Over 2.3 Billion people are affected due to floods in last 20 years and causing countless death , More than 92,million cattle are lost every year, seven million hectares of land is affected, and damage is over trillions dollars when taken globally in last 5 years. Floods are complicated natural events. It depends on several parameters, so it is very difficult to model analytically. The floods in a catchment depends on the characteristics of the catchment, rainfall and antecedent conditions. So the estimation of the flood peak is a very complex problem. Its due to the lack of Flood Prediction System which can predict the situation accurately. To Overcome this challenge we are building a Flood Prediction System using Predictive modelling. However we have divided our idea into small fragments but enough to be used globally. We have considered most flooded state of India, but can be used widely for all the low lying geographical regions. •The plains of Bihar, adjoining Nepal, are drained by a number of rivers that have their catchments in the steep and geologically nascent Himalayas. Kosi, Gandak,Burhi Gandak, Bagmati, Kamla Balan, Mahananda and Adhwara Group of rivers originates in Nepal, carry high discharge and very high sediment load and drops it down in the plains of Bihar. · About 65% of catchments area of these rivers falls in Nepal/Tibet and only 35% of catchments area lies in Bihar. · Bihar is India’s most flood-prone State, with 76 percent of the population, in the north Bihar living under the recurring threat of flood devastation. About 68800 sq Km out of total geographical area of 94163 sq Km comprising 73.06 percent is flood affected. · According to some historical data, 16.5% of the total flood affected area in India is located in Bihar while 22.1% of the flood affected population in India lives in Bihar. · From 1979 to Present day more than 8,873 Humans & 27,573 animals have lost their life due to flood. Some of Tools & Technology which is being used & can be used for Flood Prediction: •IBM. Watson Studio democratizes machine learning and deep learning to accelerate infusion of AI in to drive innovation. •An Intelligent Hydro-informatics Integration Platform for Regional Flood Inundation Warning Systems. •Three-Parameter Muskingum Model Coupled with an Improved Bat Algorithm. · Deep Learning with a Long Short-Term Memory Networks Approach for Rainfall-Runoff Simulation
4. Data Story of Natural disasters in India post-Independence
Disasters Events count Total deaths Total affected
Total damage
(million USD)
Drought 13 1,500,320 1,391,841,000 5,441
Earthquake 29 51,915 285,656,623 5,297
Epidemic 63 20,874 421,473 -
Extreme Temperature 59 17,600 - 544
Floods 283 70,343 861,462,744 58,332
Landslides/Avalanche 51 5,083 3,848,421 54
Storm 166 56,991 106,839,232 21,416
Total 664 1,723,126 2,650,069,743 91,086
5. In the last 17
years, India has faced
more than 300 natural
disasters which include
drought, earthquake,
epidemics, extreme
temperature, floods,
landslides and storms.
These disasters have
resulted in
76,031 deaths in this
millennium.
7. Over 2.3 Billion people
are affected due to
floods in last 20 years
and causing countless
death. More than 92
million cattle are lost
every year, seven
million hectares of land
is affected, and damage
is over 5 trillions dollars
when taken globally in
last 5 years.
Flooding occurs
when an extreme
volume of water is
carried by rivers,
creeks and many
other geographical
features into areas
where the water
cannot be drained
adequately.
8.
9. Its due to the
lack of
accurate flood
prediction
system which
can predict the
situation
accurately.
15. Bihar is India’s most
flood-prone State, with
76 percent of the
population, in the north
Bihar living under the
recurring threat of flood
devastation. About
68800 sq Km out of total
geographical area of
94163 sq Km comprising
73.06 percent is flood
affected.
Why Bihar?
16. From 1979 to
Present day
more than 8,873
Humans &
27,573 animals
have lost their
life due to flood.
According to some
historical data,
16.5% of the total
flood affected area
in India is located
in Bihar while
22.1% of the flood
affected population
in India lives
in Bihar.
17.
18. • About 65% of
catchments
area of these
rivers falls in
Nepal/Tibet
and only 35%
of catchments
area lies in
Bihar.
• The plains of Bihar,
adjoining Nepal, are
drained by a number of
rivers that have their
catchments in the steep
and geologically nascent
Himalayas. Kosi,
Gandak,Burhi Gandak,
Bagmati, Kamla Balan,
Mahananda and
Adhwara Group of rivers
originates in Nepal,
carry high discharge and
very high sediment load
and drops it down in the
plains of Bihar.
Complexity of
Challenge
19.
20. • TECHNOLOGY
SUGGESTIONS
• Watson
Studio democratizes
machine learning and
deep learning to
accelerate infusion of AI
in to drive innovation.
• An Intelligent Hydro-
informatics Integration
Platform for Regional
Flood Inundation
Warning Systems.
• Three-
Parameter
Muskingum
Model Coupled
with an
Improved Bat
Algorithm.
• Deep Learning
with a Long
Short-Term
Memory
Networks
Approach for
Rainfall-Runoff
Simulation.
21. SOLUTION
APPROACH
I have studied
several Solutions
for Short-Term
Flood Prediction
Using Single ML
Methods that is
currently been used
in different
geographical
regions across the
world.
Modeling
Technique
Reference
Flood
Resource
Variable
Prediction
Type Region
ANN vs.
statistical
Streamflow
and flash food Hourly USA
NN vs.
traditional
Water and
surge level Hourly Japan
ANN vs.
statistical Flood Real-time UK
ANN vs.
statistical Extreme flow Hourly Greece
FFANN vs.
ANN Water level Hourly India
ANN vs. T–S Flood Hourly India
ANN vs. AR
Stage level
and
streamflow Hourly Brazil
22. Comparative
analysis of
single ML
models for the
prediction of
short-term
floods.
Modelin
g
Techniqu
e
Complexi
ty of
Algorith
m
Ease of
Use Speed Accuracy
Input
Dataset
ANN High Low Fair Fair Historical
BPANN
Fairly
high Low
Fairly
high
Fairly
high Historical
MLP
Fairly
high Fair High
Fairly
high Historical
ELM Fair
Fairly
high
Fairly
high Fair Historical
CART Fair Fair Fair
Fairly
high Historical
SVM
Fairly
high Low Low Fair Historical
ANFIS Fair
Fairly
high Fair
Fairly
high Historical
23. • 1. District wise rainfall monthly
Data from 1901- 2019
• 2.Hydrometer Reading.
• 3.River basin discharge.
• 4.Rainfall forecast in Nepal.
• 5. River basin Catchment Area.
• 6.Death Records Human 1979-
2019.
• 7.Death Records Animals 1979-
2019.
23
DataSets