KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/kmitl/1

Browse

Search Results

Now showing 1 - 8 of 8

Some of the metrics are blocked by your
consent settings
Developing data driven framework to model earthquake induced liquefaction potential of granular terrain by machine learning classification models
(2025-12-01)
Onyelowe, Kennedy C.
;
Kamchoom, Viroon
;
Gnananandarao, Tammineni
;
Arunachalam, Krishna P.
Earthquake-inducedliquefaction of soils poses a serious georisk in geotechnical designs, construction and the application of geotechnical structures around the world. In this study, the applicability of three soft computing models for liquefaction classification, a topic of significant importance within the fields of geotechnical and earthquake engineering has been evaluated. Twelve input parameters are used to classify the liquefaction potential for 234 data sets collected from an earthquake-induced liquefaction prone granular material environment. For developing the SVM_Poly, SVM_RBK models, an extensive number of trials were conducted using various combinations of C and d for polynomial kernels and C and ∂ for radial basis function kernel-based support vector machines (SVMs) utilizing user-defined parameters. In the same way, several experiments were conducted with a fixed value of C and ∂ kernel specific parameters in order to determine an appropriate value of error-insensitive zone (∋).Similarly, for the random forest classifier (RFC) model, the number of variables used (m) and the number of trees to be grown (k) are two user-defined parameters. These optimum values of m and k parameters are fixed using trial and error process and the same fixed values. The best model was developed as evidence from the confusion matrixes and statistical indicators. The calculated values of confusion matrixes and statistical indicators for training and testing shows that an accuracy of 0.89 indicates the model is correct in its predictions 89% of the time. A sensitivity of 0.85 signifies the model correctly identifies 85% of actual positive instances, while a specificity of 0.94 implies correct identification of 94% of actual negative instances. A precision of 0.94 suggests that when the model predicts a positive instance, it is correct 94% of the time. The Phi Correlation Coefficient, with a value of 0.82, indicates a strong positive correlation between predicted and actual values.Furthermore, the model exhibits a Mean Absolute Error (MAE) of 0.2351, reflecting a relatively low average error in predictions. The Root Mean Squared Error (RMSE) value of 0.3115 indicates better accuracy in predicting the target variable.Finally, all the developed models exhibit promising performance across various evaluation metrics, with low error measures (MAE and RMSE), high accuracy, and strong performance in correctly identifying both positive and negative instances, as evidenced by sensitivity and specificity. The high precision and Phi Correlation Coefficient further affirm the reliability and accuracy of the model’s predictions. However, among the three models FRC model is the best for classifying the liquefaction. The novelty of this research lies in its comparative evaluation and optimization of SVM_Poly, SVM_RBK, and RFC models using a comprehensive set of seismic and soil parameters to accurately classify earthquake-induced liquefaction potential, with the RFC model demonstrating superior predictive performance.
Some of the metrics are blocked by your
consent settings
Multi-satellite based possible precursory signals detection linked to the 2024 Mw 7.5 Noto Peninsula Japan earthquake
(2025-06-15)
Shahzad, Rasim
;
Shah, Munawar
;
Nabi, Imtiaz
;
Jamjareegulgarn, Punyawi
Satellite-based anomaly detection can provide substantial precursory information linked to impending earthquakes (EQ). The strong EQs are followed by some complex precursory signals both before and after the main shock. For this, different methods and datasets are employed to monitor these disastrous events. In our study, we used the Moderate Resolution Imaging Spectroradiometer (MODIS) satellite to evaluate land surface temperature (LST), the Global Navigation Satellite System (GNSS) to observe total electron content (TEC) variations, Swarm satellites to monitor spatial variations in electron density, and Cosmic satellites were used to measure variations in the vertical profile of electron density to look for the complex precursors of Noto Peninsula Japan EQ of 7.5 Mw (occurred on 1st January 2024). Our objective was to observe both the pre- and post-EQ induced anomalies within 25 days and 10 days of the main shock by integrating the statistical, nonlinear autoregressive network with exogenous inputs (NARX) and continuous wavelet transformation (CWT) methods. We found synchronized and co-located pre-seismic anomalies on December 25 in LST, TEC and electron density. Which was further confirmed using NARX and CWT as well. Additionally, we found some potential post-seismic anomalies. There was an anomalous enhancement in daytime LST, TEC, and electron density on January 2nd with the exception of nighttime LST which showed abrupt increments on the night of the main shock (i.e., January 1st). These findings point towards the strong EQ-induced energy into the atmosphere and ionosphere for more prominent proof of lithosphere-atmosphere–ionosphere coupling (LAIC).
