On-site earthquake early warning: a partially non-ergodic perspective from the site effects point of view

Spallarossa, Daniele; Kotha, Sreeram Reddy; Picozzi, Matteo; Barani, Simone; Bindi, Dino

doi:10.1093/gji/ggy470

Cited by 22 publications

(14 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, the full investigation and explanation of the causes of these site conditions is beyond the aim of this paper. In our opinion, the significant variation in residuals shown in Figure 5A is not surprising, being in agreement with other studies (Spallarossa et al, 2019;Iaccarino et al, 2020); which have recently discussed how to reduce the prediction variability considering site-effect terms in EEW model using the mixed-effect regression approach (Pinheiro and Bates, 2000).…”

Section: Residual Analysissupporting

confidence: 92%

“…In other words, models calibrated combining datasets from different regions are exported to further areas assuming that regional effects do not play role in the model uncertainty (Stafford, 2014). However, results of recent EEW studies (e.g., among others Spallarossa et al, 2019;Iaccarino et al, 2020) have shown the opposite; that is to say, regional characteristics can play an important role in the robustness and accuracy of the EEW predictions, leading to increase the epistemic uncertainty (Al Atik et al, 2010). For this reason, we proceeded setting four different case studies using datasets of increasing order of heterogeneity.…”

Section: Case Studiesmentioning

confidence: 99%

“…Brondi et al (2015) used the Pd and the Integral of squared Velocity, IV 2 to predict the PGV and the Housner Intensity, I H . Spallarossa et al (2019) and Iaccarino et al (2020) explored the use of Pd and the IV 2 and for predicting PGV and the Response Spectra of Acceleration, RSA, amplitudes at nine periods, respectively, using a mixedeffect regression approach aiming to account for site-effects.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Earthquake Early Warning System for Structural Drift Prediction Using Machine Learning and Linear Regressors

et al. 2021

View full text Add to dashboard Cite

In this work, we explored the feasibility of predicting the structural drift from the first seconds of P-wave signals for On-site Earthquake Early Warning (EEW) applications. To this purpose, we investigated the performance of both linear least square regression (LSR) and four non-linear machine learning (ML) models: Random Forest, Gradient Boosting, Support Vector Machines and K-Nearest Neighbors. Furthermore, we also explore the applicability of the models calibrated for a region to another one. The LSR and ML models are calibrated and validated using a dataset of ∼6,000 waveforms recorded within 34 Japanese structures with three different type of construction (steel, reinforced concrete, and steel-reinforced concrete), and a smaller one of data recorded at US buildings (69 buildings, 240 waveforms). As EEW information, we considered three P-wave parameters (the peak displacement, Pd, the integral of squared velocity, IV2, and displacement, ID2) using three time-windows (i.e., 1, 2, and 3 s), for a total of nine features to predict the drift ratio as structural response. The Japanese dataset is used to calibrate the LSR and ML models and to study their capability to predict the structural drift. We explored different subsets of the Japanese dataset (i.e., one building, one single type of construction, the entire dataset. We found that the variability of both ground motion and buildings response can affect the drift predictions robustness. In particular, the predictions accuracy worsens with the complexity of the dataset in terms of building and event variability. Our results show that ML techniques perform always better than LSR models, likely due to the complex connections between features and the natural non-linearity of the data. Furthermore, we show that by implementing a residuals analysis, the main sources of drift variability can be identified. Finally, the models trained on the Japanese dataset are applied the US dataset. In our application, we found that the exporting EEW models worsen the prediction variability, but also that by including correction terms as function of the magnitude can strongly mitigate such problem. In other words, our results show that the drift for US buildings can be predicted by minor tweaks to models.

show abstract

Section: Residual Analysissupporting

confidence: 92%

Section: Case Studiesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Earthquake Early Warning System for Structural Drift Prediction Using Machine Learning and Linear Regressors

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Although the idea was first proposed by Cooper in the mid-19th century [1], EEW systems have only been realized in recent decades thanks to advances in communications, digital seismology, and automatic processing [2]. The development and implementation of EEW systems were summarized in previous studies by Allen et al [3] and Allen and Melgar [4], and it is still an emerging research topic in the community [5][6][7][8][9]. The EEW systems could also incorporate with structural control algorithms for better seismic response reduction [10,11].…”

