Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “complex network”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,387 records · Page 77
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Synthetic Scientific Image Generation with VAE, GAN, and Diffusion Model Architectures

Generative AI (genAI) has emerged as a powerful tool for synthesizing diverse and complex image data, offering new possibilities for scientific imaging applications. This review presents a comprehensive comparative analysis of leading generative architectures, ranging from Variational Autoencoders (VAEs) to Generative Adversarial Networks (GANs) on through to Diffusion Models, in the context of scientific image synthesis. We examine each model's foundational principles, recent architectural advancements, and practical trade-offs. Our evaluation, conducted on domain-specific datasets including microCT scans of rocks and composite fibers, as well as high-resolution images of plant roots, integrates both quantitative metrics (SSIM, LPIPS, FID, CLIPScore) and expert-driven qualitative assessments. Results show that GANs, particularly StyleGAN, produce images with high perceptual quality and structural coherence. Diffusion-based models for inpainting and image variation, such as DALL-E 2, delivered high realism and semantic alignment but generally struggled in balancing visual fidelity with scientific accuracy. Importantly, our findings reveal limitations of standard quantitative metrics in capturing scientific relevance, underscoring the need for domain-expert validation. We conclude by discussing key challenges such as model interpretability, computational cost, and verification protocols, and discuss future directions where generative AI can drive innovation in data augmentation, simulation, and hypothesis generation in scientific research.

Generative Adversarial Networks↗
DOE OSTI2024

Iodine speciation in basaltic melts at depth

The speciation of iodine in basalts has been investigated by combining in situ X-ray diffraction at high pressures and temperatures up to 4.9 GPa and 1600 °C, and Raman spectroscopy on recovered high pressure glasses at ambient conditions. Both methods point to iodine being oxidized in basalts, whether molten or quenched as glasses. Observed interatomic distances and Raman vibrational modes are consistent with iodine being dissolved as complex iodate groups alike polyiodates or periodates, not as IO$^-_3$ groups. Iodine speciation in basalts therefore seems to reflect a trend amongst halogens, with lighter chlorine bonding to network modifying cations, and bromine changing affinity from network modifying cations to oxygen anions under pressure. In the absence of a fluid aqueous phase, iodine could thus reach the Earth’s surface in basaltic magmas as an oxide, not as a reduced species.

58 GEOSCIENCES↗
DOE OSTI2020

Lighting controls: not just for lighting anymore!

For the last few years, networked lighting controls (NLCs) have promised significant energy savings beyond what is achieved through a basic LED retrofit. At the same time, NLCs can substantially increase the cost and complexity of the lighting retrofit. And as lighting system wattage declines because of the increasing efficiency of LEDs, advanced controls have less lighting energy to save and the cost-effectiveness of the NLC investment decreases. But NLCs can be leveraged to achieve significant energy savings and value by enhancing control of other building systems. Integrating NLC with control of heating, ventilation and air conditioning (HVAC), plug load control, space utilization, and grid services all enhance the value of your NLC investment. There are already a few NLC products on the market that are capable of providing these enhanced benefits. Manufacturers and entrepreneurs are working hard to expand the impact of these products. But does system interoperability work? Can it be deployed at scale? Slipstream, NEEA and Pacific Northwest National Laboratory (PNNL) have all been attempting to answer these questions in recent pilot projects and describe the outcomes in this paper.

Hackel, Scott↗
DOE OSTI2022

Resilience Design Patterns: A Structured Approach to Resilience at Extreme Scale (V.2.0)

Reliability is a serious concern for future extreme-scale high-performance computing (HPC) systems. Projections based on the current generation of HPC systems and technology roadmaps suggest the prevalence of very high fault rates in future systems. The errors resulting from these faults will propagate and generate various kinds of failures, which may result in outcomes ranging from result corruptions to catastrophic application crashes. Therefore, the resilience challenge for extreme-scale HPC systems requires coordination between various hardware and software technologies that are capable of handling a broad set of fault models at accelerated fault rates. Also, due to practical limits on power consumption in future HPC systems, they are likely to embrace innovative architectures, increasing the levels of hardware and software complexities. Therefore, the techniques that seek to improve resilience must navigate the complex trade-off space between resilience and the overheads to power consumption and performance. While the HPC community has developed various resilience solutions, application-level techniques as well as system-based solutions, the solution space of HPC resilience techniques remains fragmented. There are no formal methods to integrate the various HPC resilience techniques into composite solutions, nor are there methods to holistically evaluate the adequacy and efficacy of such solutions in terms of their protection coverage, and their performance & power efficiency characteristics. Additionally, few implementations of current resilience solutions are portable to newer architectures and software environments that will be deployed on future systems. We developed a new structured approach to the management of HPC resilience using the concept of resilience-based design patterns. In general, a design pattern is a repeatable solution to a commonly occurring problem. We identified the well-known solutions that are commonly used to deal with faults, errors and failures in HPC systems. In the initial design patterns specification (version 1.0), we described the various solutions, which address specific problems in the design of resilient HPC environments, in the form of patterns. Each pattern describes a problem caused by a fault, error or failure event in an HPC environment, and then describes the core of the solution of the problem in such a way that this solution may be adapted to different systems and implemented at different layers of the system stack. The catalog of these resilience design patterns provides designers with a collection of design elements. To construct complete resilience solutions using combinations of various patterns, we defined a framework that enhances HPC designers' understanding of the important constraints and the opportunities for the design patterns to be implemented and deployed at various layers of the system stack. The design framework is also useful for establishing interfaces and mechanisms to coordinate flexible fault management across hardware and software components, as well as to consider the trade-off between performance, resilience, and power consumption when constructing a solution. The resilience design patterns specification version 1.1 included more detailed explanations of the pattern solutions, the context in which the patterns are applicable, and the implications for hardware or software design. It also provided several additional examples and detailed case studies to demonstrate the use of patterns to build realistic solutions. In version 1.2 of the specification document, we have improved the pattern descriptions, including graphical representations of the pattern components. These improvements are largely based on critical comments, feedback and suggestions received from pattern experts and readers of the previous versions of the specification. The pattern classification has been modified to further clarify the relationships between pattern categories. This version of the specification also introduces a pattern language for resilience design patterns. The pattern language presents the patterns in the catalog as a network, revealing the relations among the resilience patterns. The language provides designers with the means to explore alternative techniques for handling a specific fault model that may have different efficiency and complexity characteristics. Using the pattern language also enables the design and implementation of comprehensive resilience solutions as a set of interconnected resilience patterns that can be instantiated across layers of the system stack. The overall goal of this work is to provide hardware and software designers, as well as the users and operators of HPC systems, a systematic methodology for the design and evaluation of resilience technologies in HPC systems that keep scientific applications running to a correct solution in a timely and cost-efficient manner despite frequent faults, errors, and failures of various types. Version 2.0 expands the resilience design pattern classification and catalog to include self-stabilization patterns and reliability, availability and performance models for each structural pattern.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Comparison between explicit and implicit discretization strategies for a dissipative thermal environment

