The world’s largest and densest tsunami observing system gives us the leverage to develop a method for a real-time tsunami inundation prediction based on machine learning. Our method utilizes 150 offshore stations encompassing the Japan Trench to simultaneously predict tsunami inundation at seven coastal cities stretching ~100 km along the southern Sanriku coast. We trained the model using 3093 hypothetical tsunami scenarios from the megathrust (Mw 8.0–9.1) and nearby outer-rise (Mw 7.0–8.7) earthquakes. Then, the model was tested against 480 unseen scenarios and three near-field historical tsunami events. The proposed machine learning-based model can achieve comparable accuracy to the physics-based model with ~99% computational cost reduction, thus facilitates a rapid prediction and an efficient uncertainty quantification. Additionally, the direct use of offshore observations can increase the forecast lead time and eliminate the uncertainties typically associated with a tsunami source estimate required by the conventional modeling approach.
This study presents a new method of centroid moment tensor (CMT) data inversion to estimate time‐dependent regional stress fields. The Gaussian process (GP) is applied to resolve the computational difficulty of the existing basis function expansion method when analyzing high‐dimensional data, including time dependence. A critical step in the formulation is an analytical derivation of the relationship of the covariance function, which is a key ingredient of GP, between CMT data and the model stress field based on an observation equation. The validity and efficiency of the proposed method are verified through applications to CMT data in and around Japan after the 2011 Tohoku earthquake. The estimated stress field exhibits small‐scale heterogeneity in space and long‐term stability in time for most regions. Additionally, significant temporal variations are observed around the margin of the focal region of the 2011 event, with opposite changes on landward and oceanward sides. GP would be particularly effective for geophysical inversions of high‐dimensional data distributed over a broad region.
Modeling typhoon-induced storm surges requires 10-m wind and sea level pressure fields as forcings, commonly obtained using parametric models or a fully dynamical simulation by numerical weather prediction (NWP) models. The parametric models are generally less accurate than the full-physics models of the NWP, but they are often preferred owing to their computational efficiency facilitating rapid uncertainty quantification. Here, we propose using a deep learning method based on generative adversarial networks (GAN) to translate the parametric model outputs into a more realistic atmospheric forcings structure resembling the NWP model results. Additionally, we introduce lead-lag parameters to incorporate a forecasting feature in our model. Thirty-four historical typhoon events from 1981 to 2012 are selected to train the GAN, followed by storm surge simulations for the four most recent events. The proposed method efficiently transforms the parametric model into realistic forcing fields by a standard desktop computer within a few seconds. The results show that the storm surge model accuracy with forcings generated by GAN is comparable to that of the NWP model and outperforms the parametric model. Our novel GAN model offers an alternative for rapid storm forecasting and can potentially combine varied data, such as those from satellite images, to improve the forecasts further.
Medical information is valuable information obtained from humans regarding the phenotype of diseases. Omics data is informative to understand diseases at biomolecular level. We aimed to detect patient stratification patterns in a data-driven manner and identify candidate drug targets by investigating biomolecules that are linked to phenotype-level characteristics of a targeted disease. Such data integration is challenging because the data types of them are different, and these data contain many items that are not directly related to the disease. Hence, we developed an algorithm, subset binding, to find inter-related attributes in heterogeneous data. To search for potential drug targets for intractable IPF (idiopathic pulmonary fibrosis), we collected medical information and proteome data of serum extracellular vesicles from patients with interstitial pneumonia including IPF. Our approach detected 20 proteins linked with IPF characteristics, whose expression intensities were confirmed to be high in fibrotic areas of human lung tissues. Furthermore, ponatinib, which inhibits these proteins, suppressed EMT (epithelial mesenchymal transition) in vitro. This workflow paves the way for data-driven drug target discovery even for intractable diseases whose mechanisms of pathogenesis are not fully understood.
Medical information is valuable information obtained from humans regarding the phenotype of diseases. Omics data is informative to understand diseases at biomolecular level. We aimed to detect patient stratification patterns in a data-driven manner and identify candidate drug targets by investigating biomolecules that are linked to phenotype-level characteristics of a targeted disease. Such data integration is challenging because the data types of them are different, and these data contain many items that are not directly related to the disease. Hence, we developed an algorithm, subset binding, to find inter-related attributes in heterogeneous data. To search for potential drug targets for intractable IPF (idiopathic pulmonary fibrosis), we collected medical information and proteome data of serum extracellular vesicles from patients with interstitial pneumonia including IPF. Our approach detected 20 proteins linked with IPF characteristics, whose expression intensities were confirmed to be high in fibrotic areas of human lung tissues. Furthermore, ponatinib, which inhibits these proteins, suppressed EMT (epithelial mesenchymal transition) in vitro. This workflow paves the way for data-driven drug target discovery even for intractable diseases whose mechanisms of pathogenesis are not fully understood.
The movement and deformation of the Earth's crust and upper mantle provide critical insights into the evolution of earthquake processes and future earthquake hazards. Crustal deformation can be modeled by dislocation models that represent an earthquake fault in the crust as a defect in a continuum medium. Forward and inverse modeling have been performed using various analytical methods based on Green's function for linear responses and numerical methods that discretize model regions or boundaries. In this study, we propose a novel physics-informed deep learning approach to model crustal deformation due to earthquakes. This approach obtains continuous solutions using neural networks by representing the governing equations and boundary conditions as a loss function. We use the polar coordinate system to accurately model the displacement discontinuity on a fault as a boundary condition. Neural network modeling enables flexible representation of arbitrary geometrical structures and mechanical properties of rocks, which cannot be achieved via existing methods in practice. We illustrate the validity and usefulness of this approach through example problems such as curved strike-slip faults in heterogeneous elastic media with surface topographies. Furthermore, this approach can be extended to high-dimensional, anelastic, and nonlinear problems in a straightforward manner. We anticipate that the proposed approach will be a starting point for progress in the quantitative assessment of future seismic hazards.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.