A PROJECT REPORT

ON
MACHINE LEARNING APPLICATION FOR PRECISION AGRICULTURE:
A COMPREHENSIVE REVIEW
Submitted in partial fulfillment for the Award of Credits To
IV-I FOR PROJECTWORK -I
IN BACHELOR OF TECHNOLOGY
IN
COMPUTER SCIENCE AND ENGINEERING

Submitted By:
D.RAM PRUDHVI [19BJ1A0524]

K.BLESSY [19BJ1A0547]

K.GNANA RAVIKIRAN [19BJ1A0550]

A.AYYAPPA [19BJ1A0508]

Under the esteemed guidance of

A.RAVI PRAKASH, M.Tech

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

ST.MARY’S GROUP OF INSTITUTIONS GUNTUR

(Affiliated to JNTU KAKINADA, Approved by AICTE, NEWDELHI & Accredited by ‘NAAC’)

CHEBROLU (V&M), GUNTUR DIST., ANDHRA PRADESH, INDIA, PIN: 522212,

2019-2023
 ST.MARY’S GROUP OF INSTITUTIONS GUNTUR
(Affiliated to JNTU Kakinada, Approved by AICTE, NEW DELHI & Accredited by ‘NAAC’)

CHEBROLU (V&M), GUNTUR DIST., ANDHRA PRADESH, INDIA, PIN: 522212

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

CERTIFICATE

This is to certify that the project report entitled “MACHINE

LEARNINGAPPLICATION FOR PRECISION AGRICULTURE:A
COMPREHENSIVE REVIEW” is the bonafied project work carried out by D.RAM
PRUDHVI [19BJ1A0524], K.BLESSY [19BJ1A0547], K. GNANA RAVI
KIRAN[19BJ1A0550], A.AYYAPPA [19BJ1A0508] during the academic year 2022-2023,
in partial fulfillment of the requirements to the award of the Credits in IV-I of Bachelor of
Technology In Computer Science and Engineering from St. Mary’s Group Of
Institutions Guntur of Jawaharlal Nehru Technological University, Kakinada.

PROJECT GUIDE HEAD OF THE DEPARTMENT

A.RAVI PRAKASH ,M.Tech Dr. S S N ANJANEYULU M.Tech, Ph.D

Assistant professor Associate professor

EXTERNAL EXAMINER
 MACHINE LEARNING APPLICATION
FOR PRECISION AGRICULTURE: A
COMPREHENSIVE REVIEW
ABSTRACT:
Agriculture plays a critical role in the global economy, and pressure on
agricultural systems will continue to increase as the world’s population grows.it
becomes a challenging task to fulfil the food requirement of the present and
future population. modern agriculture techniques should take into account
both the increased need for efficiency and the challenges posted by climate
change, which together define the competing needs for sustainable farming
and increased food production. Precision agriculture also known as smart
farming have emerged as an innovative tool to address current challenge in
agricultural sustainability. Machine Learning with Internet of things are
enabled key components of the next agriculture revolution. In this article
presents a systematic review of ML application in the field of agriculture. the
areas that are focused are prediction of soil parameters such as carbon and
moisture content, crop yield prediction, disease and weed detection in crops
and species detection. This approach can be integrated for enhanced livestock
production by predicting fertility patterns, diagnosing eating disorders, cattle
behaviour based on ML models using data collector by collar sensors, etc. this
article demonstrates how knowledge based agriculture can improve the
sustainable productivity and quality of the product.

