Dataset Information

Sharpen data-driven prediction rules of individual large earthquakes with aid of Fourier and Gauss.

ABSTRACT: Predicting individual large earthquakes (EQs)' locations, magnitudes, and timing remains unreachable. The author's prior study shows that individual large EQs have unique signatures obtained from multi-layered data transformations. Via spatio-temporal convolutions, decades-long EQ catalog data are transformed into pseudo-physics quantities (e.g., energy, power, vorticity, and Laplacian), which turn into surface-like information via Gauss curvatures. Using these new features, a rule-learning machine learning approach unravels promising prediction rules. This paper suggests further data transformation via Fourier transformation (FT). Results show that FT-based new feature can help sharpen the prediction rules. Feasibility tests of large EQs ([Formula: see text] 6.5) over the past 40 years in the western U.S. show promise, shedding light on data-driven prediction of individual large EQs. The handshake among ML methods, Fourier, and Gauss may help answer the long-standing enigma of seismogenesis.

SUBMITTER: Cho IH

PROVIDER: S-EPMC10520116 | biostudies-literature | 2023 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Sharpen data-driven prediction rules of individual large earthquakes with aid of Fourier and Gauss.

Cho In Ho IH

Scientific reports 20230925 1

Predicting individual large earthquakes (EQs)' locations, magnitudes, and timing remains unreachable. The author's prior study shows that individual large EQs have unique signatures obtained from multi-layered data transformations. Via spatio-temporal convolutions, decades-long EQ catalog data are transformed into pseudo-physics quantities (e.g., energy, power, vorticity, and Laplacian), which turn into surface-like information via Gauss curvatures. Using these new features, a rule-learning mach ...[more]

PMID: 37749367

Similar Datasets

Project description:BackgroundAcute trauma of the wrist is one of the most frequent reasons for visiting the Emergency Department. These patients are routinely referred for radiological examination. Most X-rays however, do not reveal any fractures. A clinical decision rule determining the need for X-rays in patients with acute wrist trauma may help to percolate and select patients with fractures.Methods/designThis study will be a multi-center observational diagnostic study in which the data will be collected cross-sectionally. The study population will consist of all consecutive adult patients (≥18 years) presenting with acute wrist trauma at the Emergency Department in the participating hospitals. This research comprises two components: one study will be conducted to determine which clinical parameters are predictive for the presence of a distal radius fracture in adult patients presenting to the Emergency Department following acute wrist trauma. These clinical parameters are defined by trauma-mechanism, physical examination, and functional testing. This data will be collected in two of the three participating hospitals and will be assessed by using logistic regression modelling to estimate the regression coefficients after which a reduced model will be created by means of a log likelihood ratio test. The accuracy of the model will be estimated by a goodness of fit test and an ROC curve. The final model will be validated internally through bootstrapping and by shrinking it, an adjusted model will be generated. In the second component of this study, the developed prediction model will be validated in a new dataset consisting of a population of patients from the third hospital. If necessary, the model will be calibrated using the data from the validation study.DiscussionWrist trauma is frequently encountered at the Emergency Department. However, to this date, no decision rule regarding this type of trauma has been created. Ideally, radiographs are obtained of all patients entering one of the participating hospitals with trauma to the wrist. However, this is ethically and logistically not feasible and one could argue that patients, for whom no radiography is required according to their physician, are not suspected of having a distal radius fracture and thus are not part of the domain.Trial registrationThis study is registered at the Netherlands Trial Register (NTR 2544) and was granted permission by the Medical Ethical Committee of the Academic Medical Center Amsterdam on 06-01-2011.

Dataset Information

Sharpen data-driven prediction rules of individual large earthquakes with aid of Fourier and Gauss.

Publications

Sharpen data-driven prediction rules of individual large earthquakes with aid of Fourier and Gauss.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets