On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,181 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “Petrophysics”

Conditioning of three-dimensional generative adversarial networks for pore and reservoir-scale modelsstat.ML

GANs improve 3D petrophysical model generation.

problem Generating accurate 3D petrophysical models for reservoir studies.

method Differentiable neural networks, content and perceptual losses.

result GANs effectively generate conditioned 3D pore and reservoir-scale models.

Generative Adversarial Networks Geostatistics Petrophysics Reservoir Modeling Micro-CT Imaging

2018-02-15abs ↗pdf ↗

Unsupervised clustering of series using dynamic programmingcs.LG

Unsupervised clustering of series using dynamic programming.

problem Clustering coherent segments in multi-variate series.

method Dynamic programming algorithm with constraints.

result Clusters of coherent segments identified using Waxman-Smits equation.

unsupervised clustering dynamic programming coherent segments petrophysical series Waxman-Smits equation

2021-01-23abs ↗pdf ↗

DeepFlow: History Matching in the Space of Deep Generative Modelscs.LG

DeepFlow uses deep generative models to solve history matching problems.

problem Calibrating reservoir models with transient fluid data.

method Generative adversarial network for property distribution, gradient descent on latent variables, and additional well constraints.

result Solves history matching problems for synthetic reservoir models.

history matching reservoir modeling deep generative models inverse problem petrophysical properties

2019-05-14abs ↗pdf ↗

A One class Classifier based Framework using SVDD : Application to an Imbalanced Geological Datasetcs.LG

Evaluation of hydrocarbon reservoir requires classification of petrophysical properties from available dataset. However, characterization of reservoir attributes is difficult due to the nonlinear and heterogeneous nature of the subsurface physical properties. In this context, present study proposes a generalized one cl…

2016-12-02abs ↗pdf ↗

Stochastic seismic waveform inversion using generative adversarial networks as a geological priorphysics.geo-ph

Generative models improve seismic wave inversion for subsurface structure.

problem Inaccurate subsurface geological structures in seismic inversion.

method Combining GAN for geological priors with PDE solution for wave propagation, using approximate MALA sampling.

result Efficient Bayesian inversion yields diverse realizations of subsurface structures matching seismic observations.

seismic inversion generative models wave propagation Bayesian inference partial differential equations

2018-06-10abs ↗pdf ↗