OBJECTIVE:
In this project we present a comprehensive review of research dedicated to
applications of machine learning in agriculture production system.
INTRODUCTION:
one of the main economic activity in every country is agriculture. The
population of the world will increase more in the future years. The food
requirement will increase 70% and due to rapid urbanization, land availability
for agriculture will decrease in the coming years.
In last few years nature has experienced a drastic change in weather
conditions due to global warming. the average temperature of the earth has
been increased due to which there is uncertainty in climate conditions.
Frequents droughts, heavy rainfall are the biggest challenge for poor farmers.
based on the survey climate conditions can be change then the farmers income
can be decrease.
Precision agriculture is one of the solutions to ensure food security to the
world. The main focus of precision farming is to reduce the production cost and
environment effects to increase the farm’s profitability. In precision farming,
IoT based smart sensors are deployed int the agriculture land for collecting
data related to soil nutrients, fertilizers, and water requirements as well as for
analysing the crop growth.
The data obtained from the deployed sensors are processed and
analyzed using ML algorithms to make farming practice more controlled and
optimized. ML algorithms are also used for weather and rainfall prediction
based on the data obtained from sensors, climatic records and satellite images.
This could save the lives of thousands of farmers who commit suicide. Smart
livestock management is an important component of precision agriculture.

LITERATURE SURVEY:
TITLE: Some studies in machine learning using the game of checkers
AUTHORS: L. Samuel
Two machine-learning procedures have been investigated in some detail
using the game of checkers. Enough work has been done to verify the fact that
a computer can be programmed so that it will learn to play a better game of
checkers than can be played by the person who wrote the program.
Furthermore, it can learn to do this in a remarkably short period of time (8 or
10 hours of machine-playing time) when given only the rules of the game, a
sense of direction, and a redundant and incomplete list of parameters which
are thought to have something to do with the game, but whose correct signs
and relative weights are unknown and unspecified. The principles of machine
learning verified by these experiments are, of course, applicable to many other
situations.

TITLE: Precision agriculture—A worldwide overview

AUTHORS: 1) Naiqian Zhang
2) Maohua Wang
3) Ning Wang
This article provides an overview of worldwide development and current
status of precision-agriculture technologies based on literatures generated
mainly during the past 2 years. The topics include natural-resource variability;
variability management; management zone; impact of precision-agriculture
technologies on farm profitability and environment; engineering innovations in
sensors, controls, and remote sensing; information management; worldwide
applications and adoption trend of precision-agriculture technologies; and
potentials of the technologies in modernizing the agriculture in China.

TITLE: Precision farming: The future of Indian agriculture

AUTHORS: 1) Abdul Hakkim
2) Abhilash Joseph
3) Ajay Gokul
4) Mufeedha
Precision Farming or Precision Agriculture is generally defined as
information and technology-based farm management system to identify,
analyse and manage spatial and temporal variability within fields for optimum
productivity and profitability, sustainability and protection of the land resource
by minimizing the production costs. Increasing environmental consciousness of
the general public is necessitating us to modify agricultural management
practices for sustainable conservation of natural resources such as water, air
and soil quality, while staying economically profitable. The use of inputs (i.e.
chemical fertilizers and pesticides) based on the right quantity, at the right
time, and in the right place. This type of management is commonly known as
“Site-Specific Management”. The productivity gain in global food supply have
increasingly relied on expansion of irrigation schemes over recent decades,
with more than a third of the world's food now requiring irrigation for
production. All-together, market-based global competition in agricultural
products is challenging economic viability of the traditional agricultural
systems, and requires the development of new and dynamic production
systems.

TITLE: Tuning support vector machines regression models improves

prediction accuracy of soil properties in MIR spectroscopy

AUTHOTRS: 1) Andrew j.Margenot

2)Steve W. Culman
Estimating soil properties in diffuse reflectance infrared Fourier transform
sp accuracy. However, the impact of selecting best parameters for an algorithm
(tuning), to optimize non-linear models for predicting soil properties, is
relatively unexplored in the domain of soil sciences. This study aimed to
evaluate the predictive performance of linear (partial least squares, PLS) and
non-linear (support vector machines, SVM) multivariate regression models in
estimating soil physical, chemical, and biological properties with mid-DRIFTS.
We evaluated the impact of optimizing two hyperparameters (epsilon and cost)
based on the noise tolerance in the ε-insensitive loss function of SVM models
using two contrasting and diverse sets of soils, one from northern Tanzania
(n = 533) and another one from USA Midwest (n = 400). Regression models
were trained on calibration sets (75%) and tested on independent validation
sets (25%) separately for each dataset. Support vector machines outperformed
PLS models for all tested soil properties (clay, sand, pH, total organic carbon,
and permanganate oxidizable carbon) in both datasets. Tuning
hyperparameters epsilon and cost maintained or improved prediction accuracy
of SVM models based on root mean squared errors of independent validation
sets. Support vector machines tuned hyperparameters differed among soil
properties and also for the same soil property in distinct datasets, suggesting
the need for parameterizing non-linear models for specific soil properties and
datasets. Optimizing SVM regression models in mid-DRIFTS improves prediction
accuracy of soil properties and therefore will likely enable obtaining more
robust predictive outcomes even in datasets with diverse land uses, parent
materials, and/or soil orders. We recommend that tuning should be included as
a routine step when using SVM for estimating soil properties.

TITLE: Prediction of the calcium and magnesium content in soils

through a generalized regression neural networks and genetic algorithms

AUTHORS: 1)Labrador
2)Carolina Chang
3)Jesus Viloria
Users need to discern how the soil characteristics at locations of their interest
are, but soil properties can be determined only in a small number of sampling
points. Therefore, it is necessary to predict how the soil is at points that have
not been sampled. This study proposes a system for predicting soil property
values, based on Generalized Regression Neural Networks and Genetic
Algorithms. The Generalized Regression Neural Network is particularly useful
when the amount of data is small, as is common in soil inventories. The
proposed system calculates the mean square error, mean absolute error and
the coefficient of determination as indicators of the prediction error. It also
calculates the proportion of points which are generated unpredictably in a
resulting map. This information helps the user to select the best combination
of input variables and system parameters, according to their needs. The system
allowed generating maps of calcium and magnesium concentrations in the soil,
from a digital elevation model, satellite image and the values measured in a
limited number of sampling points in a cross section of the Caramacate river
basin (Aragua state, Venezuela). The selection of input variables to the network
and the value of the smoothing parameter which is generated using a Genetic
Algorithm, allowed to minimize the prediction error and the percentage of
points rated. The results revealed that the selection of input variables to the
network is crucial for the success of the prediction.
TITLE: Machine learning approaches for crop yield prediction and
nitrogen status estimation in precision agriculture: A review
AUTHOR: 1) Anna Chlingaryan
2) Salah Sukkarieh
3) Brett whelan

Accurate yield estimation and optimised nitrogen management is

essential in agriculture. Remote sensing (RS) systems are being more widely
used in building decision support tools for contemporary farming systems to
improve yield production and nitrogen management while reducing operating
costs and environmental impact. However, RS based approaches require
processing of enormous amounts of remotely sensed data from different
platforms and, therefore, greater attention is currently being devoted to
machine learning (ML) methods. This is due to the capability of machine
learning based systems to process a large number of inputs and handle non-
linear tasks. This paper discusses research developments conducted within the
last 15 years on machine learning based techniques for accurate crop yield
prediction and nitrogen status estimation. The paper concludes that the rapid
advances in sensing technologies and ML techniques will provide cost-effective
and comprehensive solutions for better crop and environment state estimation
and decision making. More targeted application of the sensor platforms and
ML techniques, the fusion of different sensor modalities and expert knowledge,
and the development of hybrid systems combining different ML and signal
processing techniques are all likely to be part of precision agriculture (PA) in
the near future.

