FLOOD MONITORING AND ALERTING SYSTEM
CHAPTER 1
INTRODUCTION
Half of the Earth population lives today in urban areas. Therefore, the continuous sensing of
urban characteristics is particularly effective to understand people’s life, migration and so on.
The changes of the city is typically moderate with respect to all the actual sensors. Anyway,
natural disasters can cause sudden temporal discontinuity in the urban environment, creating a
necessity for a reliable and immediate response to the crisis condition. In this case, a highly
desirable sensor is required which is able to acquire information independent of the weather
condition and the hour of the day.
Prevention of flooding in urban areas caused by inadequate sewer systems has become an
important issue. With increased property values of buildings and other structures, potential
damage from prolonged flooding can easily extend into the millions of dollars. Residents pay
service fees and, thus, expect their urban drainage systems to operate effectively without fear
of failure due to weather conditions. However, drainage systems designed to cope with the
most extreme storm conditions would be too expensive to build and operate. In establishing
tolerable flood frequencies, the safety of the residents and the protection of their valuables must
be in balance with the technical and economic restrictions, thus representing a challenging
optimization problem.
The main aim of the project is automated identification of the flood hotspots on roads and
assess potential need for interventions in urban planning using machine learning techniques.
1.1 Problem Statement
Drainage systems have failed due to the increase Volume of water, disposal of solid wastes and
other waste into drainage. Disasters have events of environmental extremes which are
inevitable entities of this living world, and linked to every component of the ecosystem. The
interaction of flood causes in urban indicates significance of urban ecology in disaster risk
reduction. The data’s have been collected and interpreted in the context of flood risks and
urban management. It shows wider issues and many lessons for flood challenges in our country
cities and towns.
Department of CSE, BTI, Bangalore
2022-23
Page | 1
FLOOD MONITORING AND ALERTING SYSTEM
1.2 Existing System
In existing systems of significant attention has been paid to studies on the effectiveness of
pump stations and detention reservoirs for disaster prevention. Studies of detention reservoirs
have included: optimization of detention facilities using multi-objective genetic algorithms
(MOGA), determination of reservoir detention capacity, and stochastic rainfall analysis for
storm tank performance evaluation in urban drainage systems. Studies on reservoir location,
parameters, and optimal design capacity have drawn a lot of attention. In addition, pump station
studies have focused on: the operation of prediction-based rainwater pump stations in urban
basins, generalized methods for storm water pumping station design, and the real time
operation of rainwater pump stations. There have also been studies on drainage systems in
urban basins, including the assessment of urban drainage system resilience using a hydraulic
assessment model, and an investigation of the relationships between precipitation and floods.
Cooperative operation is advantageous as pump stations and detention reservoirs are a part of
the catchment system and their operation may drastically affect water levels and flooding in
the drainage network. This study investigates the cooperative operation of pump stations and
detention reservoirs, which are non-structural measures that can compensate for the timeconsuming and costly nature of structural measures. Drainage pumps at pump stations and
detention reservoirs are operated on the basis of centralized reservoirs (CR) and decentralized
reservoirs (DR), with monitoring nodes that consider the drainage system situation and
implement cooperative operation when necessary. To maximize flood sharing between each
drainage facility, cooperative operation is performed on the basis of the water levels in the
pump stations, drainage system, and detention reservoirs. CR operation can improve rapid
drainage effectiveness and DR operation can increase detention effectiveness. Cooperative
operation between CR and DR combines the advantages of CR/DR operation and effective
flood mitigation in urban drainage areas. In addition, we propose and apply the resilience index
as a standard for determining the condition of urban drainage systems.
Disadvantages:

Testing performances are poor

Low accuracy

Time consumption is more.
Department of CSE, BTI, Bangalore
2022-23
Page | 2
FLOOD MONITORING AND ALERTING SYSTEM
1.3 Proposed System
In the proposed system, the city drainage details such as length, breadth & height are collected
for some respective areas. And then the area wise population (number of buildings) and drain
details are studied. Depending on the number of buildings it calculates the average waste water
coming out from each and every building. The datasets for rainfall are also being collected and
depending on that the amount of rainfall in a particular area is calculated. Combining the
amount of rainfall and the waste water, the drainage capacity of the particular area is calculated
and calculate whether flood might occur in that very area or not. Applying machine learning
algorithm are Random Forest (RF), Gradient Boosting (GB), AdaBoost, Gausian Naive Bayes
(GNB) and Multi-layer Perceptron (MLP) to training the each attributes of drainage data. ML
technique is to get the best performance of classification accuracy and strategy.
Advantages:

it will achieve a success rate of 99.53%

High level of performance

Required very low computational power

The proposed method performed well compared to all the existing methods.

Execution time is less.
1.4 System Architecture
The architectural configuraton procedure is concerned with building up a fundamental basic
system for a framework. It includes recognizing the real parts of the framework and
interchanges between these segments. The beginning configuration procedure of recognizing
these subsystems and building up a structure for subsystem control and correspondence is
called construction modeling outline and the yield of this outline procedure is a portrayal of
the product structural planning. The proposed architecture for this system is given below. It
shows the way this system is designed and brief working of the system.
Department of CSE, BTI, Bangalore
2022-23
Page | 3
FLOOD MONITORING AND ALERTING SYSTEM
Fig 1.4.1: System architecture.
In the above figure of system architecture of HLD, upload the dataset in drainage data of
attribute are total area, land area, population, housing units, water area, road size with heigth
and weigth. The drainage data can be represented is as a set of housing units details, which
contains each information of drainage system. In drainage system data which must be
preprocessed before statistical methods can be applied. After preprocessing in data attributes,
checking housing units, water area and road size with heigth and weigth with rainfall. After
that applying machine learning algorithm are Random Forest (RF), Gradient Boosting (GB),
AdaBoost, Gausian Naive Bayes (GNB) and Multi-layer Perceptron (MLP) to training the each
attributes of drainage data. Finally, in web application can provide display the result with ML
technique to get the best performance of classification accuracy and strategy analysis of
calculate drainage capacity, predicted amount of rainfall, calculate rainfall whether drain is
occurring or not and drainage affected or normal.
Department of CSE, BTI, Bangalore
2022-23
Page | 4
FLOOD MONITORING AND ALERTING SYSTEM
CHAPTER 2
LITERATURE SURVEY
A literature survey or a literature review in a project report shows the various analyses and
research made in the field of interest and the results already published, taking into account the
various parameters of the project and the extent of the project.
A literature survey includes the following:
•
Existing theories about the topic which are accepted universally.
•
Books written on the topic, both generic and specific.
•
Research done in the field usually in the order of oldest to latest.
•
Challenges being faced and on-going work, if available.
Literature survey describes about the existing work on the given project .It deals with the
problem associated with the existing system and also gives user a clear knowledge on how to
deal with the existing problems and how to provide solution to the existing problems .different
thing.
2.1 RELATED WORK
1. Title: Real-time flood monitoring and warning system [2019]
Author: Jirapon Sunkpho and Chaiwat Ootamakorn
The main objective of this research work is to develop a real-time flood monitoring and
warning system. The goal of the flood monitoring system is to maintain members of a distance
GDU group as nodes of a flood monitoring infrastructure so that services, such as reliable
communication and real-time information access, can be implemented on top of this structure.
The system was designed such that it provides reliable network management to allow smooth
transmission of water-related data. The real-time flood monitoring system is implemented by
dividing into modules: real-time data reporting from sensors, forecasting, statistical and
historical information module, and warning module.
Advantages:

Provides accurate and reliable warning information to enable the better preparation for
unnecessary damages and losses.

The flood monitoring system is adequate in terms of real-time data acquisitions.
Department of CSE, BTI, Bangalore
2022-23
Page | 5
FLOOD MONITORING AND ALERTING SYSTEM
Disadvantages:

Since most GDUs are implemented in a remotely rural area, the cellular signal strength
received at some remote stations is quite weak.
2. Title: An Intelligent and Adaptable Grid-based Flood Monitoring and Warning
System [2021]
Author: Danny Hughes, Phil Greenwood, Gordon Blair, Geoff Coulson
This paper describes the operation of a GridStix-based flood monitoring system and
specifically focuses on how local grid computation can be used to support the adaptation of the
WSN to changing environmental conditions. This paper has described a WSN that is capable
of performing not only remote off-site flood modelling based on grids in the fixed network, but
also local on-site flood modelling using a lightweight grid built on our GridStix platform. This
work aims to promote the sensors to first class grid entities. This allows a greater degree of
integration and flexibility than those approaches that treat sensor networks as conceptually
distinct from the grid. In particular, for the flood prediction scenario it allows the users to more
effectively support WSN adaptation, to support richer sensor modalities, and to enable
proactive behaviour such as informing local stakeholders of pending flooding.
Advantages:

Allows a greater degree of integration and flexibility.

It allows us to more effectively support WSN adaptation, to support richer sensor
modalities, and to enable proactive behaviour such as informing local stakeholders of
pending flooding.
Disadvantages:

The adaptation policies are manually implemented.
3. Title: Flood Citizen Observatory: a crowdsourcing-based approach for flood risk
management in Brazil [2020]
Author: Lívia Castro Degrossi, Joao Porto de Albuquerque
In this work, the authors proposed a crowdsourcing-based approach for obtaining useful
volunteer information for the context of flood risk management.
Department of CSE, BTI, Bangalore
2022-23
Page | 6
FLOOD MONITORING AND ALERTING SYSTEM
Based on the experimental validation, the authors found that this platform is effective in
obtaining useful and accurate volunteer information, since volunteers can easily provide
information about the water level in the riverbed through the platform categories. This is an
important step since in certain regions of Brazil there do not exist water gauges to perform such
measurement in real time. The present work thus fills the gap of empirically evaluated
crowdsourcing approaches in the context of flood risk management in Brazil. However, it is
necessary to move forward not only in obtaining volunteered information about flood risk, but
also in the automated processing of this information to estimate the likelihood of a flood.
Advantages:

Is effective in obtaining useful and accurate volunteer information.
Disadvantages:

Performance is low
4. Title: Design of Early Warning of Flood Detection Systems for Developing
Countries [2021]
Author: Elizabeth Basha and Daniela Rus
This paper describes the problem of disaster warning, a solution to the problem in the case of
river flooding, a series of experiments towards this solution, and a set of lessons learned
through the work in rural Honduras. They agreed to design the event prediction system with
both groups working to install the system in the river basin and some help from CTSAR in
defining what constitutes a flood. Any technology needed for authority notification would fall
under the purview while CTSAR would work with the Honduran government to arrange who
receives the notification and what style of notification. For community evacuation, CTSAR
agreed to work with the communities to develop evacuation policies, determine additional
resource needs, and arrange for the implementation or purchase of those needs. Quite simply,
they work on the technology, and they work on the people and policy issues.
Advantages:

Provides security & redundancy.

Simple and ease of work.
Department of CSE, BTI, Bangalore
2022-23
Page | 7
FLOOD MONITORING AND ALERTING SYSTEM
Disadvantages:

Accuracy is low.
5. Title: Flood Detection System Using Wireless Sensor Network [2022]
Author: Abhijeet A Pasi & Uday Bhave
The main objective of this project work is to develop a real-time flood monitoring and warning
system for a selected coastal area. The system employs the use of advance sensing technology
in performing real-time monitoring of water information. The developed system is composed
of three major components:
1) sensor network,
2) processing and transmitting modules, and
3) database and base station server.
The sensor network will be implemented at remote sites, where network infrastructure is not
available. The connectivity is done through the wireless tunnels. The sensor network measures
water related data while the processing and transmission module is used to transmit measured
data to the database and application server. The database and application server is implemented
as an application to allow users to view real-time water-related data as well as historical data.
The application server is also able to send warnings to the responsible authorities in case of
emergency. We conclude with a brief discussion on some issues.
Advantages:

The developed system is stout and gives well-timed alert of flood occurrences and
controls the flood gate to avoid flood in coastal area.
Disadvantages:

The flood monitoring system is adequate in terms of real-time data acquisitions.
However, in order to enhance efficiency of flood prevention, the system could be
integrated with modern space technologies and Geographical Information Systems
(GIS).
Department of CSE, BTI, Bangalore
2022-23
Page | 8
FLOOD MONITORING AND ALERTING SYSTEM
CHAPTER 3
SYSTEM REQUIREMENTS
Framework Requirement Specification (SRS) is a focal report, which outlines the foundation
of the item headway handle. It records the necessities of a structure and in addition has a
delineation of its noteworthy highlight. A SRS is basically an affiliation's seeing (in making)
of a customer or potential client's edge work necessities and conditions at a particular point in
time (for the most part) before any veritable design or change work. It's a two-way insurance
approach that ensures that both the client and the affiliation understand exchange's necessities
from that perspective at a given point in time.
3.1 Software Requirements
1. Operating system
: Windows 10
2. Programming Language
: Python, C
3. Library
: Matplotlib, numpy, Pandas, Sckit-learn,
Joblib.
4. Simulation tool
: Anaconda Navigator IDE 3.7.4,
(jupyter Notebook), Arduino IDE.
I.
Jupyter Notebook
The Jupyter Notebook is an incredibly powerful tool for interactively developing and
presenting data science projects. This article will walk you through how to set up Jupyter
Notebooks on your local machine and how to start using it to do data science projects. As part
of the open source Project Jupyter, they are completely free. The Jupyter project is the
successor to the earlier IPython Notebook, which was first published as a prototype in 2010.
Although it is possible to use many different programming languages within Jupyter
Notebooks, this article will focus on Python as it is the most common use case. (Among R
users, R Studio tends to be a more popular choice). To get the most out of this tutorial you
should be familiar with programming, specifically Python and pandas specifically. That said,
if you have experience with another language, the Python in this article shouldn’t be too cryptic,
and will still help you get Jupyter Notebooks set up locally. Jupyter Notebooks can also act as
a flexible platform for getting to grips with pandas and even Python.
Department of CSE, BTI, Bangalore
2022-23
Page | 9
FLOOD MONITORING AND ALERTING SYSTEM
We will Cover the basics of installing Jupyter and creating your first notebook, Delve deeper
and learn all the important terminology and explore how easily notebooks can be shared and
published online. Indeed, this article is a Jupyter Notebook! Everything here was written in the
Jupyter Notebook environment, though you are viewing it in a read-only form.
II.
Python
Python is an object-oriented programming language created by Guido Rossum in 1989. It is
ideally designed for rapid prototyping of complex applications. It has interfaces to many OS
system calls and libraries and is extensible to C or C++. The characteristics of Python

