AI Article Synopsis
- Short-term forecasting of maximum magnitude is vital for managing risks related to induced seismicity during fluid stimulation, but traditional methods often need real-time data that isn't always accessible.
- This study presents two deep learning methods that utilize past seismic data patterns: one predicts maximum magnitude directly, while the other estimates seismicity rate and derives maximum magnitude from it.
- Testing on data from western Canada shows that while direct deep learning provides accurate forecasts with some delay, the physics-informed method predicts seismicity rate well but can sometimes misestimate maximum magnitude, potentially indicating the onset of serious faults.
Article Abstract
Short-term forecasting of estimated maximum magnitude ([Formula: see text]) is crucial to mitigate risks of induced seismicity during fluid stimulation. Most previous methods require real-time injection data, which are not always available. This study proposes two deep learning (DL) approaches, along with two data-partitioning methods, that rely solely on preceding patterns of seismicity. The first approach forecasts [Formula: see text] directly using DL; the second incorporates physical constraints by using DL to forecast seismicity rate, which is then used to estimate [Formula: see text]. These approaches are tested using a hydraulic-fracture monitoring dataset from western Canada. We find that direct DL learns from previous seismicity patterns to provide an accurate forecast, albeit with a time lag that limits its practical utility. The physics-informed approach accurately forecasts changes in seismicity rate, but sometimes under- (or over-) estimates [Formula: see text]. We propose that significant exceedance of [Formula: see text] may herald the onset of runaway fault rupture.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10423224 | PMC |
| http://dx.doi.org/10.1038/s41598-023-40403-2 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Association between five novel anthropometric indices and erectile dysfunction in US adults from NHANES database.
Sci Rep
January 2025
TCM gynecology department, Foshan Fosun Chancheng Hospital, Chancheng District, Foshan, Guangdong Province, China.
Erectile Dysfunction (ED) is the leading cause of sexual dysfunction affecting hundreds of millions of men worldwide, and has been described as an important public health problem. The association of five novel anthropometrics related to obesity, lipids and glucose with ED remains unclear. To investigate the association of lipid accumulation products index (LAP), triglyceride glucose index (TyG), waist triglyceride index (WTI), weight-adjusted-waist index (WWI) and a body shape index (ABSI) with ED.
View Article and Find Full Text PDFUnveiling hidden reaction kinetics of carbon dioxide in supercritical aqueous solutions.
Proc Natl Acad Sci U S A
January 2025
Department of Physics, The Hong Kong University of Science and Technology, Hong Kong, China.
Dissolution of CO in water followed by the subsequent hydrolysis reactions is of great importance to the global carbon cycle, and carbon capture and storage. Despite numerous previous studies, the reactions are still not fully understood at the atomistic scale. Here, we combined ab initio molecular dynamics (AIMD) simulations with Markov state models to elucidate the reaction mechanisms and kinetics of CO in supercritical water both in the bulk and nanoconfined states.
View Article and Find Full Text PDFThe false evidence rate: An approach to frequentist error rate control conditioning on the observed value.
Proc Natl Acad Sci U S A
January 2025
Centre for Human Genetics, Nuffield Department of Medicine, University of Oxford, Oxford OX3 7BN, United Kingdom.
A value is conventionally interpreted either as a) the probability by chance of obtaining more extreme results than those observed or b) a tool for declaring significance at a prespecified level. Both approaches carry difficulties: b) does not allow users to make inferences based on the data in hand, and is not rigorously followed by researchers in practice, while (a) is not meaningful as an error rate. Although values retain an important role, these shortcomings are likely to have contributed significantly to the scientific reproducibility crisis.
View Article and Find Full Text PDFA Parametric study on the effects of winglet cant angle on wing aerodynamics and aeroacoustics.
Sci Rep
January 2025
School of Engineering, The University of Manchester, Oxford Road, Manchester, M13 9PL, UK.
The use of winglet devices is an efficient technique for enhancing aerodynamic performance. This study investigates the effects of winglet cant angles on both the aerodynamics and aeroacoustics of a commercial wing, comparing them to other significant parameters using a parametric analysis. A Full Factorial Design method is employed to generate a matrix of experiments, facilitating a detailed exploration of flow physics, with lift-to-drag ratio (L/D) and the integral of Acoustic Power Level (APL) as the primary representatives of aerodynamic and acoustic performance, respectively.
View Article and Find Full Text PDFTime-domain signatures of distinct correlated insulators in a moiré superlattice.
Nat Commun
January 2025
Department of Chemistry, Columbia University, New York, NY, USA.
Among expanding discoveries of quantum phases in moiré superlattices, correlated insulators stand out as both the most stable and most commonly observed. Despite the central importance of these states in moiré physics, little is known about their underlying nature. Here, we use pump-probe spectroscopy to show distinct time-domain signatures of correlated insulators at fillings of one (ν = -1) and two (ν = -2) holes per moiré unit cell in the angle-aligned WSe/WS system.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!