too generic or inaccessible to small and
medium-scale farmers due to technological or financial barriers.

Therefore, the problem is to design and develop a Machine Learning-based Intelligent Crop
Recommendation System that can analyze multi-dimensional agricultural data and provide
accurate, region-specific crop suggestions. This system should aim to enhance productivity,
optimize resource usage, and support sustainable farming practices by bridging the gap between
traditional farming methods and modern data science techniques.
 abstract

a System for intelligent crop recommendation using machine learning

utilizing a hybrid model. The system considers factors like soil type,
rainfall, groundwater level, temperature, fertilizers, pesticides, and season.
By employing a machine learning classifier, the system recommends suitable
crops, aiming to improve crop yield for farmers. The proposed hybrid model
is effective in providing recommendations, offering valuable insights for
agricultural production and notifying farmers about changes in crop
market rates. The approach addresses agricultural challenges, contributes to
the Indian economy, and enhances crop quality through a ranking
process. The use of an ensemble of classifiers improves decision-making,
facilitating accurate predictions and cost estimation for the yielded
crops.
 LITERATURE SURVEY
• TITLE : "An objective method to modify numerical
model forecasts with newly given weather data using an artificial neural network"

• AUTHOR(S) : Koizumi K. Weather Forecast

• PUBLICATION: IEEE Control and System Graduate Research

Colloquium,ICSGRC 2012.82-87.10.1109/ ICSGRC.2012.6287140.

• CONCEPT DISCUSSED:
An objective method of forecasting precipitation coverage with a neural network is presented. This
method uses as predictors all available data at local weather stations including both numerical
model results and weather data obtained later than the model initial time with sometimes on
radict pere other orel hence. Since the method gives an objective and also realistic forecast of
areal precipitation coverage, its skill scores are better than those of the persistence forecast after 3.
h), the linear regression forecasts, and numerical model precipitation prediction.
 LITERATURE SURVEY
(Cont)
• TITLE: "Quantitative Rainfall Prediction in Thailand"

• AUTHOR(S) : Manusthiparom C., Oki T., and Kanae

• PUBLICATION: First International Conference on Hydrology and Water Resources on Asia

Pacific Region (APHW), Kyoto, Japan. 2003

• CONCEPT DISCUSSED:
The rainfall is one of the significant data set of water resource management. With the monthly
historical rainfall data in the period of 1941-1999 form 245 rainfall monitor stations in
Thailand
around Chao Phraya River, the rainfall prediction with an artificial intelligent technique is possible.
Artificial neural networks is one the most widely supervised techniques of data mining. It can be
applied on predictive training and testing patterns are prepared as a time-series data of the past
ten months. The numbers of training and testing patterns are 372 ot do, respect in the training
stepheteen steWe resets show that it is possible to predict annual rainfall one year ahead with
acceptably accuracy.
 LITERATURE SURVEY
(Cont)
• TITLE: "Long-range monsoon rainfall prediction of 2005 for the districts and
sub-division Kerala with artificial neural network”

• AUTHOR(S) : Guhathakurta, P

• PUBLICATION: Current Science 90:773-779, 2006

• CONCEPT DISCUSSED:
The advantages of artificial neural network tehnique for explaining the nonlinear behavior between the
inputs and output is explored to forecast the monsoon rainfall of 36 meteorological sub-divisions of India.
The model uses the past years of monsoon rainfall data only to forecast the monsoon rainfall of coming year.
Monthly rainfall time series data for each of the 36 meteorological sub-divisions constructed by
Guhathakurta and Rajeevan (2007) is used for the present study. The model captures well the input-output
nonlinear relations and predicted the seasonal rainfall quite accurately during the independent period. All
India monsoon rainfall forecasts were generated by using area weighted rainfall forecasts of all the
sub-divisions. For the first time the idea of up-scaling is introduced in monsoon rainfall prediction using
neural network technique and it is shown that up scaling helps to capture the variability of the all India
rainfall better. This helps to predict the extreme years like 2002, 2004 better than the neural network model
developed based on single time series of all India rainfall. However, derivation of smaller scale (sub-divisions)
forecast model may be more useful than the all India forecast.
 LITERATURE SURVEY
(Cont)
• TITLE: "Modeling inter-annual variation of a local rainfall data
using a fuzzy logic technique"