TITLE: Machine learning based regression model for prediction of soil

surface humidity over moderately vegetated field

AUTHOR: 1) Emrullah Acar

2)Mehmet Sirac Ozerdem

3)Burak Berk Ustundag
The soil surface humidity parameter over vegetated fields is of great
importance for controlling water consumption; prevention of salinity caused by
over-irrigation; efficient use of irrigation system and improving the yield and
quality of the cultivated crop. However, determination of the soil surface
humidity is very difficult on vegetated fields. In order to overcome this
problem, polarimetric decomposition models and machine learning based
regression model were implemented. The main purpose of this study is to
predict soil surface humidity on moderately vegetated fields. Thus, the study is
conducted in agricultural fields of Dicle University and it consists of several
stages. In the first stage, a Radarsat-2 data was obtained in 3 March 2016 and
the local humidity samples were measured simultaneously with the Radarsat-2
acquisition. In the second stage, 10 polarimetric features were obtained from
each cell (2x2 pixels) of ground sample by utilizing standard ıntensity-phase
technique as well as Freeman-Durden and H/A/$\alpha$ polarimetric
decomposition models. This step is repeated for all ground samples and as a
result, a dataset with 156x10 lengths is formed. In the next stage, Extreme
Learning Machine based Regression (ELM-R) model was used for predicting the
soil surface humidity with the aid of polarimetric SAR features. For the
validation of the proposed system, leave-one-out cross-validation method was
applied and finally, 2.19% Root Mean Square Error (RMSE) were computed.
TITLE: Modelling of soil moisture retention curve using machine learning
techniques: Artificial and deep neural networks vs support vector regression
models

AUTHOR: Kevin Acheing

Soil water retention curve (SWRC) is of fundamental importance in
analyzing both flow and contaminant transport in the vadose zone. Field
and/or laboratory-based measurements of soil moisture and soil suction – the
two main variables that are used to develop SWRC – is often time consuming
and sometimes impossible. In this study, plausibility of various machine
learning techniques to simulate SWRC of loamy sand are evaluated.
Specifically, the machine learning techniques that are investigated include:
three support vector regression (SVR) models (i.e. radial basis function (RBF),
linear and polynomial kernels), single-layer artificial neural network (ANN), and
deep neural network (DNN). The soil moisture and soil suction were measured
using time-domain reflectometer (TDR) and tensiometer, respectively. The data
were collected under both monotonic wetting and drying of a disturbed sample
of loamy sand soil. These datasets were used to train and test the machine
learning techniques. Results show that the RBF-based SVR outperforms all the
other machine learning techniques in simulating SWRC for loamy sand
subjected to either monotonic wetting or drying. The ANN and DNN models
simulated soil water content with a RMSE of 0.004–0.009 cm³/cm³ for
monotonic wetting in the training phase; and 0.002–0.003 cm³/cm³ for
monotonic drying in training phase. In the testing phase, ANN and DNN models
simulated soil water content with RMSE of 0.02–0.121 cm³/cm³ and 0.003. The
RBF-based SVR model – the best performing machine learning model –
simulated soil water content with RMSE of 0.006 and 0.002 cm³/cm³ for soil
subjected monotonic wetting and drying, respectively. In the testing phase, the
RBF-based SVRmodel simulated soil water content with RMSE of 0.02–0.033
cm³/cm³ and 0.003–0.006 cm³/cm³ for soil under monotonic wetting and
drying, respectively. These machine models, therefore, provided plausible
SWRC simulations, and the models do not require knowledge of physical soil
parameters
TITLE :estimation of soil temperature from meteorological data using
different machine learning model
AUTHOR: 1)Yu Feng
2)Ningbo Cui
3)Weiping Hao
4)Lili Gaos
Soil temperature (T s) plays a key role in physical, biological and chemical
processes in terrestrial ecosystems. Accurate estimation of T s at various soil
depths is crucial for land-atmosphere interactions. This study investigated the
applicability of four different machine learning models, extreme learning
machine (ELM), generalized regression neural networks (GRNN),
backpropagation neural networks (BPNN) and random forests (RF), for
modeling half-hourly T s at four different depths of 2 cm, 5 cm, 10 cm, and 20
cm on the Loess Plateau of China. A field experiment was conducted to
measure half-hourly T s and meteorological variables. Air temperature , wind
speed, relative humidity, solar radiation, and vapor pressure deficit were used
as inputs to train the models for estimation of half-hourly T s. The results
showed ELM, GRNN, BPNN and RF models provided desirable performance in
modeling half-hourly T s at all depths, with root mean square error values
ranging 2.26-2.95, 2.36-3.10, 2.32-3.04 and 2.31-3.00 °C, mean absolute error
values ranging 1.76-2.26, 1.83-2.31, 1.80-2.32 and 1.79-2.26 °C, Nash-Sutcliffe
coefficient values ranging 0.856-0.930, 0.841-0.924, 0.847-0.927 and 0.850-
0.927, and concordance correlation coefficient values ranging 0.925-0.965,
0.925-0.963, 0.928-0.963, and 0.924-0.961 for the ELM, GRNN, BPNN, and RF
models, respectively. There was a statistically significant agreement (P < 0.001)
between the measured and modeled values at both half-hour and daily
timescales, and the box plots showed the distributional differences between
the measured and modeled values were small. Generally, the ELM model had
slightly better performance with much better computation speed than GRNN,
BPNN as well as RF models at half-hourly timescales, thus the ELM model was
highly recommended to estimate T s at different soil depths.

