Realtime seismic monitoring is of primary importance for rapid and targeted emergency operations after potentially destructive earthquakes. A key aspect in determining the impact of an earthquake is the reconstruction of the groundshaking field, usually expressed as the ground motion parameter. Traditional algorithms compute the groundshaking fields from the punctual data at the stations relying on groundmotion prediction equations (GMPEs) computed on estimates of the earthquake location and magnitude when the instrumental data are missing. The results of such algorithms are then subordinate to the evaluation of location and magnitude, which can take several minutes. The integration of neural networks in the processing workflow has been assessed as a viable way to speed up groundshaking map reconstructions. New datadriven algorithms that leverage the information recorded at the stations have been developed to provide realtime estimates of the groundshaking fields and fill the temporal gap between the arrival of the data and the estimate of these parameters. The first developed algorithm, called ShakeRec, is an endtoend model consisting of an ensemble of convolutional neural networks (CNNs) trained on a database of groundshaking maps produced with traditional algorithms. It provides estimates of the groundshaking maps and their associated uncertainties in real time. Site effects are accounted for using a normalized VS30 map as input. A second algorithm called ShakeRechybrid has been developed to integrate neural networks in the ShakeMap® workflow to speed up the current groundshaking maps evaluation process while overcoming some of the intrinsic limitations of ShakeRec. The core idea is to adopt the multivariate normal distribution (MVN) method used in ShakeMap® for the IM interpolation and use a neural network, based on the convolutional conditional neural process and replacing the GMPEs, to estimate the IM conditional expected value and uncertainty at the target sites based only on data available in realtime. Considering a correlation function independent of the epicentral distance and the event magnitude, the whole workflow became independent from the evaluation of the source parameters resulting in a considerable speedup. By reusing the ShakeMap® framework, the complexity of the model is reduced with improvements in the interpretability of the results. To further improve the interpretability of the results, the local site effects have been accounted for using amplification factors. The developed methods have been tested for their reconstruction capabilities (using real data), robustness to noise, network geometry changes over time, and considering multiple simultaneous events. The adaptability of ShakeRechybrid to different areas is mainly linked to the availability of large datasets to train the network. To overcome this possible limitation two different approaches have been considered. The first approach consists of generating synthetic data to train the neural network: this provides an efficient way to obtain a large training dataset with a high level of control over all the desired parameters, allowing also to target specific scenarios and develop a more balanced dataset. The second approach consists of finetuning a model developed for an area to a different one where only a small dataset of recorded data is available, showing promising results. The two approaches could also be combined either by pretraining the neural network on a synthetic dataset and with a final finetuning stage on real data or by developing larger and more balanced datasets mixing real and synthetic data. The proposed algorithms have been implemented and integrated into BRTT Antelope showing realtime capabilities in handling the data flow from the integrated Italian strong motion network stations and a web service has been developed to disseminate the results in realtime.
Realtime seismic monitoring is of primary importance for rapid and targeted emergency operations after potentially destructive earthquakes. A key aspect in determining the impact of an earthquake is the reconstruction of the groundshaking field, usually expressed as the ground motion parameter. Traditional algorithms compute the groundshaking fields from the punctual data at the stations relying on groundmotion prediction equations (GMPEs) computed on estimates of the earthquake location and magnitude when the instrumental data are missing. The results of such algorithms are then subordinate to the evaluation of location and magnitude, which can take several minutes. The integration of neural networks in the processing workflow has been assessed as a viable way to speed up groundshaking map reconstructions. New datadriven algorithms that leverage the information recorded at the stations have been developed to provide realtime estimates of the groundshaking fields and fill the temporal gap between the arrival of the data and the estimate of these parameters. The first developed algorithm, called ShakeRec, is an endtoend model consisting of an ensemble of convolutional neural networks (CNNs) trained on a database of groundshaking maps produced with traditional algorithms. It provides estimates of the groundshaking maps and their associated uncertainties in real time. Site effects are accounted for using a normalized VS30 map as input. A second algorithm called ShakeRechybrid has been developed to integrate neural networks in the ShakeMap® workflow to speed up the current groundshaking maps evaluation process while overcoming some of the intrinsic limitations of ShakeRec. The core idea is to adopt the multivariate normal distribution (MVN) method used in ShakeMap® for the IM interpolation and use a neural network, based on the convolutional conditional neural process and replacing the GMPEs, to estimate the IM conditional expected value and uncertainty at the target sites based only on data available in realtime. Considering a correlation function independent of the epicentral distance and the event magnitude, the whole workflow became independent from the evaluation of the source parameters resulting in a considerable speedup. By reusing the ShakeMap® framework, the complexity of the model is reduced with improvements in the interpretability of the results. To further improve the interpretability of the results, the local site effects have been accounted for using amplification factors. The developed methods have been tested for their reconstruction capabilities (using real data), robustness to noise, network geometry changes over time, and considering multiple simultaneous events. The adaptability of ShakeRechybrid to different areas is mainly linked to the availability of large datasets to train the network. To overcome this possible limitation two different approaches have been considered. The first approach consists of generating synthetic data to train the neural network: this provides an efficient way to obtain a large training dataset with a high level of control over all the desired parameters, allowing also to target specific scenarios and develop a more balanced dataset. The second approach consists of finetuning a model developed for an area to a different one where only a small dataset of recorded data is available, showing promising results. The two approaches could also be combined either by pretraining the neural network on a synthetic dataset and with a final finetuning stage on real data or by developing larger and more balanced datasets mixing real and synthetic data. The proposed algorithms have been implemented and integrated into BRTT Antelope showing realtime capabilities in handling the data flow from the integrated Italian strong motion network stations and a web service has been developed to disseminate the results in realtime.