2
Some of the metrics are blocked by your
consent settings
Unveiling Differences in Seismic Response: Comparative Study of Equivalent Linear and Nonlinear Analyses in the Central Coastal Region of Bengkulu, Indonesia
(2025-01-01)
Anggraini, Giovanny Dhebby
;
Mase, Lindung Zalbuin
;
Supriani, Fepy
;
Misliniyati, Rena
;
Amri, Khairul
Seismic response analysis is a key aspect in earthquake geotechnical engineering, as it provides important insights into the behavior of soils when exposed to seismic forces. This research compares equivalent linear and non-linear models in the central coastal region of Bengkulu, which is known for its complex geology and high seismicity. By evaluating the accuracy and reliability of each model in predicting ground motion amplification, this research aims to provide useful recommendations for seismic design. The research method uses one-dimensional equivalent linear and nonlinear propagation modeling, namely Pressure Dependent Hyperbolic (PDH). The analysis resulted in the parameters of Peak Ground Acceleration (PGA), time history acceleration, spectral response acceleration, and amplification factor. The equivalent linear method consistently produced higher values for peak ground acceleration (PGA), spectral response acceleration, time history acceleration, and amplification factor compared to the nonlinear method. The analysis results show that the equivalent linear PGA values are in the range of 0.32g to 0.63g, while the nonlinear values range from 0.20g to 0.52g. The resulting spectral responses are averaged over the design spectrum within 0.2s to 0.9s, which can affect low-to high-ceilinged buildings. The equivalent linear amplification factor has a range of 1.59 to 1.91, while the nonlinear has a range of 0.80 to 1.59. Both methods have their advantages, with the nonlinear approach offering greater accuracy for large seismic events, while the equivalent linear model remains useful for preliminary analysis. Hopefully, these findings will improve the understanding of ground response in coastal areas and provide valuable data for improving infrastructure resilience in earthquake-prone areas around the world.
2
Some of the metrics are blocked by your
consent settings
Possible atmospheric-ionospheric precursors of the 2020 Hotan China earthquake from various satellites
(2024-10-01)
Hameed, Amna
;
Shah, Munawar
;
Ghaffar, Bushra
;
Riaz, Salma
;
Jamjareegulgarn, Punyawi
The earthquake (EQ) precursors from satellites data portray an image of the energy propagation from the lithosphere to atmosphere and then to the ionosphere. Previous studies have often presented detailed discussion on different precursors at various altitudes. However, this study aimed to investigate the anomalies at various altitudes associated with the Hotan China EQ (hypocentral depth: 10 km, latitude 35.5°N, longitude 82.4°E). The goal was to identify pre-and post-seismic anomalies statistically in the conjunction with the wavelet transformation. We observed possible precursors in the atmosphere such as variations in aerosol optical depth, tropopause pressure, relative humidity, latent heat flux, and outgoing longwave radiation in a window of 5–10 days before the seismic event. Moreover, the total electron content had precursors during quiet geomagnetic storm conditions (−20 < Dst ≤ − 40 nT, Kp ≤ 3) beyond the bound within 5–10 days. These findings highlight the potential of using atmospheric and ionospheric parameters to detect seismic anomalies as EQ precursors for improved EQ early warning systems.
1
Some of the metrics are blocked by your
consent settings
Atmospheric precursors from multiple satellites associated with the 2020 Mw 6.5 Idaho (USA) earthquake
(2024-01-01)
Qasim, Muhammad
;
Shah, Munawar
;
Shahzad, Rasim
;
Jamjareegulgarn, Punyawi
Remote sensing has became a powerful tool for identifying lithosphere and atmosphere anomalies associated with the impending Earthquakes (EQs) in the vicinity of seismic breeding zone. In this paper, Land Surface Temperature (LST) of both the daytime and nighttime from the Moderate Resolution Imaging Spectroradiometer (MODIS) along with Air Temperature (AT), Relative Humidity (RH), Air Pressure (AP) and Outgoing Longwave Radiations (OLR) are studied for the 2020 Idaho (USA) EQ of Mw 6.5. We found the EQ induced surface and atmospheric parameters anomalies just one day prior to EQ main shock using statistical analysis. Moreover, we observed a sharp increment in LST and AT followed by the drop in both AP and RH, which are responsible for cooling the hot gases emitted from epicenter during preparation period. Also, we observed a large increase in OLR on the same day confirming these anomalous variations to be related with the main shock. Furthermore, these abrupt variations are also confirmed using neural networks (nonlinear autoregressive network with exogenous inputs (NARX), multilayer perceptron (MLP) and continuous wavelet transformation (CWT). These multi-parameter and multi-technique analyses can contribute to assist in the main shock forecasting in future with an enhanced cluster of satellite observations.
