AI BASED CROP

MONITORING USING
IOT
Under the guidance of
Prof. Chhaya Narvekar

By
Group 24
Farman Haider (XIEIT2019032006)
Akhila Jadhav (XIEIT181916)
Darshan Bhanushali (XIEIT2019032005 )
 Table of Contents

01 Introduction
02 Objective
03 Literature Survey
04 Problem Statement
05 Implementation Plan
06 Requirement Analysis
07 Time Plan
08 References
 Introduction

 Agriculture has seen many revolutions, whether the systematic use of crop rotations and other improvements in
farming practice a few hundred years ago, or the “green revolution” with systematic breeding and the widespread
use of man-made fertilizers and pesticides a few decades ago.
 But now, agriculture is undergoing a fourth revolution triggered by the exponentially increasing use of information
and communication technology in it.
 In the proposed system, a conscious effort to scale down the immense groundwork of farmers is made.
 Unmanned monitoring of crops and autonomous control of pumps lays the way for elaborate farm management.
 Precise agricultural systems reduce ecological footprint as well as resources resulting in retaining labor and other
costs.
 Objective

 By the end of our project, we aim to increase productivity and encouragement in the field of agriculture.

 We are striving to reduce the gap between agriculture and technology.

 We focus on smart agricultural methods that will not only help the farmers but also help in minimizing the load that

the agricultural sector is currently facing.

Literature Survey
SR NO. YEAR NAME OF PAPER AUTHOR CONTENT

1. 2021 IoT and AI in Precision Javed Anjum The Proposed Recommender System gets real-time values by
Agriculture: Designing Sheikh , Sehrish sensors implanted in user farms to make recommendations about
Smart System to Munawar suitable crops to grow, fertilizers, pesticides, and irrigations to put
support illiterate Cheema, recommendations. Microcontroller grabs data from sensors and
Farmers Muhammad Ali , transmits to the webserver (fog nodes) where rule base analysis
Zohaib Amjad, will perform to match between predefined conditions and the
Jahan Zaib Tariq , current state of crops grabbed through sensors.
Ammerha Naz

2. 2020 “Application OF IOT Basudeba Behra , The proposed system makes use of technologies such as Wireless
And Weather Samita Kumari, Sensor Networks (WSN) and Internet of Things (IoT) for solving the
Prediction For Alisha Kumari, major challenges faced in agricultural fields. The acquired data
Enhancement OF Ajay Kumar about various parameters will be sent over to the cloud platform
Agriculture where it will be analyzed and processed against the required
Productivity climatic conditions and the further processed data can be used for
”International weather prediction using Machine Learning (ML) and Application
Programming Interfaces(APIs) and further, the farmers can be
informed about the same so that they can aim for increased
agricultural productivity.
Literature Survey
SR NO. YEAR NAME OF PAPER AUTHOR CONTENT

3. 2018 IOT Based Low Cost Kiranmai In this paper Smart Irrigation System One of the essential and
Smart Irrigation Pernapati basic services to survive on earth is Water. Recent time increasing
System the scarcity of water due to growing in population. So this is
becoming as a universal obstacle. The old irrigation system which
demands a lot of water, so it needs smart techniques for reducing
the percentage of wasting available water for the irrigation.

4. 2018 Agricultural Crop Kavitha B C, Shilpa In this paper The Internet of things (IOT) is remodeling the
Monitoring Sensors D P, Thanushree K agriculture enabling the farmers with the wide range of
using IoT. S, Swathi A M, techniques. IOT technology helps in collecting information about
Ranjitha M K conditions like weather, moisture, temperature and fertility of soil,
Crop online monitoring enables detection of weed, level of water,
pest detection, animal intrusion in to the field, crop growth,
agriculture.
Literature Survey
SR NO. YEAR NAME OF PAPER AUTHOR CONTENT

5. 2018 Plant Disease G. Prem Rishi The visible features such as shape, size, dryness, wilting, are very
Prediction using Kranth helpful to recognize the plant condition. The research paper deals
Machine Learning M. Hema Lalitha with all such features and apply various machine learning
Algorithms Laharika Basava technologies to find out the output. The research work deals with
Anjali Mathur decision tree, Naive Bayes theorem, artificial neural network and
k-mean clustering and random forest algorithms. Disease
development depends on three conditions-host plants susceptible
to disease, favorable environment and viable pathogen. The
presence of all three conditions is must for a disease to occur.