EXISTING SYSTEM:
The main reason for reduced food production is the lack of planning, unpredictable weather
conditions, improper harvesting and irrigation techniques and livestock mismanagement. In the last
few years, nature has experienced a drastic change in weather conditions due to global warming.
ADVANTAGES:
 people earn their living directly or indirectly through agriculture.
 Agriculture produces raw materials that are needed in manufacturing
like seal, cotton, ….
 Agriculture is practiced to improve food security in a country.
 Agriculture provides food that can be consumed by human beings.
 International trade is dependent on agricultural products which are
interchanged between countries.
 The agricultural sector is a leading employer in many countries.
 The roots of plants hold together the soil particles and stop soil erosion.
DISADVANTAGES:
 Invest in the farm productivity.
 Stay resilient against global economic factors.
 Cope with climate change, soil erosion and biodiversity loss.
 Satisfy consumers changing tastes and expectations.
 Adopt and learn new technologies.
 Inspire young people to stay in rural areas and become future farmers.

PROPOSED SYSTEM:
In this project presents a systematic review of ML application in the field of
agriculture. the areas that are focused are prediction of soil parameters such as
carbon and moisture content, crop yield prediction, disease and weed
detection in crops and species detection.

ADVANTAGES:
• Facilities in online trading and E-commerce.
 Modern machines can control the effects of farmers.
  Inspire young people to stay in rural areas and become future
farmers.
 They increase the price and demand of the products.
 Better marketing and exposure to the price.
 Modern machines can control the effects of farmers.
 Further improve the fertility of the soil.
 Decrease the use of water, fertilizers which keeps the prices down.

BLOCKDIAGRAM:
SYSTEM REQUIREMENT SPECIFICATION

H/W System Configuration:-

➢ Processor - P–IV

➢ RAM - 2 GB (min)

➢ Hard Disk - 40 GB

➢ Key Board - Standard Windows Keyboard

➢ Mouse - Two or Three Button Mouse

➢ Monitor - SVGA 21
SOFTWARE REQUIREMENTS:
Operating system : Windows 7 Ultimate or above.
Coding Language : Python.
Front-End : Flask or Django
Python IDE : pycharm,jupyter note book
FEASIBILITY STUDY
During this stage, the project's viability is evaluated, and a business
proposal outlining the project's broad strokes and some preliminary cost
estimates is presented. The practicality of the proposed model is to be
investigated throughout system analysis. This is necessary to guarantee that
the suggested solution won't cost the business too much. Understanding your
system's primary needs is crucial for conducting a feasible analysis.
There are three main factors to think about while doing a feasibility study:
ECONOMICAL FEASIBILITY
TECHNICAL FEASIBILITY
SOCIAL FEASIBILITY
ECONOMICAL FEASIBILITY
The purpose of this analysis is to determine how much money the system will
really make for the business. The corporation can only devote so much money
to the system's development phase. Spending must be rationalised. This is due
to the majority of both the technologies utilised are open source and so cost
nothing to implement. It was just necessary to buy the personalised items.
TECHNICAL FEASIBILITY
This research is performed to verify the system's technical viability, or the
system's technical needs. Whenever possible, systems should be designed such
that they do not place an excessive strain on existing infrastructure. The
ensuing strain on our limited technological resources is inevitable. The
customer will have to deal with a lot of pressure as a result. The created
system should have low requirements, as adopting it will need few or no
modifications.
SOCIAL FEASIBILITY
Users' reactions towards the system are being analysed to see how much they
trust it. Training your user to make the most of the technology is part of this
procedure. The user should feel safe using the system and should not perceive
it as a danger. User adoption is directly proportional to the effort put into
familiarising and instructing each individual user on how to best utilise the
system. Raising his self-assurance will allow him to provide the positive
feedback that is essential since he is the system's end user
EXPECTED OUTPUT:
REFERNCES:
 J. Diez-Sierra and M. D. Jesus, ‘‘Long-term rainfall prediction using
atmospheric synoptic patterns in semi-arid climates with statistical and
machine learning methods,’’ J. Hydrol., vol. 586, Jul. 2020, Art. no.
124789.

