arXiv subjects

Pania Newell

Publications and source records attributed to Pania Newell.

4 recordsLinked to original sources

arXiv2026

Connecting Microseismicity to Lithology via a Model of Slip Avalanches

Fluid injection into the earth's crust can induce small and frequent earthquakes in the subsurface. Predicting their sizes and temporal occurrences via statistical analysis is crucial for safe operations in unconventional oil and gas recovery, enhanced geothermal systems, and geologic carbon storage. Here we show that a simple micromechanical model of slip avalanches in slowly deforming solids predicts the slip statistics observed over drastically different spatial scales, namely meter-scale microseismic observations and nanometer- to micrometer-scale nanoindentation experiments can be described with this model. Microseismic catalogs extracted from high-pressure fluid injection operations into geological basins with various lithologies and nanoindentation experiments on shale across a wide range of temperatures and mineral compositions yield statistics consistent with model predictions. This universality across materials, temperatures, and scales is consistent with the prediction that the slip statistics result from only a few basic properties. Previously debated deviations of the statistics in layered sedimentary formations are explained by finite-size and stress-integrative effects resulting from mechanically weak bedding planes. The slip statistics therefore provide important information about the structure and scales of the bedding planes. Conversely, the basin structure can also be used to predict the probability distribution for the sizes of triggered microseismic events.

cond-mat.other↗

arXiv2023

Interpreting and generalizing deep learning in physics-based problems with functional linear models

Although deep learning has achieved remarkable success in various scientific machine learning applications, its opaque nature poses concerns regarding interpretability and generalization capabilities beyond the training data. Interpretability is crucial and often desired in modeling physical systems. Moreover, acquiring extensive datasets that encompass the entire range of input features is challenging in many physics-based learning tasks, leading to increased errors when encountering out-of-distribution (OOD) data. In this work, motivated by the field of functional data analysis (FDA), we propose generalized functional linear models as an interpretable surrogate for a trained deep learning model. We demonstrate that our model could be trained either based on a trained neural network (post-hoc interpretation) or directly from training data (interpretable operator learning). A library of generalized functional linear models with different kernel functions is considered and sparse regression is used to discover an interpretable surrogate model that could be analytically presented. We present test cases in solid mechanics, fluid mechanics, and transport. Our results demonstrate that our model can achieve comparable accuracy to deep learning and can improve OOD generalization while providing more transparency and interpretability. Our study underscores the significance of interpretable representation in scientific machine learning and showcases the potential of functional linear models as a tool for interpreting and generalizing deep learning.

cs.LG↗

arXiv2022

Determining parameters in generalized thermomechanics for metamaterials by means of asymptotic homogenization

Advancement in manufacturing methods enable designing so called metamaterials with a tailor-made microstructure. Microstructure affects materials response within a length-scale, where we model this behavior by using the generalized thermomechanics. Strain gradient theory is employed as a higher-order theory with thermodynamics modeled as a first-order theory. Developing multiphysics models for heterogeneous materials is indeed a challenge and even this ``simplest'' model in generalized thermomechanics causes dozens of parameters to be determined. We develop a computational model by using a given microstructure, modeled as a periodic domain, and numerically calculate all parameters by means of asymptotic homogenization. Finite element method (FEM) is employed with the aid of open-source codes (FEniCS). Some example with symmetric and random distribution of voids in a model problem verifies the method and provides an example at which length-scale we need to consider generalized thermoeleasticity in composite materials.

cs.CE↗

arXiv2022

Machine Learning in Heterogeneous Porous Materials

The "Workshop on Machine learning in heterogeneous porous materials" brought together international scientific communities of applied mathematics, porous media, and material sciences with experts in the areas of heterogeneous materials, machine learning (ML) and applied mathematics to identify how ML can advance materials research. Within the scope of ML and materials research, the goal of the workshop was to discuss the state-of-the-art in each community, promote crosstalk and accelerate multi-disciplinary collaborative research, and identify challenges and opportunities. As the end result, four topic areas were identified: ML in predicting materials properties, and discovery and design of novel materials, ML in porous and fractured media and time-dependent phenomena, Multi-scale modeling in heterogeneous porous materials via ML, and Discovery of materials constitutive laws and new governing equations. This workshop was part of the AmeriMech Symposium series sponsored by the National Academies of Sciences, Engineering and Medicine and the U.S. National Committee on Theoretical and Applied Mechanics.

cs.LG↗