6. 2016 Using Deep learning Sharada P. In this paper the author has used Deep Learning for Image-Based
for Image-Based Plant Mohanty David P. Plant Disease Detection. The combination of increasing global
Disease Detection Hughes Marcel smartphone penetration and recent advances in computer vision
Salathé made possible by deep learning has paved the way for
smartphone-assisted disease diagnosis. Using a public dataset of
images of diseased and healthy plant leaves collected under
controlled conditions, we train a deep convolutional neural
network to identify 14 crop species and 26 diseases (or absence
thereof).

06
 Problem Statement

 The idea is to help people in the agricultural industry and farmers to advance their approach and
make cultivation innovative as opposed to old methods which were expensive, time-consuming
and inconsistent as traditional agriculture cannot meet the requirements of modern agriculture.
 Overuse of pesticides, fertilizer and watering leads to destruction of the crop as well as reduces the
efficiency of the field increasing the soil vulnerability.
 There is a need of developing a system that automates the agricultural practices like cultivation,
irrigation, predicts yields and helps in better demand and supply of agricultural produce throughout
the globe.
 Implementation Plan

Overview

 To collect data from soil sample such as humidity, moisture and temperature and
forward that data to the cloud.
 Process the data and predict weather using ML algorithms.
 Assembling a smart irrigation pumping system and setting soil threshold values to set
the amount of water to be pumped accordingly.
 Choosing an appropriate dataset to study and predict disease that fester on crops.
 Creating a user application for controlling irrigation and monitoring crops.

11
System Architecture
Circuit Design

NodeMCU ESP8266 is used as microcontroller to control the system. Various sensors such as DHT11,
BMP180, Soil Moisture, Rain are used to collect data from the setup. Rain sensor is switching device
activated by rainfall.
DC motor for pumping motor as per the plant requirement. Solenoid valve will be connected to the
relay module so that it will generate trigger to sprinkle water.
 Requirement Analysis
Hardware Software (Modern Tools)
 NodeMCU ESP8266  Arduino IDE
 Sensors : Soil Moisture, Rain, DHT 11  ThingSpeak
(temperature and humidity), BMP-180 (to  Google Collab
measure specific atmospheric pressure)  Spyder
 Module LDR (potentiometer)  Android Studio
 10K variable resistance pot
 Solenoid valve (pump)
 Relay Module (works as electrically operated
switch)
 LED
 LCD
 DC motor

10
Dataset
• The Dataset we used for Plant Disease Detection is New Plant Diseases Dataset which is a Image
dataset containing different healthy and unhealthy crop leaves from Samir Bhattarai.

• This dataset consists of about 87K rgb images of healthy and diseased crop leaves which is
categorized into 38 different classes.

• The total dataset is divided into 80/20 ratio of training and validation set preserving the directory
structure.

• A new directory containing 33 test images is created later for prediction purpose.
Results
 For Early Blight Disease:
Results
 For Healthy Plant:
Results
 For Late Blight Disease:
Time Plan
Sr no. Task Duration (Sem 7 & Sem 8)

1. Setup and sending sensors data to cloud November

2. Setting up irrigation module February

3. Monitoring the data from cloud January

4. Selecting an appropriate data set for health disease August - September

5. Processing data for prediction December

6. Creating an android application March

7. Testing April - May

References
 (PDF) APPLICATION OF IoT AND WEATHER PREDICTION FOR ENHANCEMENT OF AGRICULTURAL PRODUCTI
VITY (researchgate.net)

 https://www.frontiersin.org/journals/plant-science

• https://ieeexplore.ieee.org/document/8473292
 https://www.ijert.org/research/agricultural-crop-monitoring-sensors-using-iot-a-study-IJERTCONV6IS1311
5.pdf
 https://robu.in/iot-based-smart-irrigation-using-blynk-application/#:~:text=Here%20we%20are%20buildin
g%20an,track%20of%20the%20land%20condition
.
• https://www.kdnuggets.com/2020/06/crop-disease-detection-computer-vision.html
 https://www.irjet.net/archives/V5/i9/IRJET-V5I9158.pdf
THANK-YOU!