Hari Viswanathan
YOU?
Author Swipe
View article: A Foundation Model for Material Fracture Prediction
A Foundation Model for Material Fracture Prediction Open
Accurately predicting when and how materials fail is critical to designing safe, reliable structures, mechanical systems, and engineered components that operate under stress. Yet, fracture behavior remains difficult to model across the div…
View article: Drone-based methane emissions monitoring from orphaned oil and gas wells in Pennsylvania, US
Drone-based methane emissions monitoring from orphaned oil and gas wells in Pennsylvania, US Open
More than a hundred thousand documented orphaned oil and gas wells are known to exist in the United States, with potentially millions remaining undocumented. Due to funding shortfalls, many orphaned wells remain unplugged and continue to e…
View article: SC-03: Application of Machine Learning to Support CCS Deployment
SC-03: Application of Machine Learning to Support CCS Deployment Open
Objective of the workshop is to provide an overview of machine-learning based SMART tools with special emphasis on two tools: SMARTSeis (for site characterization) and ModelExplorer (for Scenario analysis).
View article: Thank You to Our 2024 Reviewers
Thank You to Our 2024 Reviewers Open
On behalf of the journal, AGU, and the scientific community, the editors of Geophysical Research Letters would like to sincerely thank those who reviewed manuscripts in 2024. The hours reading and commenting on manuscripts not only improve…
View article: Deep Learning–Assisted Multiobjective Optimization of Geological CO2 Storage Performance under Geomechanical Risks
Deep Learning–Assisted Multiobjective Optimization of Geological CO2 Storage Performance under Geomechanical Risks Open
Summary In geological CO2 storage, designing the optimal well control strategy for CO2 injection to maximize CO2 storage while minimizing the associated geomechanical risks is not trivial. This challenge arises due to pressure buildup, CO2…
View article: Turning Carbon into Stone: Unlocking Mineralization in Fractured Rock
Turning Carbon into Stone: Unlocking Mineralization in Fractured Rock Open
Carbon mineralization is a promising solution for mitigating greenhouse gas emissions, but we must learn to optimize the complex interplay between reactions and mechanics in fractures to develop a scalable solution.
View article: Learning the factors controlling mineral dissolution in three-dimensional fracture networks: applications in geologic carbon sequestration
Learning the factors controlling mineral dissolution in three-dimensional fracture networks: applications in geologic carbon sequestration Open
We perform a set of high-fidelity simulations of geochemical reactions within three-dimensional discrete fracture networks (DFN) and use various machine learning techniques to determine the primary factors controlling mineral dissolution. …
View article: Mechanistic understanding of carbon mineralization in fracture systems using microfluidics
Mechanistic understanding of carbon mineralization in fracture systems using microfluidics Open
High-pressure microfluidics reveal how fracture flow dynamics control dissolution–precipitation pathways, providing insights into optimizing permanent geologic carbon storage in mafic and ultramafic rock systems.
View article: Complex Fluid‐Driven Fractures Caused by Crack‐Parallel Stress
Complex Fluid‐Driven Fractures Caused by Crack‐Parallel Stress Open
Managing fluid‐driven fracture networks is crucial for subsurface resource utilization, yet the current understanding of the key controlling factors remains insufficient. While geologic discontinuities have been shown to significantly infl…
View article: Patchfinder: Leveraging Visual Language Models for Accurate Information Retrieval using Model Uncertainty
Patchfinder: Leveraging Visual Language Models for Accurate Information Retrieval using Model Uncertainty Open
For decades, corporations and governments have relied on scanned documents to record vast amounts of information. However, extracting this information is a slow and tedious process due to the sheer volume and complexity of these records. T…
View article: Computationally efficient multiscale neural networks applied to fluid flow in complex 3D porous media
Computationally efficient multiscale neural networks applied to fluid flow in complex 3D porous media Open
The permeability of complex porous materials is of interest to many engineering disciplines. This quantity can be obtained via direct flow simulation, which provides the most accurate results, but is very computationally expensive. In part…
View article: Accelerating Multiphase Simulations With Denoising Diffusion Model Driven Initializations
Accelerating Multiphase Simulations With Denoising Diffusion Model Driven Initializations Open
This study introduces a hybrid fluid simulation approach that integrates generative diffusion models with physics‐based simulations, aiming at reducing the computational costs of flow simulations while still honoring all the physical prope…
View article: Carbon Mineralization in Fractured Mafic and Ultramafic Rocks: A Review
Carbon Mineralization in Fractured Mafic and Ultramafic Rocks: A Review Open
Mineral carbon storage in mafic and ultramafic rock masses has the potential to be an effective and permanent mechanism to reduce anthropogenic CO 2 . Several successful pilot‐scale projects have been carried out in basaltic rock (e.g., Ca…
View article: Developing a Foundation Model for Predicting Material Failure
Developing a Foundation Model for Predicting Material Failure Open
Understanding material failure is critical for designing stronger and lighter structures by identifying weaknesses that could be mitigated. Existing full-physics numerical simulation techniques involve trade-offs between speed, accuracy, a…
View article: SMART – A Comprehensive Research and Development Program to Demonstrate Application of Machine Learning for Supporting CCS Deployment
SMART – A Comprehensive Research and Development Program to Demonstrate Application of Machine Learning for Supporting CCS Deployment Open
Presentation material for a paper presented at the GHGT-17 conference, Calgary, Canada, October 20-24, 2024. The objective of the US Department of Energy’s SMART Initiative, i.e., Science-informed Machine Learning (ML) for Accelerating Rea…
View article: Unlocking Solutions: Innovative Approaches to Identifying and Mitigating the Environmental Impacts of Undocumented Orphan Wells in the United States
Unlocking Solutions: Innovative Approaches to Identifying and Mitigating the Environmental Impacts of Undocumented Orphan Wells in the United States Open
In the United States, hundreds of thousands of undocumented orphan wells have been abandoned, leaving the burden of managing environmental hazards to governmental agencies or the public. These wells, a result of over a century of fossil fu…
View article: Aerial imagery dataset of lost oil wells
Aerial imagery dataset of lost oil wells Open
Orphaned wells are wells for which the operator is unknown or insolvent. The location of hundreds of thousands of these wells remain unknown in the United States alone. Cost-effective techniques are essential to locate orphaned wells to ad…
View article: Complementing the CCS Class VI Well Permit Process with DOE-NETL's SMART Initiative Tools and Workflows
Complementing the CCS Class VI Well Permit Process with DOE-NETL's SMART Initiative Tools and Workflows Open
This is a presentation on model explorer developed under SMART initiative Task 2. Our team will present the current progress of the model explorer in using machine learning models to accelerate CCS project at GWPC meeting. Model explorer b…
View article: An integrated experimental–modeling approach to identify key processes for carbon mineralization in fractured mafic and ultramafic rocks
An integrated experimental–modeling approach to identify key processes for carbon mineralization in fractured mafic and ultramafic rocks Open
Controlling atmospheric warming requires immediate reduction of carbon dioxide (CO2) emissions, as well as the active removal and sequestration of CO2 from current point sources. One promising proposed strategy to reduce atmospheric CO2 le…
View article: Sensitivity Analysis in the Presence of Intrinsic Stochasticity for Discrete Fracture Network Simulations
Sensitivity Analysis in the Presence of Intrinsic Stochasticity for Discrete Fracture Network Simulations Open
Large‐scale discrete fracture network (DFN) simulators are standard fare for studies involving the sub‐surface transport of particles since direct observation of real world underground fracture networks is generally infeasible. While these…