Some of the metrics are blocked by your
consent settings
Possible atmosphere and ionospheric anomalies of the 2019 Pakistan earthquake using statistical and machine learning procedures on MODIS LST, GPS TEC, and GIM TEC
(2021-01-01)
Hafeez, Amna
;
Shah, Munawar
;
Naqvi, Najam Abbas
;
Ehsan, Muhsan
;
Jamjareegulgarn, Punyawi
Identifying atmospheric and ionospheric anomalies based on remote sensing satellites has contributed highly to develop the hypothesis of lithosphere-atmosphere-ionosphere coupling over the earthquake (EQ) epicenter during the seismic preparation period. This article has investigated the variations of potential EQ precursor in daytime and nighttime land surface temperature (LST) before and after the 2019 Pakistan EQ from Moderate Resolution Imaging Spectroradiometer (MODIS) satellite. The nighttime LST values of MODIS exhibit temporal anomalies during nighttime period within a time window of five days before and after the main shock day. Furthermore, the LST values predicted by artificial neural network (ANN) validate the significant enhancement in nighttime time series of MODIS. The nighttime LST anomalies obtained from the observation and ANN prediction are more than 20% and 7% of normal distribution beyond the confidence bounds, respectively, within five days after the main shock. Likewise, the ionospheric anomaly from daily total electron content (TEC) values at Sukkur Global Positioning System (GPS) station confirms the EQ associated ionospheric perturbations on the day after the main shock. The Global Ionospheric Maps (GIMs) also show the TEC anomalies during 1000–1400 LT on September 25, 2019.
Some of the metrics are blocked by your
consent settings
Earthquake Sensor Based on Surface Water Wave in Cylindrical Container
(2019-07-01)
Wardkein, Kawisara
;
Zaechew, Alongkorn
;
Chuamuangphan, Phiphat
;
Wardkien, Paramote
The purposes of the study are to create a seismometer from water surface wave to solve the problem of the spring constant varying and friction of fixpoint pendulum, and to reduce the import seismometer. The operation of the machine uses the light from the LED illumination to the surface of the water that is vibrating due to the force of the earthquake and get the reflected ray back to the receiver (LDR), which will change the light into an electrical signal. The electrical signal will be sent to the portable computer via a sound card, and it is displayed on the screen by the MATLAB program. All the equipment will be assembled inside the PVC pipe that contains the water inside. The Electrical signal as mention above is recorded and the difference of p wave and s wave traveling time is determined. Those are the variables that are used to figure out earthquake magnitude. The system testing consists of 2 steps: 1) a graph showing on the computer screen every time 2.) earthquake magnitude calculated and displayed on the computer screen. From an experimental result, it showed that this technique can detect an earthquake event with R=0.95
Some of the metrics are blocked by your
consent settings
The effects of sumatra-andaman earthquake on total ionospheric electron content (TEC) and ionospheric scintillation of GPS signal in thailand
(2005-12-01)
Theerapatpaiboon, P.
;
Leelaruji, N.
;
Hemmakorn, N.
;
Supnithi, P.
This paper presents the effects of Sumatra-Andaman earthquake (26 December 2004) on the total ionospheric electron content (TEC) by using the TEC Meter (JAVAD) installed at KMITL. From the results, we found that the total ionospheric electron content enhancement at the time of this earthquake is higher than other days about 7 TEC units. Furthermore, the study includes the effect of this phenomenon on GPS signal (1575.45 MHz) by employing S<inf>4</inf> index and σ<inf>φ</inf> (60sec) to identify the severity of amplitude scintillation and phase scintillation, respectively. From the observation, we can conclude that TEC variation is the cause of ionospheric scintillation leading to the position error on GPS about 8 meters. © 2005 IEEE.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results