Development of machine learning approaches for realtime groundshaking maps reconstruction / Fornasari, SIMONE FRANCESCO.  (2024 Mar 22).
Development of machine learning approaches for realtime groundshaking maps reconstruction
FORNASARI, SIMONE FRANCESCO
20240322
Abstract
Realtime seismic monitoring is of primary importance for rapid and targeted emergency operations after potentially destructive earthquakes. A key aspect in determining the impact of an earthquake is the reconstruction of the groundshaking field, usually expressed as the ground motion parameter. Traditional algorithms compute the groundshaking fields from the punctual data at the stations relying on groundmotion prediction equations (GMPEs) computed on estimates of the earthquake location and magnitude when the instrumental data are missing. The results of such algorithms are then subordinate to the evaluation of location and magnitude, which can take several minutes. The integration of neural networks in the processing workflow has been assessed as a viable way to speed up groundshaking map reconstructions. New datadriven algorithms that leverage the information recorded at the stations have been developed to provide realtime estimates of the groundshaking fields and fill the temporal gap between the arrival of the data and the estimate of these parameters. The first developed algorithm, called ShakeRec, is an endtoend model consisting of an ensemble of convolutional neural networks (CNNs) trained on a database of groundshaking maps produced with traditional algorithms. It provides estimates of the groundshaking maps and their associated uncertainties in real time. Site effects are accounted for using a normalized VS30 map as input. A second algorithm called ShakeRechybrid has been developed to integrate neural networks in the ShakeMap® workflow to speed up the current groundshaking maps evaluation process while overcoming some of the intrinsic limitations of ShakeRec. The core idea is to adopt the multivariate normal distribution (MVN) method used in ShakeMap® for the IM interpolation and use a neural network, based on the convolutional conditional neural process and replacing the GMPEs, to estimate the IM conditional expected value and uncertainty at the target sites based only on data available in realtime. Considering a correlation function independent of the epicentral distance and the event magnitude, the whole workflow became independent from the evaluation of the source parameters resulting in a considerable speedup. By reusing the ShakeMap® framework, the complexity of the model is reduced with improvements in the interpretability of the results. To further improve the interpretability of the results, the local site effects have been accounted for using amplification factors. The developed methods have been tested for their reconstruction capabilities (using real data), robustness to noise, network geometry changes over time, and considering multiple simultaneous events. The adaptability of ShakeRechybrid to different areas is mainly linked to the availability of large datasets to train the network. To overcome this possible limitation two different approaches have been considered. The first approach consists of generating synthetic data to train the neural network: this provides an efficient way to obtain a large training dataset with a high level of control over all the desired parameters, allowing also to target specific scenarios and develop a more balanced dataset. The second approach consists of finetuning a model developed for an area to a different one where only a small dataset of recorded data is available, showing promising results. The two approaches could also be combined either by pretraining the neural network on a synthetic dataset and with a final finetuning stage on real data or by developing larger and more balanced datasets mixing real and synthetic data. The proposed algorithms have been implemented and integrated into BRTT Antelope showing realtime capabilities in handling the data flow from the integrated Italian strong motion network stations and a web service has been developed to disseminate the results in realtime.File  Dimensione  Formato  

Fornasari_PhD_thesis_final.pdf
embargo fino al 22/03/2025
Descrizione: Development of machine learning approaches for realtime groundshaking maps reconstruction  Thesis PhD Fornasari
Tipologia:
Tesi di dottorato
Dimensione
18.36 MB
Formato
Adobe PDF

18.36 MB  Adobe PDF  Visualizza/Apri Richiedi una copia 
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.