A MINI PROJECT REPORT
On
“Weather Forecasting With Help Of Iot”
Submitted by,
Ishan Raising
Harshwardhan Lahane
Sarthak Patil
Sanchit More
Prem Sirsat
Sarvajeet Patil
UNDER THE GUIDANCE OF
PROF. Shubhangi A. Joshi
IN PARTIAL FULFILMENT OF
T.E. (ELECTRONICS & TELECOMMUNICATION)
SAVITRIBAI PHULE PUNE UNIVERSITY
2023-2024
MARATHWADA MITRA MANDAL’S COLLEGE OF ENGINEERING, PUNE-52
DEPARTMENT OF ELECTRONICS AND TELECOMMUNICATION
MARATHWADA MITRA MANDAL’S
COLLEGE OF ENGINEERING, PUNE.
CERTIFICATE
This is to certify that the project report entitled
“Weather Forecasting With Help Of Iot”
Submitted by
Ishan Raising Exam No:- T190453145
Harshwardhan Lahane Exam No:- T190453103
Sarthak Patil Exam No:- T190453154
Sanchit More Exam No:- T190453117
Prem Sirsat Exam No:- T190453168
Sarvajeet Patil Exam No:- T190453133
is bonafide work carried out by them under the supervision of Ms. Shubhangi Joshi and it is
approved for the partial fulfilment of requirement of Savitribai Phule Pune University for award
of the Degree of Third Year Engineering (Electronics and Telecommunication).
This project report has not been earlier submitted to any other Institute or University for the
award of any degree or diploma.
PROF. Shubhangi A. Joshi
Project Guide
Department Of E&TC
External Examiner Name & Signature:
Date:
2
ACKNOWLEDGEMENT
“Ability and ambition alone are not enough for success. Many able persons have
failed to achieve anything worthwhile because of lack of guidance and direction.
Success of any project depends greatly on the support, guidance and
encouragement received from the guide.” We have been fortunate to have more
than one pillar of strength in our humble effort to make this project successful.
It gives us great pleasure to express our deep sense of gratitude to our
college project guide Ms. Shubhangi Joshi for her resourceful & able guidance
which lead to timely completion of this seminar report. It was really her insight
and obsession for innovative ideas that motivated us to consider our idea
seriously.
We managed to learn quite few things from her which will definitely help
us in the future. We sincerely thank her for this kind co-operation and extreme
patience that she has shown.
We are very thankful to Prof. Mr. Gopal Gawande, Head of Department
for providing all the necessary facilities and support.
We would also like to thank the entire teaching and non-teaching staff of
E&TC Department, who extended their kind cooperation. Last but not the least;
we would like to thank our family and friends for their constant support.
3
INDEX
TITLE Page. No.
ABSTRACT 5
CHAPTER 1: INTRODUCTION
1. Project Overview 6
2. Problem Statement 6
CHAPTER 2: LITERATURE SURVEY 7
CHAPTER 3: METHODOLOGY 8
CHAPTER 4: OBJECTIVE 8
CHAPTER 5: SYSTEM BLOCK DIAGRAM 9
CHAPTER 6: HARDWARE DESCRIPTION 10
CHAPTER 7: SOFTWARE DESCRIPTION 11
CHAPTER 8: CIRCUIT DIAGRAM 12
CHAPTER 9: RESULT 13
CHAPTER 10: ADVANTAGES 14
CHAPTER 11: LIMITATIONS 15
CHAPTER 12: APPLICATION 16
CHAPTER 13: CONCLUSION 17
CHAPTER 14: FUTURE SCOPE 18
REFERENCES 19
DATA SHEETS 19
4
ABSTRACT
This paper introduces the concept of weather forecasting utilizing
Internet of Things (IoT) technology, revolutionizing traditional
methods by harnessing real-time data from interconnected devices. The
architecture involves deploying sensors to collect environmental data,
transmitting it wirelessly to a central server or cloud platform for
analysis using machine learning algorithms. IoT-based forecasting
offers advantages like enhanced accuracy, scalability, and real-time
monitoring, catering to specific locations for improved decision-
making in sectors such as agriculture and disaster management.
5
Chapter 1 : Introduction
1.1 Project Overview
The project aims to develop a weather forecasting system leveraging
Internet of Things (IoT) technology. Traditional forecasting methods
often lack real-time data and localized accuracy, hindering effective
decision-making in various sectors. By integrating IoT devices
equipped with sensors to collect environmental data, this project seeks
to enhance forecasting accuracy, scalability, and real-time monitoring
capabilities.
