Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Machine learning reveals cyclic changes in seismic source spectra in Geysers geothermal field.

ABSTRACT: The earthquake rupture process comprises complex interactions of stress, fracture, and frictional properties. New machine learning methods demonstrate great potential to reveal patterns in time-dependent spectral properties of seismic signals and enable identification of changes in faulting processes. Clustering of 46,000 earthquakes of 0.3 < ML < 1.5 from the Geysers geothermal field (CA) yields groupings that have no reservoir-scale spatial patterns but clear temporal patterns. Events with similar spectral properties repeat on annual cycles within each cluster and track changes in the water injection rates into the Geysers reservoir, indicating that changes in acoustic properties and faulting processes accompany changes in thermomechanical state. The methods open new means to identify and characterize subtle changes in seismic source properties, with applications to tectonic and geothermal seismicity.

SUBMITTER: Holtzman BK

PROVIDER: S-EPMC5966224 | biostudies-literature | 2018 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Publications

Machine learning reveals cyclic changes in seismic source spectra in Geysers geothermal field.

Holtzman Benjamin K BK Paté Arthur A Paisley John J Waldhauser Felix F Repetto Douglas D

Science advances 20180523 5

The earthquake rupture process comprises complex interactions of stress, fracture, and frictional properties. New machine learning methods demonstrate great potential to reveal patterns in time-dependent spectral properties of seismic signals and enable identification of changes in faulting processes. Clustering of 46,000 earthquakes of 0.3 < <i>M</i><sub>L</sub> < 1.5 from the Geysers geothermal field (CA) yields groupings that have no reservoir-scale spatial patterns but clear temporal pattern ...[more]

PMID: 29806015

Similar Datasets

Energy-free machine learning force field for aluminum.

Project description:We used the machine learning technique of Li et al. (PRL 114, 2015) for molecular dynamics simulations. Atomic configurations were described by feature matrix based on internal vectors, and linear regression was used as a learning technique. We implemented this approach in the LAMMPS code. The method was applied to crystalline and liquid aluminum and uranium at different temperatures and densities, and showed the highest accuracy among different published potentials. Phonon density of states, entropy and melting temperature of aluminum were calculated using this machine learning potential. The results are in excellent agreement with experimental data and results of full ab initio calculations.

| S-EPMC5561031 | biostudies-other

Discovering geothermal supercritical fluids: a new frontier for seismic exploration.

Project description:Exploiting supercritical geothermal resources represents a frontier for the next generation of geothermal electrical power plant, as the heat capacity of supercritical fluids (SCF),which directly impacts on energy production, is much higher than that of fluids at subcritical conditions. Reconnaissance and location of intensively permeable and productive horizons at depth is the present limit for the development of SCF geothermal plants. We use, for the first time, teleseismic converted waves (i.e. receiver function) for discovering those horizons in the crust. Thanks to the capability of receiver function to map buried anisotropic materials, the SCF-bearing horizon is seen as the 4km-depth abrupt termination of a shallow, thick, ultra-high (>30%) anisotropic rock volume, in the center of the Larderello geothermal field. The SCF-bearing horizon develops within the granites of the geothermal field, bounding at depth the vapor-filled heavily-fractured rock matrix that hosts the shallow steam-dominated geothermal reservoirs. The sharp termination at depth of the anisotropic behavior of granites, coinciding with a 2?km-thick stripe of seismicity and diffuse fracturing, points out the sudden change in compressibility of the fluid filling the fractures and is a key-evidence of deep fluids that locally traversed the supercritical conditions. The presence of SCF and fracture permeability in nominally ductile granitic rocks open new scenarios for the understanding of magmatic systems and for geothermal exploitation.

| S-EPMC5674042 | biostudies-literature

Seismic Stereometry Reveals Preparatory Behavior and Source Kinematics of Intermediate-Size Earthquakes.

Project description:Although moderate-size earthquakes are poorly studied by lack of near-fault observations, they can provide key information about larger damaging earthquakes. Here we propose a new approach, inspired by double-difference relocation, that uses high-coherency waveforms recorded at neighboring sensors, to study the preparation phase and dynamics of moderate-size earthquakes. We validate this technique by analyzing the 2016, M w 5.2 Borrego Springs earthquake in Southern California and find consistent rupture velocities of 2 km/s highlighting two main rupture asperities. The analysis of the 2019, Ml5.2 Le Teil earthquake in France reveals slow nucleation at depth that migrates to the surface and propagates northward with a velocity of ∼2.8 km/s, highlighting two main rupture events also imaged by InSAR. By providing unprecedented resolution in our observation of the rupture dynamics, this approach will be useful in better understanding the preparation phase and rupture of both tectonic and induced earthquakes.

| S-EPMC7583370 | biostudies-literature

Nanotube abundance from non-negative matrix factorization of Raman spectra as an example of chemical purity from open source machine learning.