• AUTHOR(S) : Halide, H. and Ridd P

• PUBLICATION: Proceedings of International Forum on Climate Prediction,

2002, James Cook University, Australia, pp: 166-170, 2002

• CONCEPT DISCUSSED:
The developed Fuzzy Logic model is made up of two functional components; the knowledge
base and the fuzzy reasoning or decision making unit. Two operations were performed on the
Fuzzy Logic model; the fuzzification operation and defuzzification operation. The model
predicted outputs were compared with the actual rainfall data. Simulation results reveal that
predicted results are in good agreement with measured data. Prediction Error, Root Mean
Square Error (RMSE), Mean Absolute Error (MAE) and the Prediction Accuracy were calculated,
and on the basis of the results obtained, it can be suggested that fuzzy methodology is
efficiently capable of handling scattered data. The developed fuzzy rule-based model shows
flexibility and ability in modeling an ill-defined relationship between input and output variables.
 Existing System
More and more researchers have begun to identify this problem in Indian agriculture and are
increasingly dedicating their time and efforts to help alleviate the issue. Different works
include the use of Regularized Greedy Forest to determine an appropriate crop sequence at a
given time stamp. Another approach proposes a model that makes use of historical records of
meteorological data as training set. Model is trained to identify weather conditions that are
deterrent for the production of apples . It then efficiently predicts the yield of apples on
the basis of monthly weather patterns. The use of several algorithms like Artificial Neural
Network,
K Nearest Neighbors, and Regularized Greedy Forest is demonstrated in to select a crop based
on the predicted yield rate, which, in turn, is influenced by multiple parameters.
 Existing System
drawback

One shortcoming that we identified in all these notable

published works was that the
authors of each paper concentrated on a single
parameter (either weather or soil ) for
predicting the suitability of crop growth.
 proposed System

We to eliminate the aforementioned drawbacks, we propose an

Intelligent Crop Recommendation system- which takes into
consideration all the appropriate parameters, including temperature,
rainfall, and soil condition, to predict crop suitability. This system is
fundamentally concerned with performing the primary function of
Agro Consultant, which is, providing crop recommendations to
farmers algorithms. We also provide the prot analysis on crops
grown in different states which gives the user an easy and reliable
insight to decide and plan the crops.
 proposed System
advantages

Acquisition of Training Dataset

Training model and crop recommendation
Data Preprocessing
architecture diagram
 Algorithm Used

RANDOM FOREST ALGORITHM

Random Forest belongs to the supervised learning technique. It can be used for
both Classification and Regression problems in ML. It is based on the concept of
ensemble learning, which is a process of combining multiple classifiers to solve a
complex problem and to improve the performance of the model. "Random Forest
is a classifier that contains a number of decision trees on various subsets of the
given dataset and takes the average to improve the predictive accuracy of that
dataset. Instead of relying on one decision tree, the random forest takes the
prediction from each tree and based on the majority votes of predictions, and it
predicts the final output. The greater number of trees in the forest leads to higher
accuracy and prevents the problem of overfitting.
The Working process

Step-1: Select random K data points from the training set.

Step-2: Build the decision trees associated with the selected data
points.

Step-3: Choose the number N for decision trees that you want to build.

Step-4: Repeat Step 1 & 2.

Step-5: For new data points, find the predictions of each decision tree,
and assign the new data points to the category that wins the majority
votes.
The Working process

Step-1: Select random K data points from the training set.

Step-2: Build the decision trees associated with the selected data
points.

Step-3: Choose the number N for decision trees that you want to build.

Step-4: Repeat Step 1 & 2.

Step-5: For new data points, find the predictions of each decision tree,
and assign the new data points to the category that wins the majority
votes.
 MODULES

➢ Metadata
➢ Data Pre-processing
➢ Crop Prediction Module
➢ Crop Recommendation Module
Metadata:

➢ All the main data used in the data set are initialized with the number to
use in the algorithm

➢ it is like initializing all the details. In this metadata, we are going to

initialize all the crop names with the numbers.