1.2 Problem Statement
● Existing weather forecasting methods suffer from limited real-
time data and localized accuracy, hindering effective decision-
making across various sectors. This project aims to tackle these
shortcomings by developing an IoT-based weather forecasting
system, leveraging interconnected sensors to provide accurate,
real-time predictions tailored to specific locations, thereby
improving decision-making in agriculture, transportation, and
disaster management.
6
Chapter 2 : Literature Survey
In this section, an analysis is carried with the current
weather prediction strategies accessible in the literature.
Linear Regression is the most fundamental and regularly
utilized prescient model for investigation. Regression
estimates are for the most part used to depict the information
and illustrate connection between at least one independent
and dependent factor. Linear regression finds the best-fit
through the points, graphically. The best-fit line through the
focuses is known as the regression line. Here, the line can be
straight or curved relying upon the data. The best-fit line can
likewise be a quadratic or polynomial which gives us better
solution to our inquiries. Two of the algorithms used as a
part of this research are Decision Tree and Time Series
Analysis
Weather prediction has been a major challenge from early
days; new methodologies cluster everyday replacing the old
ones. Literature studies have shown that machine learning
techniques achieved better performance than traditional
statistical methods. The next wave in the era of computing
will be outside the realm of the traditional desktop. In the
Internet of Things (IoT) paradigm, many of the objects that
surround us will be on the network in one form or another.
Machine Learning is closely related to internet of things.
A perfect combination of them can promote fast
development of agricultural modernization, realize smart
agriculture and effectively solve the issues concerning
agriculture, countryside and farmers.
7
Chapter 3 : Methodology
The project will begin with a comprehensive review of existing IoT-
based weather forecasting systems and technologies. Based on the
review, an appropriate architecture will be designed and implemented,
involving the selection and deployment of IoT devices equipped with
relevant sensors. Data transmission protocols will be established to
ensure seamless communication between sensors and the central server
or cloud platform. Machine learning algorithms and predictive models
will be trained and optimized using historical weather data to generate
accurate forecasts. The system will be tested and validated in real-
world scenarios to assess its performance and reliability.
Chapter 4 : OBJECTIVE
● Develop a scalable architecture for IoT-based weather
forecasting, including sensor deployment, data transmission, and
analysis.
● Implement sensor nodes capable of collecting key environmental
parameters such as temperature, humidity, wind speed, and
precipitation.
● Design a central server or cloud platform for receiving,
processing, and analyzing data collected from IoT devices.
8
Chapter 5 : System Block Diagram
9
Chapter 6 : Hardware Description
The hardware components for the weather forecasting system include
the DHT sensor for measuring temperature and humidity, the BMP282
sensor for measuring atmospheric pressure and temperature, a
breadboard for prototyping and connecting the components, the ESP32
microcontroller for processing data and communication, and jumper
wires for establishing electrical connections. These components
together form the foundation of the IoT-based weather forecasting
system, enabling accurate data collection and processing for generating
real-time weather forecasts.
Hardware Specifications:-
● DHT Sensor
● BMP282 Sensor
● Breadboard
● ESP32
● Jumper Wires
10
Chapter 7 : Software Description
The software for weather prediction utilizing the Random Forest
algorithm will be developed using Jupyter Notebook, an open-source
web application that enables interactive data analysis and code
execution. Additionally, the Tensor Flow library, a popular open-
source machine learning framework developed by Google, will be used
to implement the Random Forest algorithm for weather prediction.
The software will provide a user-friendly and interactive platform for
building, training, and deploying Random Forest models for weather
prediction, empowering users to leverage advanced machine learning
techniques for accurate and timely weather forecasting.
11
Chapter 8 : CIRCUIT DIAGRAM
12
Chapter 9 : Result
The implementation of Machine Learning (ML) models in conjunction
with Internet of Things (IoT) technologies for weather forecasting has
yielded promising outcomes. Through extensive testing and validation,
our project has demonstrated notable improvements in prediction
accuracy compared to traditional forecasting methods.
Increased Accuracy: Our ML model, integrated with IoT sensor data,
consistently outperforms conventional forecasting techniques by
accurately predicting weather patterns, including temperature changes,
precipitation, wind speeds, and atmospheric pressure.Enhanced
Reliability: By leveraging real-time data collected from diverse
environmental sensors deployed across different regions, our system
provides reliable forecasts tailored to specific geographical locations,
minimizing inaccuracies associated with generalized predictions.
Timely Alerts: The integration of IoT sensors enables the system to
detect and alert users about sudden changes or extreme weather events,
facilitating proactive measures for risk mitigation and disaster
preparedness.
Scalability and Adaptability: The modular design of our system allows
for seamless integration of additional sensors and expansion to cover
larger geographical areas, ensuring scalability and adaptability to
evolving weather forecasting needs.
