0% found this document useful (0 votes)
15 views9 pages

Literature Review

Uploaded by

Chenna Sanjana
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
15 views9 pages

Literature Review

Uploaded by

Chenna Sanjana
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 9

EARTHQUAKE FORECASTING MODEL

Batch No: 10 Name of the Guide: Ms. Preety Singh


Designation: Assistant Professor
1.22071A66E1-Challa Sai Keerthika Reddy
2.22071A66E5-Chenna Sanjana
3.22071A66F3-Jutla Preethi Chowdary
4.22071A66F4-K.V.Akshay Chowdary

Dept. of CSE- AIML & IOT


VNR VJIET
Abstract
Earthquake forecasting has been a challenging research area, where a future occurrence of the
devastating catastrophe is predicted. The serial components of earthquake monitoring workflows
include detection, arrival time measurement, phase association, location, and magnitude. We
explore the application of ML algorithms for earthquake prediction using a diverse set of data
sources, including seismic data, geophysical measurements, satellite imagery, and socio-economic
indicators. At least two basic categories of earthquake prediction exist: short-term predictions and
forecast ones. Short term earthquake predictions are made hours or days in advance, while
forecasts are predicted months to years in advance. The majority of studies are done on forecast,
taking into consideration the history of earthquakes in specific countries and areas. Our model
provides insights into the potential of ML techniques to enhance earthquake prediction and
contributes to ongoing efforts to develop reliable and accurate early warning systems for seismic
events.
Dept.of CSE- AIML & IOT
VNR VJIET
Introduction
In the realm of earthquake forecasting, the ability to predict the occurrence of these
devastating events remains a formidable challenge. This research delves into the application of
machine learning algorithms to enhance earthquake prediction, leveraging a wide array of data
sources including seismic data, geophysical measurements, and socio-economic indicators. The
serial components of earthquake monitoring workflows, encompassing detection, arrival time
measurement, phase association, location, and magnitude, are explored in the context of ML-
driven approaches.
Two fundamental categories of earthquake prediction are examined: short-term
predictions, which provide forecasts hours or days in advance, and forecast predictions, which
extend months to years ahead. The focus primarily lies on forecast predictions, drawing from
the rich history of seismic events in specific countries and regions. Our model aims to shed light
on the potential of ML techniques to augment earthquake prediction, contributing to the
ongoing endeavor to develop reliable and accurate early warning systems for seismic events.

Dept.of CSE- AIML & IOT


VNR VJIET
Literature Survey
S.No
Title of Title of the Referen Problem or gap Objective of the Focus of the Summary
the Paper Journal ce with addressed paper paper(discuss
DOI methods
used)

Suggestion:
If you feel that you cannot accommodate the table
here u can create a link such that when
It is clicked it will navigate to the table in your laptop.
A sample is shown in the figure on the left

Dept.of CSE- AIML & IOT


VNR VJIET
Existing System
• Traditional classification methods rely on statistical assumptions for earthquakes that turn out to be
unsatisfactory in danger state prediction. Some of it’s features are:
• Seismic Monitoring: Seismologists use a network of seismographs to monitor seismic activity
continuously. These instruments detect and record ground motions caused by earthquakes and
other sources, such as volcanic activity or human-induced events.
• Seismic Analysis: Recorded seismic data are analyzed to identify patterns and trends that may
indicate increased seismic activity or the potential for an earthquake. Scientists look for precursory
signals, such as foreshocks, changes in seismic wave patterns, or ground deformation, which could
suggest the buildup of stress along fault lines.
• Statistical Models: Some earthquake prediction models rely on statistical analysis of historical
earthquake data to assess the likelihood of future earthquakes in a given region. These models
consider factors such as past seismic activity, fault characteristics, and geological features to
estimate earthquake probabilities over
Dept.of time.
CSE- AIML & IOT
VNR VJIET
Research Gap Identified

Dept.of CSE- AIML & IOT


VNR VJIET
Proposed System
• Multivariate Analysis: Explore multivariate analysis techniques to identify correlations
between different types of data and earthquake occurrence. Consider not only seismic
measurements but also environmental, geophysical, and socio-economic variables that may
influence seismic activity.
• Hybrid Approaches: Neural networks and SVMs can be combined into hybrid prediction
models that leverage the strengths of both approaches. By integrating complementary
aspects of neural networks and SVMs, hybrid models can achieve superior performance
compared to individual algorithms alone.
• Real-Time Monitoring and Early Warning Systems: Enhance real-time monitoring
capabilities by deploying more seismic sensors and developing more sophisticated early
warning systems. These systems should be able to detect seismic activity quickly and
accurately, providing timely alerts toAIML
Dept.of CSE- at-risk
& IOT populations.
VNR VJIET
Technical Specifications

Dept.of CSE- AIML & IOT


VNR VJIET
Thank you

Note :Please maintain the decorum of the slides and abide to this format to maintain the
uniformity

Dept.of CSE- AIML & IOT


VNR VJIET

You might also like