Earthquake Risk Prediction With Artificial Intelligence Methods

Earthquake Risk Prediction With Artificial Intelligence Methods

Ayşe Berika Varol Malkoçoğlu, Zeynep Orman, Ruya Samli
DOI: 10.4018/978-1-6684-6015-3.ch007
OnDemand:
(Individual Chapters)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Earthquakes are one of the most difficult natural phenomena in human history to predict. Today, despite very advanced technologies, earthquake predictions still have not been conclusive. It is especially known that the trilogy of location, time, and magnitude is quite difficult to predict at the same time. In order to discover this powerful natural phenomenon, scientists are trying to collect and make sense of the parameters affecting the earthquake and the earthquake results. In general, their goal is to determine the characteristics that have an impact on earthquakes, to perform classifications thanks to various artificial intelligence algorithms, and to predict future earthquakes. The aim of this study is to compile, examine, and analyze earthquake risk prediction researches or applications carried out using artificial intelligence methods. The studies obtained as a result of the literature review were grouped according to the metrics used, data sets, features, and models used and evaluated according to the success rates obtained.
Chapter Preview
Top

Background

In order to better understand the literature review section, this section will focus on earthquake magnitude types and some data sets used in earthquake prediction approaches. Although the data types are different, all of this data is used in the study to estimate the loss of earthquakes, lives, or property.

Magnitude Types

The magnitude is derived from the energy released by the earthquake. It allows us to express the magnitude of the earthquake numerically. In this way, we can determine the corresponding effects of magnitude levels by categorizing earthquakes.

The general purpose of the AI-based studies examined in this chapter is to predict the magnitude of earthquakes and to take precautions without overestimating the possible effects. Previous earthquake data of the designated region are used to develop earthquake prediction models with artificial intelligence methods. The measurement of calculated earthquake data is carried out indirectly. In other words, by studying the effects of earthquakes, magnitude is calculated, and various magnitude values that define earthquakes are obtained using multiple methods (Kandilli Observatory, 2021; British Columbia Institute of Technology Department of Civil Engineering, 2021). These are the ones that are going to;

  • Time-dependent magnitude (Md): Measurement is made using the duration of vibration in the seismometer. Magnitude range ~4.0 or smaller.

  • Local magnitude (Ml): Measurement is made using the amplitude of the sound wave. Magnitude range ~ 2.0 to ~6.5.

  • Surface wave magnitude (Ms): Measurement is made using wave amplitude emitted from the epicenter to the environment. Magnitude range ~ 5.5 to ~8.5.

  • Body wave magnitude (Mb): Measurement is made using sound waves and cutting waves. Magnitude range ~ 5.5 to ~7.0.

  • Momentum magnitude (Mw): Calculated by performing a mathematical model of earthquake formation. Magnitude range ~ 5.0 and above.

Table 1 lists the earthquake magnitude scale and its effects.

Table 1.
Earthquake magnitude scale and effects
MagnitudeClassEffect
2.5 or less-It is usually not felt but can be recorded with a seismograph.
3.0 – 3.9MinorIt is usually felt but can only cause minor damage.
4.0 – 4.9LightIt is usually felt but can only cause minor damage.
5.0 – 5.9ModerateIt can damage buildings and other structures.
6.0 – 6.9StrongIt can cause a lot of damage in multipopulated areas.
7.0 – 7.9MajorIt can cause very serious damage in multipopulated areas.
8.0 or greaterGreatIt could completely destroy communities close to the epicenter. It's a total earthquake.

Complete Chapter List

Search this Book:
Reset