 S. B. Kamatchi and R. Parvathi, ‘‘Improvement of crop production using

recommender system by weather forecasts,’’ Procedia Comput. Sci., vol.
165, pp. 724–732, 2019.
 M. Lazri, K. Labadi, J. M. Brucker, and S. Ameur, ‘‘Improving satellite
rainfall estimation from MSG data in Northern Algeria by using a multi-
classifier model based on machine learning,’’ J. Hydrol., vol. 584, May
2020, Art. no. 124705.
 N. K. Shardoor and M. V. Rao, ‘‘Analysis of rainfall prediction using
machine learning data mining and satellite techniques,’’ Int. J. Eng.
Technol., vol. 7, no. 4, pp. 4362–4367, 2018.
 Y. Li, K. Guan, A. Yu, B. Peng, L. Zhao, B. Li, and J. Peng, ‘‘Toward building
a transparent statistical model for improving crop yield prediction:
Modeling rainfed corn in the U.S,’’ Field Crops Res., vol. 234, pp. 55–65,
Mar. 2019.
 M. Maimaitijiang, V. Sagan, P. Sidike, S. Hartling, F. Esposito, and F. B.
Fritschi, ‘‘Soybean yield prediction from UAV using multimodal data
fusion and deep learning,’’ Remote Sens. Environ., vol. 237, Feb. 2020,
Art. no. 111599.
 Kocian, D. Massa, S. Cannazzaro, L. Incrocci, S. D. Lonardo, P. Milazzo,
and S. Chessa, ‘‘Dynamic Bayesian network for crop growth prediction in
greenhouses,’’ Comput. Electron. Agricult., vol. 169, Feb. 2020, Art. no.
105167.
 S. Shahinfar and L. Kahn, ‘‘Machine learning approaches for early
prediction of adult wool growth and quality in Australian merino sheep,’’
Comput. Electron. Agricult., vol. 148, pp. 72–81, May 2018.
 S. P. Mohanty, D. P. Hughes, and M. Salathé, ‘‘Using deep learning for
image-based plant disease detection,’’ Frontiers Plant Sci., vol. 7, pp. 1–
10, Sep. 2016.
 Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V.
Vanhoucke, and A. Rabinovich, ‘‘Going deeper with convolutions,’’ in
Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Boston, MA, USA,
Jun. 2015, pp. 1–9.
 J. Amara, B. Bouaziz, and A. Algergawy, ‘‘A deep learning-based approach
for banana leaf diseases classification,’’ in Datenbanksysteme für
 Business, Technologie und Web (BTW 2017)—Workshopband, B.
Mitschang, D. Nicklas, F. Leymann, H. Schöning, M. Herschel, J. Teubner,
T. Härder, O. Kopp, and M. Wieland, Eds. Bonn, Germany: Gesellschaft
für Informatik e.V., 2017, pp. 79–88.
 P. Hughes and M. Salathe, ‘‘An open access repository of images on plant
health to enable the development of mobile disease diagnostic,’’
Comput. Soc., Cornell Univ., Ithaca, NY, USA, Tech. Rep., 2016. [Online].
Available: https://arxiv.org/abs/1511.08060
 D. S. Ferreira, D. M. Freitas, G. G. D. Silva, H. Pistori, and M. T. Folhes,
‘‘Weed detection in soybean crops using ConvNets,’’ Comput. Electron.
Agricult., vol. 143, pp. 314–324, Dec. 2017.
 Waheed, M. Goyal, D. Gupta, A. Khanna, A. E. Hassanien, and H. M.
Pandey, ‘‘An optimized dense convolutional neural network model for
disease recognition and classification in corn leaf,’’ Comput. Electron.
Agricult., vol. 175, Aug. 2020, Art. no. 105456
 ] H. Jiang, C. Zhang, Y. Qiao, Z. Zhang, W. Zhang, and C. Song, ‘‘CNN
feature based graph convolutional network for weed and crop
recognition in smart farming,’’ Comput. Electron. Agricult., vol. 174, Jul.
2020, Art. no.
 ACKNOWLEDGEMENT