It provides rich data types and easier to read syntax than any other programming
languages

It is a platform independent scripted language with full access to operating system API's

Compared to other programming languages, it allows more run-time flexibility

It includes the basic text manipulation facilities of Perl and Awk

A module in Python may have one or more classes and free functions

Libraries in Pythons are cross-platform compatible with Linux, MacIntosh, and
Windows
3.2 Hardware Requirements
1. Processor
: Intel i5 3.0 GHz
2. RAM
: 16 GB and above
3. System type
: 64-bit Operating system
4. Hard disk
: 500 GB
5. Arduino Uno
6. Node MCU
7. Ultrasonic sensor
8. Flow sensor
9. Moisture sensor
Department of CSE, BTI, Bangalore
2022-23
Page | 10
FLOOD MONITORING AND ALERTING SYSTEM
Arduino Uno - Open-source microcontroller board used as an interface.
Node MCU - Microcontroller used for connections and it lets data transfer using the Wi-Fi
protocol.
An ultrasonic sensor is an instrument that measures the distance to an object using ultrasonic
sound waves.
Flow sensors, also known as flow meters, are used to measure the flow rate of a liquid or gas.
Moisture sensors measure or estimate the amount of water in the soil. These sensors can be
stationary or portables such as handheld probes.
Department of CSE, BTI, Bangalore
2022-23
Page | 11
FLOOD MONITORING AND ALERTING SYSTEM
CHAPTER 4
OBJECTIVES AND METHODOLOGY
4.1 OBJECTIVES
The main objective of this study is to access the impacts of urban flooding on traffic
congestions by using geo-spatial datasets and explore the possibility of using hydrodynamic
modelling to identify the points of flood risk. The study will focus on the potential impact of
flooding on the performance of urban transport and not the infrastructure damage. The key
objectives would be

Establish a correlation between traffic volumes, traffic signal location with traffic
congestions in urban road network during a flood event.

Identification of the flood hotspots on roads and assess potential need for interventions
in urban planning.

High level of performance

Required very low computational power

The proposed method performed well compared to all the existing methods.