Section: Introductionmentioning

confidence: 99%

On-Site Earthquake Early Warning Using Smartphones

Hsu

Nieh

2020

Sensors

View full text Add to dashboard Cite

In this study, the measured accelerations of a single smartphone were used to provide an earthquake early warning system. In the presented system, after the smartphone is triggered, the triggering event is then classified as an earthquake event or not. Once an earthquake event is detected, the peak ground acceleration is then predicted every second until 10 s after the trigger. These predictions are made by the neural network classifier and predictor embedded in the smartphone, and an alert can be issued if a large peak ground acceleration is predicted. The proposed system is unique among approaches that use crowdsourcing ideas for earthquake early warning because the proposed system provides on-site earthquake early warning. In general, the accuracy rates of the earthquake classifications and peak ground acceleration predictions of the system were quite high according to the results of large amounts of earthquake and non-earthquake data. More specifically, according to said earthquake data, 96.9% of the issued alerts would be correct and 61.9% of the earthquakes that exceeded the threshold would have resulted in an alert being issued before the arrival of the peak ground acceleration. Among the false negative cases, approximate 97.8% would occur because of negative lead time. Using the shake table tests of worldwide and Meinong earthquake datasets, the proposed approach is confirmed to be quite promising.

show abstract

“…Multiple studies (e.g. Festa et al 2008;Picozzi et al 2018;Spallarossa et al 2019) propose to incorporate the early radiated energy, obtained as the squared velocity integrated over time. As the quantitative results in these studies are obtained in the context of early warning, they can not directly be compared to the results of this study.…”

Section: Multifeature Magnitude Estimation 143 1 Introductionmentioning

confidence: 99%

Low uncertainty multifeature magnitude estimation with 3-D corrections and boosting tree regression: application to North Chile

Münchmeyer

Bindi

Sippl

et al. 2019

Geophysical Journal International

View full text Add to dashboard Cite

SUMMARY Magnitude estimation is a central task in seismology needed for a wide spectrum of applications ranging from seismicity analysis to rapid assessment of earthquakes. However, magnitude estimates at individual stations show significant variability, mostly due to propagation effects, radiation pattern and ambient noise. To obtain reliable and precise magnitude estimates, measurements from multiple stations are therefore usually averaged. This strategy requires good data availability, which is not always given, for example for near real time applications or for small events. We developed a method to achieve precise magnitude estimations even in the presence of only few stations. We achieve this by reducing the variability between single station estimates through a combination of optimization and machine learning techniques on a large catalogue. We evaluate our method on the large scale IPOC catalogue with >100 000 events, covering seismicity in the northern Chile subduction zone between 2007 and 2014. Our aim is to create a method that provides low uncertainty magnitude estimates based on physically meaningful features. Therefore we combine physics based correction functions with boosting tree regression. In a first step, we extract 110 features from each waveform, including displacement, velocity, acceleration and cumulative energy features. We correct those features for source, station and path effects by imposing a linear relation between magnitude and the logarithm of the features. For the correction terms, we define a non-parametric correction function dependent on epicentral distance and event depth and a station specific, adaptive 3-D source and path correction function. In a final step, we use boosting tree regression to further reduce interstation variance by combining multiple features. Compared to a standard, non-parametric, 1-D correction function, our method reduces the standard deviation of single station estimates by up to $57\, {\rm per\, cent}$, of which $17\, {\rm per\, cent}$ can be attributed to the improved correction functions, while boosting tree regression gives a further reduction of $40\, {\rm per\, cent}$. We analyse the resulting magnitude estimates regarding their residuals and relation to each other. The definition of a physics-based correction function enables us to inspect the path corrections and compare them to structural features. By analysing feature importance, we show that envelope and P wave derived features are key parameters for reducing uncertainties. Nonetheless the variety of features is essential for the effectiveness of the boosting tree regression. To further elucidate the information extractable from a single station trace, we train another boosting tree on the uncorrected features. This regression yields magnitude estimates with uncertainties similar to the single features after correction, but without using the earthquake location as required for applying the correction terms. Finally, we use our results to provide high precision magnitudes and their uncertainties for the IPOC catalogue.

show abstract

On-site earthquake early warning: a partially non-ergodic perspective from the site effects point of view

Cited by 22 publications

References 44 publications

Earthquake Early Warning System for Structural Drift Prediction Using Machine Learning and Linear Regressors

Earthquake Early Warning System for Structural Drift Prediction Using Machine Learning and Linear Regressors

On-Site Earthquake Early Warning Using Smartphones

Low uncertainty multifeature magnitude estimation with 3-D corrections and boosting tree regression: application to North Chile

Contact Info

Product

Resources

About