13
Chapter 10 : Advantages
● Real-Time Data Collection: The use of IoT sensors enables real-time
data collection of environmental parameters such as temperature,
humidity, and atmospheric pressure, allowing for timely and accurate
weather monitoring.
● Enhanced Accuracy: By leveraging multiple sensors and machine
learning algorithms, the system can provide more accurate and
localized weather forecasts compared to traditional methods,
improving decision-making in various sectors.
● Scalability: The modular design of the system allows for easy
scalability, enabling the addition of more sensors and devices to
expand monitoring capabilities as needed.
● Cost-Effective: IoT sensors and microcontrollers like the ESP32 are
relatively affordable, making the system cost-effective to deploy and
maintain, especially in comparison to traditional weather monitoring
infrastructure.
● Customization: The system can be customized to cater to specific
locations or applications, allowing stakeholders to receive weather
forecasts tailored to their needs, whether it be agriculture,
transportation, or disaster management.
● Remote Monitoring: With built-in Wi-Fi and Bluetooth capabilities,
the ESP32 microcontroller enables remote monitoring and control of
the weather forecasting system, facilitating easy access to data and
system management.
14
Chapter 11 : Limitations
● Reliability on Connectivity: The system's reliability heavily
depends on the availability and stability of internet connectivity
for data transmission between IoT sensors and the central server
or cloud platform. Connectivity issues or network outages could
disrupt data collection and forecasting processes.
● Sensor Calibration and Maintenance: IoT sensors such as DHT
and BMP282 require periodic calibration and maintenance to
ensure accurate measurements. Failure to calibrate or maintain
sensors properly could lead to inaccurate data and unreliable
forecasts.
● Power Dependency: IoT sensors and microcontrollers typically
require a power source, which could pose challenges in remote or
off-grid locations where access to electricity is limited.
Dependence on power sources also increases operational costs
and the system's vulnerability to power outages.
● Limited Coverage: The effectiveness of the system may be
limited by the availability and deployment of IoT sensors.
Coverage gaps in sensor deployment could result in incomplete
or biased weather data, affecting the accuracy and reliability of
forecasts, particularly in rural or sparsely populated areas.
15
Chapter 12 : APPLICATIONS
● Agriculture: Farmers can utilize accurate weather forecasts to
optimize irrigation schedules, plan crop planting and harvesting,
and mitigate risks associated with adverse weather conditions
such as droughts, frosts, or heavy rainfall.
● Transportation: Weather forecasts enable transportation
authorities to better manage traffic flow, plan routes, and mitigate
risks of accidents or delays caused by adverse weather conditions
such as fog, snow, or high winds.
● Disaster Management: Accurate weather predictions help
emergency responders and disaster management agencies prepare
for and respond to natural disasters such as hurricanes, floods,
wildfires, and severe storms, enabling timely evacuation and
resource allocation.
● Renewable Energy: Energy companies can use weather forecasts
to optimize the generation and distribution of renewable energy
sources such as solar and wind power, maximizing energy
production efficiency and grid stability.
16
Chapter 13 : Conclusion
The project endeavors to harness the potential of IoT technology to
revolutionize weather forecasting, addressing the limitations of
traditional methods and providing enhanced accuracy and real-time
monitoring capabilities. By integrating IoT devices and machine
learning algorithms, the project aims to contribute to the development
of more resilient and adaptive systems for weather prediction,
benefiting various industries and societal needs.
17
Chapter 14 : FUTURE SCOPE
● Enhanced Sensor Technology: Continued advancements in
sensor technology, including improved accuracy, reliability, and
energy efficiency, will enable the development of more
sophisticated IoT-based weather monitoring systems capable of
capturing a wider range of environmental parameters with higher
precision.
● Integration of AI and Machine Learning: Integration of artificial
intelligence (AI) and machine learning techniques into weather
forecasting systems will enhance predictive modeling
capabilities, enabling more accurate and reliable long-term
forecasts and improving the system's adaptability to changing
environmental conditions.
● Edge Computing: Adoption of edge computing technologies will
enable data processing and analysis to be performed closer to the
source of data collection, reducing latency and bandwidth
requirements while enhancing real-time decision-making
capabilities in IoT-based weather forecasting systems.
● Predictive Analytics: Incorporation of predictive analytics
techniques will enable weather forecasting systems to not only
predict future weather conditions but also anticipate potential
impacts on various sectors such as agriculture, transportation, and
public health, enabling proactive risk mitigation strategies.
18
REFERENCES
IoT based Machine Learning Techniques for Climate Predictive
Analysis - M.K. Nallakaruppan, U. Senthil Kumaran
DATASHEETS
● Kaggle dataset
https://www.kaggle.com/datasets/ananthr1/weather-prediction
19
20