Execution time is less.
4.2 METHODOLOGY
1. Volume & density of the drainage:
Multiple datasets are used for this study and from those datasets at first we need to collect the
volume and density of the drains. Based on those data's we can manage the drainage system.
We then collect the population of the city. Based on those population's we can predict the
capability of the drainage and according to that the drains are located.
2. Waste management:
Cities used to face acute problems related to solid wastes. So, waste management is an
important task to be done. Poor waste management is another significant factor for flooding.
Disposal of waste into drainage leads to the large and rapid accumulation of sediments in the
Department of CSE, BTI, Bangalore
2022-23
Page | 12
FLOOD MONITORING AND ALERTING SYSTEM
drains. Dumping of solid wastes, building debris and casual litter disposal on drains causes
blockage and pollution in the drainage system and hence reduces the capacity of the drains.
3. Risk for flood:
Depending on the amount of rainfall we can predict the risk of flood. If the drainage is not
capable of taking the heavy amount of rainfall it develops the risk of flood.
The drainage system using machine learning method. Such as:1. Identify flood periods:
This step is time periods where alarm floods occur and builds the corresponding alarm flood
sequences. The alarm log is divided into time interval so f10min based on the water flow.
Intervals with more alarm occurrences than a specified threshold are highlighted. The
threshold(t) is chosen based on the definitionon the outlet of the drainage for an area which is
measured in cubic metres.
2. Rainfall Feature Extraction:
Based on the amount of waterfall from the previous data for an area we can predict the
formation of flood on that area. This information shall help us to keep a minimum threshold
which can be set for rainfall which shall cause the formation of flood on that area. This
calculation can achieve by the plotting a graph against the amount of rainfall and the water
flow in the drainage outlet. Now as we plot a graph, we can get the threshold for the next
prediction for which the flood can occur for the minimum amount of rain.
3. Cluster flood sequences and classification:
Here the different flood periods area is clustered together based on a set of areas. Now this
information is clustered together to predict the formation of flood in an area. Here the threshold
value is normalized based on the cubic metre excretion of the outlet pipe from the drainage and
then the average value is calculated and made it as a clustered threshold for an area. Finally we
are applying supervised machine learning algorithms are Random Forest (RF), Gradient
Boosting (GB), AdaBoost, Gausian Naive Bayes (GNB), multilayer perceptron (MLP) to get
the best performance of result and strategy.
Department of CSE, BTI, Bangalore
2022-23
Page | 13
FLOOD MONITORING AND ALERTING SYSTEM
4. Flood Alert:
Based on the prediction of flood on a certain area we can create a flood alert for the formation
of flood if the rain increases or not. This can help in preventing the flood and to take preventive
measures to stop it. An alert mechanism shall be provided which shall inform us that the flood
will occur or not.
Department of CSE, BTI, Bangalore
2022-23
Page | 14
FLOOD MONITORING AND ALERTING SYSTEM
CHAPTER 5
WORKING PRINCIPLE
The framework configuration prepare develops general structure building outline.
Programming diagram incorporates addressing the item system works in a shape that might be
changed into at least one anticipates. The essential demonstrated by the end customer must be
placed in a systematic way.
5.1 DATA FLOW DIAGRAMS
DFD graphically representing the functions, or processes, which capture, manipulate, store,
and distribute data between a system and its environment and between components of a system.
DFD has often been used due to the following reasons:

Logical information flow of the system

Determination of physical system construction requirements

Simplicity of notation

Establishment of manual and automated systems requirements
DFD Components
DFD can represent Source, destination, storage and flow of data using the following set of
components –
1. Entities - An external entity is a person, department, outside organization, or other
information system that provides data to the system or receives outputs from the system.
2. Process - any process that changes the data, producing an output. It might perform
computations, or sort data based on logic, or direct the data flow based on business
rules.
3. Data Storage - files or repositories that hold information for later use, such as a
database table or a membership form. Each data store receives a simple label, such as
“Orders.”
4. Data Flow - the route that data takes between the external entities, processes and data
stores.
Department of CSE, BTI, Bangalore
2022-23
Page | 15
FLOOD MONITORING AND ALERTING SYSTEM

DFD-L0
In the figure below of DFD-L0, collecting in Indian drainage data of attribute are total area,
land area, population, housing units, water area, road size with heigth and weigth. The drainage
data can be represented is as a set of housing units details, which contains each information of
drainage system. In drainage system data which must be preprocessed before statistical mehods
can be applied. After preprocessing in data attributes for each value of drainage system can
rescaled the data with normalization process. Finally, each attribute of drainage data applying
Machine Learning (ML) model technique to get the best performance of the result.
Fig: 5.1.1 Data Flow Diagram Level 0
In the above level diagram, the information and data of the drainage like the drainage area,
corresponding land area and its population, housing units, water area and road size is being
collected. This data is sent for pre-processing for further analysis. Data normalization is the
process of arranging the data into similar fields. This allows the data to be queried and
analyzed more easily. This rearranged data is sent for further analysis.