➢ This data makes us use the data easily in the algorithm. Hear the metadata
of all the crops is given with a particular number. This number is not
duplicated that is one number is given to one crop,

➢ the same number is not given to the other crop. This metadata consists of
more than a hundred crops that grown all over India.
Data Pre-processing :

➢ Hear the raw data in the crop data is cleaned and the metadata is appending
to it by removing the things which are converted to the integer.

➢ the data is easy to train. Hear all the data. In this pre-processing, we first
load the metadata into this and then this metadata will be attached to the
data and replace the converted data with metadata.

➢ Then this data will be moved further and remove the unwanted data in the
list and it will divide the data into the train and the test data.
Crop prediction module :

➢ The obtained result will be helpful for the farmers to know the Yield of the crop.

➢ He can go for the better crop which gives high yield and also say them the efficient use of
agriculture field.

➢ This way we can help the farmers to grow the crop which gives them better yield.
Crop Recommendation module :

➢ In this module, we have proposed a model that addresses these issues.

➢ The novelty of the proposed system is to guide the farmers to maximize the
crop yield as well as suggest the most profitable crop for the specific
region.
 Output
DATA ENTER PreView
UPLOAD PAGE
Recommendation PAGE
DATA SET
Accuracy level of algorithms
 CONCLUSION

This project proposes a novel intelligent system for agricultural

crop prediction. The key idea is to use ensemble of classifiers for
prediction. The usage of ensemble of classifiers paves a path way
to make a better decision on predictions due to the usage of
multiple classifiers. Further, a ranking process is applied for
decision making in order to select the classifiers results. This
system is used to predict the Recommended of the crop rate for
further. The solution will benefit farmers to maximize productivity
in agriculture, reduce soil degradation in cultivated fields, and
reduce fertilizer use in crop production by recommending the
right crop by considering various attributes.
 FUTURE SCOPE

This research work can be enhancing to the high level by building a

recommender system of agriculture production and distribution for farmer.
India may be a country wherever agriculture is extremely vital. The
prosperity of the farmers ends up in the prosperity of the state. Thus, our
work would assist farmers in sowing the acceptable seed supported
soil necessities so as to extend productivity and exploit such a way . As
a result, farmers will plant the acceptable crop, increasing their yield and
therefore the nation's overall productivity. Our future work can concentrate
on associate degree improved knowledge set with an oversized variety
of attributes, in addition as yield prediction .
 REFERENCES

[1] Aruvansh Nigam, Saksham Garg, Archit Agrawal ―Crop Yield Prediction using ML Algorithms ―,
2019 Fifth International Conference on Image Information Processing (ICIIP)

[2] LeoBrieman, ―Random Forestsǁ, 2019 IEEE Transactions on Instrumentation and Measurement

[3] Priya, P., Muthaiah, U., Balamurugan, M.ǁ Predicting Yield of the Crop Using Machine Learning
Algorithmǁ,2020 International Journal of Engineering Sciences & Research Technology (IJESRT)

[4] Mishra, S., Mishra, D., Santra, G. H.,―Applications of machine learning techniques in agricultural
crop productionǁ,2020 Indian Journal of Science and Technology

[5] Dr.Y Jeevan Kumar,ǁSupervised Learning Approach for Crop Productionǁ, 2020 5th International
Conference on Communication and Electronics Systems (ICCES)
[6] RameshMedar,Vijay S, Shweta, ―Crop Yield Prediction using Machine Learning Techniquesǁ,
2018 International Journal of Engineering Sciences & Research Technology (IJESRT)

[7] Ranjini B Guruprasad, Kumar Saurav, Sukanya Randhawa,ǁMachine Learning Methodologies

for Paddy Yield Estimation in India: A CASE STUDYǁ, IGARSS 2019 - 2019 IEEE International
Geoscience and Remote Sensing Symposium

[8] https://en.wikipedia.org/wiki/Crop_yield

[9] https://en.wikipedia.org/wiki/Random_forest

[10] https://en.wikipedia.org/wiki/Knearest_neighbors_algorithm

[11] N. Suresh, Nvk Ramesh, Syed Inthiyaz, P. Poorna Priya, KurraNagasowmika,Kota V. N. Harish
Kumar, Mashkoor Shaik, B. Naresh Kumar Reddy,―CropYieldPrediction Using Random Forest
Algorithmǁ,2021 7th International Conference on Advanced Computing and Communication
Systems (ICACCS)