Project description:The chemical purity of materials is important for semiconductors, including the carbon nanotube material system, which is emerging in semiconductor applications. One approach to get statistically meaningful abundances and/or concentrations is to measure a large number of small samples. Automated multivariate classification algorithms can be used to draw conclusions from such large data sets. Here, we use spatially-mapped Raman spectra of mixtures of chirality-sorted single walled carbon nanotubes dispersed sparsely on flat silicon/silicon oxide substrates. We use non-negative matrix factorization (NMF) decomposition in scikit-learn, an open-source, python language "machine learning" package, to extract spectral components and derive weighting factors. We extract the abundance of minority species (7,5) nanotubes in mixtures by testing both synthetic data, and real samples prepared by dilution. We show how noise limits the purity level that can be evaluated. We determine real situations where this approach works well, and identify situations where it fails.

| S-EPMC9270454 | biostudies-literature

Machine learning of optical properties of materials - predicting spectra from images and images from spectra.

Project description:As the materials science community seeks to capitalize on recent advancements in computer science, the sparsity of well-labelled experimental data and limited throughput by which it can be generated have inhibited deployment of machine learning algorithms to date. Several successful examples in computational chemistry have inspired further adoption of machine learning algorithms, and in the present work we present autoencoding algorithms for measured optical properties of metal oxides, which can serve as an exemplar for the breadth and depth of data required for modern algorithms to learn the underlying structure of experimental materials science data. Our set of 178 994 distinct materials samples spans 78 distinct composition spaces, includes 45 elements, and contains more than 80 000 unique quinary oxide and 67 000 unique quaternary oxide compositions, making it the largest and most diverse experimental materials set utilized in machine learning studies. The extensive dataset enabled training and validation of 3 distinct models for mapping between sample images and absorption spectra, including a conditional variational autoencoder that generates images of hypothetical materials with tailored absorption properties. The absorption patterns auto-generated from sample images capture the salient features of ground truth spectra, and band gap energies extracted from these auto-generated patterns are quite accurate with a mean absolute error of 180 meV, which is the approximate uncertainty from traditional extraction of the band gap energy from measurements of the full transmission and reflection spectra. Optical properties of materials are not only ubiquitous in materials applications but also emblematic of the confluence of underlying physical phenomena yielding the type of complex data relationships that merit and benefit from neural network-type modelling.

| S-EPMC6334722 | biostudies-literature

Machine learning of EEG spectra classifies unconsciousness during GABAergic anesthesia.

Project description:In current anesthesiology practice, anesthesiologists infer the state of unconsciousness without directly monitoring the brain. Drug- and patient-specific electroencephalographic (EEG) signatures of anesthesia-induced unconsciousness have been identified previously. We applied machine learning approaches to construct classification models for real-time tracking of unconscious state during anesthesia-induced unconsciousness. We used cross-validation to select and train the best performing models using 33,159 2s segments of EEG data recorded from 7 healthy volunteers who received increasing infusions of propofol while responding to stimuli to directly assess unconsciousness. Cross-validated models of unconsciousness performed very well when tested on 13,929 2s EEG segments from 3 left-out volunteers collected under the same conditions (median volunteer AUCs 0.99-0.99). Models showed strong generalization when tested on a cohort of 27 surgical patients receiving solely propofol collected in a separate clinical dataset under different circumstances and using different hardware (median patient AUCs 0.95-0.98), with model predictions corresponding with actions taken by the anesthesiologist during the cases. Performance was also strong for 17 patients receiving sevoflurane (alone or in addition to propofol) (median AUCs 0.88-0.92). These results indicate that EEG spectral features can predict unconsciousness, even when tested on a different anesthetic that acts with a similar neural mechanism. With high performance predictions of unconsciousness, we can accurately monitor anesthetic state, and this approach may be used to engineer infusion pumps to intelligibly respond to patients' neural activity.

| S-EPMC8101756 | biostudies-literature

Machine learning of solvent effects on molecular spectra and reactions.

Project description:Fast and accurate simulation of complex chemical systems in environments such as solutions is a long standing challenge in theoretical chemistry. In recent years, machine learning has extended the boundaries of quantum chemistry by providing highly accurate and efficient surrogate models of electronic structure theory, which previously have been out of reach for conventional approaches. Those models have long been restricted to closed molecular systems without accounting for environmental influences, such as external electric and magnetic fields or solvent effects. Here, we introduce the deep neural network FieldSchNet for modeling the interaction of molecules with arbitrary external fields. FieldSchNet offers access to a wealth of molecular response properties, enabling it to simulate a wide range of molecular spectra, such as infrared, Raman and nuclear magnetic resonance. Beyond that, it is able to describe implicit and explicit molecular environments, operating as a polarizable continuum model for solvation or in a quantum mechanics/molecular mechanics setup. We employ FieldSchNet to study the influence of solvent effects on molecular spectra and a Claisen rearrangement reaction. Based on these results, we use FieldSchNet to design an external environment capable of lowering the activation barrier of the rearrangement reaction significantly, demonstrating promising venues for inverse chemical design.

| S-EPMC8409491 | biostudies-literature

Machine learning molecular dynamics for the simulation of infrared spectra.

Project description:Machine learning has emerged as an invaluable tool in many research areas. In the present work, we harness this power to predict highly accurate molecular infrared spectra with unprecedented computational efficiency. To account for vibrational anharmonic and dynamical effects - typically neglected by conventional quantum chemistry approaches - we base our machine learning strategy on ab initio molecular dynamics simulations. While these simulations are usually extremely time consuming even for small molecules, we overcome these limitations by leveraging the power of a variety of machine learning techniques, not only accelerating simulations by several orders of magnitude, but also greatly extending the size of systems that can be treated. To this end, we develop a molecular dipole moment model based on environment dependent neural network charges and combine it with the neural network potential approach of Behler and Parrinello. Contrary to the prevalent big data philosophy, we are able to obtain very accurate machine learning models for the prediction of infrared spectra based on only a few hundreds of electronic structure reference points. This is made possible through the use of molecular forces during neural network potential training and the introduction of a fully automated sampling scheme. We demonstrate the power of our machine learning approach by applying it to model the infrared spectra of a methanol molecule, n-alkanes containing up to 200 atoms and the protonated alanine tripeptide, which at the same time represents the first application of machine learning techniques to simulate the dynamics of a peptide. In all of these case studies we find an excellent agreement between the infrared spectra predicted via machine learning models and the respective theoretical and experimental spectra.

| S-EPMC5636952 | biostudies-literature

A machine learning tool for interpretation of Mass Transport Deposits from seismic data.

Project description:Machine learning is a tool that allows machines or intelligent systems to learn and get equipped to solve complex problems in predicting reliable outcome. The learning process consists of a set of computer algorithms that are employed to a small segment of data with a view to speed up realistic interpretation from entire data without extensive human intervention. Here we present an approach of supervised learning based on artificial neural network to automate the process of delineating structural distribution of Mass Transport Deposit (MTD) from 3D reflection seismic data. The responses, defined by a set of individual attributes, corresponding to the MTD, are computed from seismic volume and amalgamated them into a hybrid attribute. This generated new attribute, called as MTD Cube meta-attribute, does not only define the subsurface architecture of MTD distinctly but also reduces the human involvement thereby accelerating the process of interpretation. The system, after being fully trained, quality checked and validated, automatically delimits the structural geometry of MTDs within the Karewa prospect in northern Taranaki Basin off New Zealand, where MTDs are evidenced.

| S-EPMC7445243 | biostudies-literature

Predicting residential structures from open source remotely enumerated data using machine learning.

Project description:Having accurate maps depicting the locations of residential buildings across a region benefits a range of sectors. This is particularly true for public health programs focused on delivering services at the household level, such as indoor residual spraying with insecticide to help prevent malaria. While open source data from OpenStreetMap (OSM) depicting the locations and shapes of buildings is rapidly improving in terms of quality and completeness globally, even in settings where all buildings have been mapped, information on whether these buildings are residential, commercial or another type is often only available for a small subset. Using OSM building data from Botswana and Swaziland, we identified buildings for which 'type' was indicated, generated via on the ground observations, and classified these into two classes, "sprayable" and "not-sprayable". Ensemble machine learning, using building characteristics such as size, shape and proximity to neighbouring features, was then used to form a model to predict which of these 2 classes every building in these two countries fell into. Results show that an ensemble machine learning approach performed marginally, but statistically, better than the best individual model and that using this ensemble model we were able to correctly classify >86% (using independent test data) of structures correctly as sprayable and not-sprayable across both countries.

| S-EPMC6150517 | biostudies-other

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data