DFD-L1:
In the figure below of DFD-L1 is splitting the data of drainage attributes with features, level
and generate the valid model.
Department of CSE, BTI, Bangalore
2022-23
Page | 16
FLOOD MONITORING AND ALERTING SYSTEM
After valid the model, applying machine learning algorithm are Random Forest (RF),
Gradient Boosting (GB), AdaBoost, Gausian Naive Bayes (GNB) and Multi-layer Perceptron
(MLP) to training the each attributes of drainage data. After traing it can generate the train
model. Finally, ML technique to find the best performance of classification accuracy and
strategy.
Fig. 5.1.2 Data Flow Diagram Levelv1
In this level, the dataset is split according to their specific categories and sent for training and
testing purposes. The testing is done to generate a validate model. A model validation is the
process of confirming that the model actually achieves its intended purpose. Training a model
using ML techniques is done to determine how well the model will work when eventually put
into an application for the end-users. This trained model is then generated with the prediction
of its accuracy value. The generated model is processed and the performance of the result is
displayed along with its accuracy and strategy.
Department of CSE, BTI, Bangalore
2022-23
Page | 17
FLOOD MONITORING AND ALERTING SYSTEM
5.2 ENTITY-RELATIONSHIP DIAGRAM
An entity relationship diagram (ERD), also known as an entity relationship model, is a
graphical representation that depicts relationships among people, objects, places, concepts or
events within an information technology (IT) system. There are three basic elements in an ER
Diagram which are:

Entity

Attribute

Relationship
There are more elements which are based on the main elements. They are weak entity, multi
valued attribute, derived attribute, weak relationship, and recursive relationship.
To model the factors that constitute a flood, we define several entity types, i.e. the
Soil Reference, Soil Type, Land Use, Drainage, Topography and District. The entity Land
Use defines the usage of a certain piece of land.
The ER diagram that covers the factors that constitute the flood models can be seen in the above
figure. To model the factors that constitute a flood, we define several entity types, i.e. the Soil
Reference, Soil Type, Land Use, Drainage, Topography and District. The entity Land Use
defines the usage of a certain piece of land. It contains the attributes to define the type of land
use (e.g.: forest, farm, field, residence) as well as the area (spatial type: region) covered by the
land. The entity Soil Type defines a certain area of soil and what kind of soil type it belongs
to. The attributes define for the Soil Type are the type name as well as the area covered (spatial
type: region). The existence of drainage systems is captured via the entity Drainage which
contains the attributes the volume of the drainage, type, as well as the area covered by the
drainage.
Department of CSE, BTI, Bangalore
2022-23
Page | 18
FLOOD MONITORING AND ALERTING SYSTEM
Fig 5.2 ER Diagram for Flood Monitoring
The entity Topography is used to store the height of land area. The entity District covers a
certain area, usually in the form of governmental district, in which we record the rain
precipitation, the radiation flux, humidity, wind speed, aerodynamic resistance, mean saturated
vapor pressure and daily mean temperature, all of which are of the type moving real as well as
the air density. The attributes are modeled as moving real since the values changes over time.
Topography is the practice of showing on maps or charts the heights and depths of the features
of a place.
A form of water, such as rain, snow, or sleet, that condenses from the atmosphere, becomes too
heavy to remain suspended, and falls to the Earth's surface is precipitation.
The way any form of radiation (ultraviolet, visible, infrared) from the sun is absorbed scattered
or returned around the earth and can be expressed as some radiation arrival rate per the unit of
area of the surface is radiation flux or it is also defined as the measure of the amount of any
radiation received by an object from a given source.
Humidity is the concentration of water vapor present in the air.
Department of CSE, BTI, Bangalore
2022-23
Page | 19
FLOOD MONITORING AND ALERTING SYSTEM
Air density is the density of air or atmospheric density, denoted ρ, is the mass per unit volume
of Earth's atmosphere. Air density, like air pressure, decreases with increasing altitude. It also
changes with variation in atmospheric pressure, temperature and humidity.
The summing the maximum and minimum instantaneous temperatures during a 24-hour period
and dividing by two is daily mean temperature.
The inflows to any water system or area is equal to its outflows plus change in storage during
a time interval is water balance initial stage.
The vapor pressure of a system, at a given temperature, for which the vapor of a substance is
in equilibrium with a plane surface of that substance's pure liquid or solid phase is mean
saturation vapour pressure.
Wind speed is the rate at which air is moving in a particular area. Wind speeds were estimated
at between 200 mph and 210 mph.
The component of force exerted by the air on a liquid or solid object (such as a raindrop or
airplane) that is parallel and opposite to the direction of flow relative to the object is
aerodynamic resistance.
The infiltration rate is the velocity or speed at which water enters into the soil is known as the
water infiltration capacity.
Constant infiltration capacity rate is the velocity or speed at which water enters into the soil.
Infiltration capacity reaches a constant value equals to fc = 1.0 cm/hr.
Canopy Resistance is in total leaf area, by an increase in the resistance of an expansion of the
energy balance equation to more in individual leaves due to old age in leaves.
Leaf area index (LAI) quantifies the amount of leaf material in a canopy.
By definition, it is the ratio of one-sided leaf area per unit ground area.
K value or the K factor is soil erodibility factor which represents both susceptibility of soil to
erosion and the rate of runoff, as measured under the standard unit plot condition. Soils high in
clay have low K values, about 0.05 to 0.15, because they resistant to detachment.
Department of CSE, BTI, Bangalore
2022-23
Page | 20
FLOOD MONITORING AND ALERTING SYSTEM
Hence, this ER Diagram in DBMS is widely used to describe the conceptual design of
databases. It helps both users and database developers to preview the structure of the database
before implementing the database
5.3 CLASS DIAGRAM
The existence of drainage systems is captured via the entity Drainage which contains the
attributes the volume of the drainage, type, as well as the area covered by the drainage. The
entity Topography is used to store the height of land area. The entity District covers a certain
area, usually in the form of governmental district, in which we record the rain precipitation, the
radiation flux, humidity, wind speed, aerodynamic resistance, mean saturated vapor pressure
and daily mean temperature, all of which are of the type moving real as well as the air density.
The attributes are modeled as moving real since the values changes over time.
Department of CSE, BTI, Bangalore
2022-23
Page | 21
FLOOD MONITORING AND ALERTING SYSTEM
Process_data
Feature_extractio
n
String path;
Training
RandomForest rf;
f_list=[]
Numpy npl
SVM s;
DecisionTree dt;
Dataframe df;
process_data ()
Select_features()
fit()
save_model()
Collect_sensor_data
Server
Int water_presence;
String data;
Double height;
Int prediction;
collect()
save()
Fig 5.3 UML Class Diagram
Department of CSE, BTI, Bangalore
2022-23
Page | 22
FLOOD MONITORING AND ALERTING SYSTEM
CHAPTER 6
TESTING
Testing is an important phase in the development life cycle of the product. This is the phase,
where the remaining errors, if any, from all the phases are detected. Hence testing performs a
very critical role for quality assurance and ensuring the reliability of the software.
During the testing, the program to be tested was executed with a set of test cases and the output
of the program for the test cases was evaluated to determine whether the program was
