PREDICTIVE CROP DISEASE OUTBREAKS

A PROJECT REPORT

Submitted by

Jhelam Rout (220720100335)

in partial fulfillment for the award of the

degree of

MASTER IN COMPUTER APPLICATION

in
COMPUTER SCIENCE AND ENGINEERING

DEPARTMENT OF MCA

SCHOOL OF ENGINEERING AND TECHNOLOGY

BHUBANESWAR CAMPUS
CENTURION UNIVERSITY OF TECHNOLOGY AND MANAGEMENT
ODISHA

NOVEMBER 2023

SPECIMEN CERTIFICATE

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

SCHOOL OF ENGINEERING AND TECHNOLOGY
BHUBANESWAR CAMPUS
 BONAFIDE CERTIFICATE

Certified that this project report “Predictive crop disease outbreaks” is the bonafide
work of “ Jhelam Rout ” who carried out the project work under my supervision. This
is to further certify to the best of my knowledge that this project has not been carried
out earlier in this institute and the University.

SIGNATURE
Dr. Saneev Kumar
Das
ASST. PROFESSOR,
DEPT. OF MCA

Certified that the above-mentioned project has been duly carried out as per the norm
of the college statutes of the university

SIGNATURE

Prof. Rakesh Kumar Ray

HEAD OF THE DEPARTMENT MCA, CUTM

DEPARMENTAL SEAL
 DECLARATION

I hereby declare that the project entitled “PREDICTIVE CROP DISEASE

OUTBREAKS” submitted for the “Minor Project” of 3rd semester M.C.A in

Computer Science and Engineering is my original work and the project has not

formed the basis for the award of any Degree / Diploma or any other similar titles

in any other University / Institute.

Name of the Student: Jhelam Rout

Registration No: 220720100335

Place:

Date:

ACKNOWLEDGEMENT
 I wish to express my profound and sincere gratitude to Prof. Saneev Kumar
Das, Department of Computer Science and Engineering, SoET, Bhubaneswar
Campus, who guided me into the intricacies of this project nonchalantly with
matchless magnanimity.

I thank Prof. Rakesh Kumar Ray, Head of the Dept. of Department of

Computer Science and Engineering, SoET, Bhubaneswar Campus and Prof. Sujata
Chakravarty, Dean, School of Engineering and Technology, Bhubaneswar Campus
for extending their support during Course of this investigation.

I would be failing in my duty if I don’t acknowledge the cooperation

rendered during various stages of Predictive crop disease outbreaks.

I am highly grateful to Dr. Saneev Kumar Das, who evinced keen interest
and invaluable support in the progress and successful completion of my project
work.

I am indebted to Predictive crop disease outbreaks for their constant

encouragement, co-operation and help. Words of gratitude are not enough to
describe the accommodation and fortitude which they have shown throughout my
endeavour.

JHELAM ROUT(220720100335)

TABLE OF CONTENTS
CHAPTER NO TITLE
1 CERTIFICATE 2
2 DECLARATION 3

3 ACKNOWLEDGEMENT 4

4 PROBLEM STATEMENT 6

5 ABSTRACT 7

6 INTRODUCTION 8

7 REQUIRMENTS 9

8 USES 11

9 SOURCE CODE 12

10 OUTPUT 13

11 CONCLUSION 24

12 REFERENCES
25

PROBLEM STATEMENT
The growing availability of big data analysis methods has the potential to spur even
more research and development in smart farming. Besides promoting higher yield
crops in a more sustainable manner, it also aims to contribute to event forecasting,
detection of diseases, and management of water and soil. Big data is coming to the
agriculture domain by collecting data from meteorological stations, remote sensors,
historical data, and publicly available data-sets

ML-based applications for agriculture are still young, but are already showing
promise. For instance, disease classification from images can be done using popular
Convolutional Neural Network (CNN) architectures for different plants with different
diseases relationships between weather data and pest occurrence can be retrieved
using Long Short Term Memory (LSTM) networks for forecasting future pest attacks
insect detection on leaves can be performed using object segmentation and deep
learning techniques .

ABSTRACT
Considering the population growth rate of recent years, a doubling of the current
worldwide crop productivity is expected to be needed by 2050. Pests and diseases are
a major obstacle to achieving this productivity outcome. Therefore, it is very
important to develop efficient methods for the automatic detection, identification, and
prediction of pests and diseases in agricultural crops. To perform such automation,
Machine Learning (ML) techniques can be used to derive knowledge and
relationships from the data that is being worked on. This paper presents a literature
review on ML techniques used in the agricultural sector, focusing on the tasks of
classification, detection, and prediction of diseases and pests, with an emphasis on
tomato crops. This survey aims to contribute to the development of smart farming
and precision agriculture by promoting the development of techniques that will allow
farmers to decrease the use of pesticides and chemicals while preserving and
improving their crop quality and production.

