Flood and rainfall predction final

WELCOME TO OUR PRESENTATION
Course code: CSE 326
Course Title: System Analysis and Design Laboratory
1

Flood and Rainfall prediction
2

Contents
4
Topics Slide no Topics Slide no
Overview 5 Use case Diagram 16
Introduction 6 Activity Diagram 17
Objective 7 ER Diagram 18
Features 8 Data flow Diagram 19-21
Intelligence 9 State Diagram 22
Technology & Tools 10
Hardware & Software 11 Business impact 24
Core components
Description
12 Scope for future work 25
ML model flow 13 Limitation 26
Artificial Neural Network 14 Challenged faced 27
Work flow Diagram 15 Conclusion 28

Overview
 The main purposes of our project are to increase awareness among the common people and reduce the loss.
People can easily visit our website and get information about flood possibility.
 Our website will provide a easy way to search and find rainfall range in different areas. All the visitors can
easily be informed about flood and heavy rainfall. Our website will give the users the facility of knowing the
previous flood history.
 Floods are the most destructive, causing massive damage to human life. Flood prediction system used in most
countries around the world today. Through the help of our website, people can get early warning of flood
effect and they can take essential steps or preparation to fight with that.
 Our website will provide early warning so that the damage of life, property and agricultural field can be
reduced. User can easily search for their areas and see the possibility of flood and also see the rain flow. We
are trying our level best to provide more facility to the users so that user can easily get their desired
information from our website and can protect themselves from the damage. We expect that government will
be conscious about destruction of agricultural field and take hard protection through our websites.
5

Introduction
 All of the natural disasters, floods are the most destructive, causing massive damage to human life,
infrastructure, agriculture and the socioeconomic system. Governments, therefore, are under pressure to
develop reliable and accurate maps of flood risk areas and further plan for sustainable flood risk
management focusing on prevention, protection and preparedness.
 Flood prediction models are of significant importance for hazard assessment and extreme events
management. Robust and accurate prediction highly contributes to water recourse management strategies,
policy suggestions and analysis, and further evacuation modeling. Thus, importance of advanced systems for
short-term and long-term prediction for flood and other hydrological events are strongly emphasized to
alleviate damage. However, prediction of flood lead-time and occurrence location is fundamentally complex
due to the dynamic nature of climate condition.
 Therefore, today’s major flood prediction models are mainly data specific and involve various simplified
assumptions.
6

Objectives
To predict floods and rainfall analysis in various rural regions of the country beforehand so
that safety measures can be taken.
To use for various industrial companies whose products are affected by Rainfall Patterns.
To helps in agriculture industry for proper planning beforehand.
To use in predicting suitable climatic condition of areas for transportation of goods and
services for companies.
To give early warning so that the damage and disaster can be prevented.
7

Features
 Not too demanding in terms of input data.
 Fast to run and produce the forecast so that adequate
lead time will be available.
 Able to generate real-time hazard maps.
 Proven reliable in terms of flood forecasting.
 Operational to satisfy end user requirements.
 Able to update the output and correct the error.
 Able to generate user-friendly warning information
automatically.
8

Intelligence
 Model can be deployed in flood prone areas for advance warning.
 Can be used for early decision making of disaster relief responses.
 Can be used for various industrial companies whose products are affected by rainfall
patterns.
 Can be used in agriculture industry for proper planning beforehand.
 Can be used in predicting suitable climatic condition of areas for transportation of goods and
services for companies.
9

Technology & Tools
• Environment – Python 3.6
• Python 3.6 Libraries - Keras , Tensorflow , Scikit learn , Pandas, Numpy, Matplotlib,
Seaborn , Imblearn(SMOTE)
• Tools- Fbprophet(for time series) , Flask ,Wtforms
• UI - HTML,CSS, Bootstrap
10

Hardware & Software
Operating System- Windows 7, Windows 8 or Windows 10
Hardware- Processor (CPU) with 2 gigahertz (GHz) frequency or above, A minimum of 2 GB
of RAM, A minimum of 50 MB of available space on the hard disk, Internet Connection
Broadband (high-speed) Internet connection with a speed of 1 Mbps or higher , Keyboard and
a Microsoft Mouse or some other compatible pointing device.
Browser- Chrome 36+, Edge 20+,Mozilla Firefox 31+, Internet Explorer 11+,Jupitar /Spyder
IDE.
11

Core Components Description
Data Ingestion – Ingest data related to flood and rainfall.
Data Analyzer – Data preparation - analysis, exploration, cleaning, feature
extraction, etc.
ML Training – Machine Learning model training, fine tuning and evaluation.
Model Store – Trained model weights are persisted in file system.
Model Serving – Serving flask jinja calls with trained models.
User Interface – UI provides real-time graphs and data analysis.
12

ML model flow
Machine learning (ML) is the study of computer algorithms that improve automatically through
experience.
13

Artificial Neural Network (Ann)
 INPUT LAYER: is the first layer of the ANN structure
is the input layer that takes the input for processing.
 HIDDEN LAYER: is the second layer that process the
data transferred from the input layer for processing
through neurons and, the weights are updated continuously
for precision and validity of the output .
 OUTPUT LAYER: This is the third and the last layer
through which the results are obtained from above
diagram.
14

Data flow diagram
Level 0
18

Data flow diagram
Level 1
19

Data flow diagram
Level 2
20

Business Impact
An alternate solution can be acquisition of factors like humidity, wind flow, geographical
location etc into the dataset.
Model can be deployed by government in flood prone areas for advance warning.
Can be used for early decision making of disaster relief responses.
Can be used in agriculture industry for proper planning beforehand.
Can be used in predicting suitable climatic condition of areas for transportation of goods
and services for companies.
22

Scope for future work
 Allow people to operate multiple use from one
account.
 Add rating or review system.
 Allow to save user details for future use.
23

Limitation
 No interaction with general people to administration.
 No auto generate forms.
 No rating or review system.
24

Challenges Faced
Collection of reliable data from different origins.
Deciding on a particular machine learning model for achieving maximum accuracy without
overfitting the data to it.
Prediction of Flood based on rivers discharge and daily, weekly runoff.
Analysis of River Pattern based on acquire dataset.
Improving the accuracy of the model with limited data sources available.
Integrating the model with an User Interface.
25

Conclusion
We developed a different model, using a rainfall-flow pattern based on historical rainfall and
flood flow data for real-time predictions of short-term flood stream-flow.
Our models predict the flood process line in real-time using hydrological feature extraction
and spatial-temporal metrics for similar rainfall flow patterns. The experimental results based
on the datasets of various models in wet and drought-ridden watersheds show that the
proposed models offer considerable advantages in accurately predicting the peak time of
floods in real time.
we will consider large-scale watershed discharge forecasts and other types of discharge
forecasts (such as urban underground drainage and high-sand rivers) forecasts. Finally, a
fusion of radar rainfall data and ground station data could be developed.
26

Flood and rainfall predction final

More Related Content

What's hot (20)

Similar to Flood and rainfall predction final (20)

More from City University (11)

Recently uploaded (20)

Flood and rainfall predction final