performing as expected. Errors were found and corrected by using the below stated testing
steps and correction was recorded for future references. Thus, a series of testing was performed
on the system, before it was ready for implementation.
A good test is sometimes described as one, which reveals an error; however, more recent
thinking suggest that a good test is one which reveals information of interest to someone who
matters within the project community.
6.1 TYPES OF TESTING
6.1.1 Unit Testing
Individual component are tested to ensure that they operate correctly. Each component is tested
independently, without other system component. This system was tested with the set of proper
test data for each module and the results were checked with the expected output. Unit testing
focuses on verification effort on the smallest unit of the software design module.
6.1.2 Integration Testing
Integration testing is another aspect of testing that is generally done in order to uncover errors
associated with flow of data across interfaces. The unit-tested modules are grouped together
and tested in small segment, which make it easier to isolate and correct errors. This approach
is continued unit I have integrated all modules to form the system as a whole.
6.1.3
Acceptance Testing
This is the final stage of testing process before the system is accepted for operational use. The
system is tested within the data supplied from the system procurer rather than simulated data.
Department of CSE, BTI, Bangalore
2022-23
Page | 23
FLOOD MONITORING AND ALERTING SYSTEM
6.2 TEST CASES
Test 3Case
UTC-*1
Name3of3Test
Dataset collection
Expected3Result
Collection of standard dataset with csv format like
Finaldrain_systemdataset.csv, Population.csv and Rainfall
India.csv.
Actual3output
3Same3as3expected.
Remarks3
3Successful
Table 6.1 Unit Test Case 1
Test 3Case
UTC-*2
Name3of3Test
Feature Extraction
Expected3Result
Extraction of data from the dataset using data
normalisation technique.
Actual3output
3Same3as3expected.
Remarks3
3Successful
Table 6.2 Unit Test Case 2
Sl # 3Test 3Case
UTC-*3
Name3of3Test
Data Pre-processing
Expected3Result
Removal of unwanted Data using EDA format.
Actual3output
3Same3as3expected.
Remarks3
3Successful
Table 6.3 Unit Test Case 3
Department of CSE, BTI, Bangalore
2022-23
Page | 24
FLOOD MONITORING AND ALERTING SYSTEM
Test 3Case
UTC-*4
Name3of3Test
ML algorithms(Classification)
Expected3Result
Classification of dataset based on the Features and
accurate classification of data vector, using ML
algorithms like RF, GNB, GB, Deep Learning
algorithm(MLP)
Actual8output
Extraction failed
Remarks3
3unSuccessful
Table 6.4 Unit Test Case 4
Test 3Case
UTC-*5
Name3of3Test
Prediction of test data
Expected3Result
Based on the user input, detemination of flood
occurrence of test data.
Actual3output
3Same3as3expected.
Remarks3
3Successful
Table 6.5 Unit Test Case 5
Department of CSE, BTI, Bangalore
2022-23
Page | 25
FLOOD MONITORING AND ALERTING SYSTEM
CHAPTER 7
EXPECTED CONCLUSION
This project will be implementing an intelligent flood prediction and alerting system which is
an automated identification of the flood hotspots on roads and will assess potential need for
interventions in urban planning using machine learning technique. This paper uses machine
learning techniques to model the nonlinear relationship between the rainfall and the drainage
water level, and predict the water level in advance. This is critical in flood management and
prevents possible life and property lost due to the flash flood. This will be a low-cost and selfguiding system, hence there will be no requirement of real-time training.
Department of CSE, BTI, Bangalore
2022-23
Page | 26
FLOOD MONITORING AND ALERTING SYSTEM
CHAPTER 8
REFERENCES
1. Tingsanchali, T. Urban flood disaster management. Procedia Eng. 2012, 32, 25–37.
2. Andjelkovic, I. Non-Structural Measures in Urban Flood Management; IHP-V
Technical Documents in Hydrology No. 50; UNESCO: Paris, France, 2001.
3. Chung, J.H.; Han, K.Y.; Kim, K.S. Optimization of detention facilities by using multiobjective genetic algorithms. J. Korea Water Resour. Assoc. 2008, 41, 1211–1218.
4. Al-Hamati, A.A.N.; Ghazali, A.H.; Mohammed, T.A. Determination of storage volume
required in a sub-surface stormwater detention/retention system. J. Hydro-Environ.
Res. 2010, 4, 47–53.
5. Andrés-Doménech, I.; Montanari, A.; Marco, J.B. Stochastic rainfall analysis for storm
tank performance evaluation. Hydrol. Earth Syst. Sci. 2010, 14, 1221–1232.
6. Andrés-Doménech, I.; Montanari, A.; Marco, J.B. Efficiency of storm detention tanks
for urban drainage systems under climate variability. J. Water Resour. Plan. Manag.
2012, 138, 36–46.
7. Chill, J.; Mays, L.W. Determination of the optimal location for developments to
minimize detention requirements. Water Resour. Manag. 2013, 27, 5089–5100.
8. Tao, T.;Wang, J.; Xin, K.; Li, S. Multi-objective optimal layout of distributed stormwater detention. Int. J. Environ. Sci. Technol. 2014, 11, 1473–1480.
9. Tamoto, N.; Endo, J.; Yoshimoto, K.; Yoshida, T.; Sakakibara, T. Forecast-based
operation method in minimizing flood damage in urban area. In Proceedings of the 11th
International Conference on Urban Drainage, Edinburgh, Scotland, UK, 31 August–5
September 2008.
10. Graber, S.D. Generalized method for storm-water pumping station design. J. Hydrol.
Eng. 2010, 15, 901–908.
11. Mugume, S.; Gomez, D.E.; Butler, D. Quantifying the Resilience of Urban Drainage
Systems Using a Hydraulic Performance Assessment Approach. In Proceedings of the
13th International Conference on Urban Drainage, Sarawak, Malaysia, 7–11 September
2014; International Association for Hydro-Environment (IAHR): Perugia, Italy;
International Water Association (IWA): Lisbon, Portugal, 2014.
Department of CSE, BTI, Bangalore
2022-23
Page | 27
FLOOD MONITORING AND ALERTING SYSTEM
12. Flood Citizen Observatory: a crowdsourcing-based approach for flood risk
management in Brazil, Lívia Castro Degrossi, Joao Porto de Albuquerque [2020]
13. Flood Detection System Using Wireless Sensor Network, Abhijeet A Pasi & Uday
Bhave 2022
14. Real-time flood monitoring and warning system Jirapon Sunkpho and Chaiwat
Ootamakor, 2019.
15. An Intelligent and Adaptable Grid-based Flood Monitoring and Warning System
Danny Hughes, Phil Greenwood, Gordon Blair, Geoff Coulson, 2021
16. Title: Design of Early Warning of Flood Detection Systems for Developing Countries
Elizabeth Basha and Daniela Rus,
Department of CSE, BTI, Bangalore
2022-23
Page | 28