On the occasion of presenting the dissertation, We would like to thank the Almighty for
providing strength and power by his enormous blessings to overcome all the hurdles and
hindrances during this project work.

First & Foremost, We would like to express my sincere gratitude to our guide
A.RAVI PRAKASH,M.Tech, Department of Computer Science And Engineering, St.
Mary’s Group of Institutions Guntur, for the continuous support of our B. Tech study and
research, for his patience, motivation, enthusiasm, and immense knowledge. His guidance
helped me in all the time of research and writing of this thesis. I could not have imagined
having a better advisor and mentor for our B. Tech study.

We also thank Chairman Sir Rev. Dr. K.V.K. RAO garu, St. Mary’s Group of Institutions
Guntur for providing necessary facilities to carry out this research work.

Besides our advisor, we would like to thank Dr. B. PENCHALAIAH, Principal, Dr. S.
APPARAO, Director & Dr. S S N ANJANEYULU, Head of The Department, St. Mary’s Group
of Institutions Guntur, for their guidance, support, encouragement and valuable
suggestions.

We also express my deepest sense of gratitude to all Lab technicians of SMGG. We would
like to tthank all the teaching and non-teaching staff of who were very helpful in completion
of our project work successfully.

We would extend my heartfelt thanks to our family: our parents for giving birth to me at
the first place and supporting me spiritually throughout my life.

We are fortunate to have friends and classmates, who constantly helped me throughout the
period, this study was carried out. I extend my hearty gratitude to all those who have
directly or indirectly helped me during this research. Thanks to one and all….
 ST.MARY’S GROUP OF INSTITUTIONS GUNTUR
(Affiliated to JNTU, KAKINADA, Approved by AICTE, NEWDELHI & Accredited by ‘NAAC’)

CHEBROLU (V&M), GUNTUR DIST., ANDHRA PRADESH, INDIA, PIN: 522212

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

DECLARTION

We, D.RAM PRUDHVI[19BJ1A0524], K.BLESSY[19BJ1A0547], K.GANNA RAVIKIRAN

[19BJ1A0550], A.AYYAPPA[19BJ1A0508] Students of B. Tech, ST.MARY’S GROUP OF
INSTITUTIONS GUNTUR, Jawaharlal Nehru Technological University Kakinada, A.P, do
hereby Declare that the Project Report Entitled “MACHINE LEARNING APPLICATION FOR
PRECISSION AGRICULTURE:A COMPREHENSIVE REVIEW” is the Genuine Work carried out
at ST.MARY’S GROUP OF INSTITUTIONS GUNTUR, under the Guidance of A.RAVI
PRAKASH,M.Tech, Department Of Computer Science and Engineering, ST.MARY’S GROUP
OF INSTITUTIONS GUNTUR. We declare that the Work embodied in the thesis has not
been submitted for the award of credits for Degree or Diploma of this or any other
University.

D.RAM PRUDHVI [19BJ1A0524]

K.BLESSY [19BJ1A0547]

K.GANNA RAVIKIRAN [19BJ1A0550]

A.AYYAPPA [19BJ1A0508]