INTRODUCTION
 Due to extremely high infant mortality, the human population of the planet
increased slowly until the year 1700. The first billion was reached in ca. 1800,
followed by the second billion in 1928, the third billion in 1960. In 2017, the world’s
population reached its seventh billion. The fast population growth over recent decades
is mainly due to better medical care. According to predictions from the United
Nations, the world’s population is expected to reach 9.7 billion in 2050, and 10.9
billion in 2100 .
Rapid population growth over recent decades has resulted in an increased demand
for agricultural goods, which in turn has lead to a large expansion of cultivation . To
meet rising population demands for food, bio-fuels, and animal products, crop yield
production must double its output by 2050. In order to achieve this goal, key crop
yields must improve by 2.4% each year, but they are now only increasing by roughly
1.3% per year . However, fulfilling this condition will have negative consequences for
the ecosystem, including the loss of biodiversity and increased greenhouse gas
emissions. Traditional agricultural production is not sustainable from an economic or
environmental standpoint; hence, it is critical to optimize the use of resources such as
water and soil to enable high yield crops

SOFTWARE REQUIREMENTS OF PREDICTIVE CROP DISEASE

OUTBREAKS
 Operating System: Windows 2000 Professional
  Environment: Jupyter Notebook

 Framework: Version 1.0

 Language: Python

HARDWARE REQUIREMENTS OF PREDICTIVE CROP DISEASE

OUTBREAKS

 Processor: 11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz 2.42 GHz

 Processor Speed: 250 MHz to 833 MHz

 Ram: 512 Mb Ram

 Hard Disk: 40 Gb
USES

Pandas

Pandas is an open-source library authorized under the Berkeley Programming

Conveyance (BSD). This well-known library is frequently utilized in the field of data
science. They're generally utilized for examination, control, and cleaning of
information, in addition to other things. Without having to switch to another
programming language like R, Pandas enables us to carry out straightforward data
modelling and analysis.

NumPy

When it comes to scientific computing, NumPy is one of the fundamental packages

for Python, providing support for large multidimensional arrays and matrices along
with a collection of high-level mathematical functions to execute these functions
swiftly. NumPy relies on BLAS and LAPACK for efficient linear algebra
computations. NumPy can also be used as an efficient multi-dimensional container of
generic data.

Seaborn

This package makes statistical model visualization possible. The library, which is
largely based on Matplotlib, makes statistical graphics possible by:

1. Variable examination by means of a Programming interface in view of datasets.

2. Make complex representations effortlessly, including multi-plot frameworks.
3. To compare data subsets, univariate and bivariate visualizations are utilized.
4. A wide range of color schemes are available for pattern displays.
5. Direct relapse assessment and plotting are done consequently.
Matplotlib

This library is responsible for the plotting of numerical data. It is utilized in data
analysis for this reason. An open-source library plots superior quality figures, for
example, pie outlines, scatterplots, boxplots, and diagrams, in addition to other things.

SciPy

Scipy is a Python library. Scientific computing, information processing, and high-

level computing are the primary uses for this open-source library. The library contains
a large number of easy-to-use methods and functions for quick and easy computation.
Scipy can be utilized for numerical calculations close by NumPy.

Some of SciPy's subpackages include cluster, fftpack, constants, integrate, io, linalg,
interpolate, ndimage, odr, optimize, signal, spatial, special, sparse, and stats.

Scikit- learn

Additionally, Scikit-learn is a Python-based open-source machine learning library.

This library supports both supervised and unsupervised learning methods. This library
already comes pre-installed with a number of well-known algorithms as well as the
SciPy, NumPy, and Matplotlib packages. Spotify music recommendations are the
Scikit-most-learn application that is most widely used.
Conclusion
 This survey presented an insight into existing research addressing the application
of ML-based techniques for forecasting, detection, and classification of diseases and
pests.
Data-sets containing weather, diseases, and pests data should keep records for
long periods of time. Time-series ML models, such as RNN, can be employed to
accurately forecast the occurrence of diseases and pests based on meteorological
measurements series. NDVI measurements can also be helpful, since they provide
additional information regarding the crop’s development.
Detection and classification of pests and diseases can be performed using
computer vision and deep-learning algorithms based on CNN models, which show
better performance when compared with older image classification approaches based
on “manual” features extraction. However, deep learning models require large
amounts of data, which can be difficult to obtain. To tackle this issue, the use of
transfer learning or few-shot learning methods can prove useful. Nonetheless,
although the performance of deep learning-based methods is high for images acquired
under controlled conditions, additional research is required regarding the analysis of
images taken in the field, under real life conditions.
Since the literature does not yet include substantial work on pest and disease
forecasting using combinations of different data modalities, this article also aimed to
provide a general overview on the use of ML techniques over different types of data,
in order to facilitate further developments that may help fulfill this gap.

References
1. https://www.mdpi.com/2077-0472/12/9/1350

2. https://www.frontiersin.org/articles/10.3389/fenvs.2018.00063/full

3. https://www.kaggle.com/code/durgeshrao9993/crop-disease-prediction-
end-to-end

4. https://www.geeksforgeeks.org/disease-prediction-using-machine-
learning/