We investigate strategies for simulating open quantum systems coupled to dissipative baths by comparing explicit wave function-based discretization [via multi-layer multi-configuration time-dependent Hartree (ML-MCTDH)] and the implicit density matrix-based master equation method [via tree tensor network hierarchical equations of motion (TTN-HEOM)]. For dissipative baths characterized by exponentially decaying bath correlation functions, the implicit discretization approach of HEOM—rooted in bath correlation function decompositions—proves significantly more efficient than explicit discretization of the bath into discrete harmonic modes. Explicit methods, like ML-MCTDH, require extensive mode discretization to approximate continuum baths, leading to computational bottlenecks. Case studies for two-level systems and a Fenna–Matthews–Olson complex model highlight TTN-HEOM’s superiority in capturing dissipative dynamics with relaxations with a minimal number of auxiliary modes, while the explicit methods are as exact as the HEOM in pure dephasing regimes. This comparison is enabled by the TENSO package, which has both ML-MCTDH and TTN-HEOM implemented using the same computational structure and propagation strategy.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Frame invariant neural network closures for Kraichnan turbulence

Numerical simulations of geophysical and atmospheric flows have to rely on parameterizations of subgrid scale processes due to their limited spatial resolution. Despite substantial progress in developing parameterization (or closure) models for subgrid scale (SGS) processes using physical insights and mathematical approximations, they remain imperfect and can lead to inaccurate predictions. In recent years, machine learning has been successful in extracting complex patterns from high-resolution spatio-temporal data, leading to improved parameterization models, and ultimately better coarse grid prediction. However, the inability to satisfy known physics and poor generalization hinders the application of these models for real-world problems. In this work, we put forth a frame invariant closure approach to improve the accuracy and generalizability of deep learning-based subgrid scale closure models by embedding physical symmetries directly into the structure of the neural network. Specifically, we utilized specialized layers within the convolutional neural network in such a way that desired constraints are theoretically guaranteed without the need for any regularization terms. We demonstrate our framework for a two-dimensional decaying turbulence test case mostly characterized by the forward enstrophy cascade. We show that our frame invariant SGS model (i) accurately predicts the subgrid scale source term, (ii) respects the physical symmetries such as translation, Galilean, and rotation invariance, and (iii) is numerically stable when implemented in coarse-grid simulation with generalization to different initial conditions and Reynolds number. This work opens up a possibility of connecting physics-based theories and data-driven modeling paradigms, and thus represents a promising step towards the development of physically consistent data-driven turbulence closure models.

42 ENGINEERING↗
DOE OSTI2024

Lie–Poisson Neural Networks (LPNets): Data-based computing of Hamiltonian systems with symmetries

An accurate data-based prediction of the long-term evolution of Hamiltonian systems requires a network that preserves the appropriate structure under each time step. Every Hamiltonian system contains two essential ingredients: the Poisson bracket and the Hamiltonian. Hamiltonian systems with symmetries, whose paradigm examples are the Lie–Poisson systems, have been shown to describe a broad category of physical phenomena, from satellite motion to underwater vehicles, fluids, geophysical applications, complex fluids, and plasma physics. The Poisson bracket in these systems comes from the symmetries, while the Hamiltonian comes from the underlying physics. We view the symmetry of the system as primary, hence the Lie–Poisson bracket is known exactly, whereas the Hamiltonian is regarded as coming from physics and is considered not known, or known approximately. Using this approach, we develop a network based on transformations that exactly preserve the Poisson bracket and the special functions of the Lie–Poisson systems (Casimirs) to machine precision. We present two flavors of such systems: one, where the parameters of transformations are computed from data using a dense neural network (LPNets), and another, where the composition of transformations is used as building blocks (G-LPNets). We also show how to adapt these methods to a larger class of Poisson brackets. We apply the resulting methods to several examples, such as rigid body (satellite) motion, underwater vehicles, a particle in a magnetic field, and others. The methods developed in this paper are important for the construction of accurate data-based methods for simulating the long-term dynamics of physical systems.

Data-based modeling↗
DOE OSTI2023

Scalable simulation of coupled adsorption and transport of methane in confined complex porous media with density preconditioning

The growing significance of shales and tight formations in the transition to less carbon-intensive and clean energy drives the research endeavor to understand the physics of gas flow within these systems. However, shales are composed of massively heterogeneous physical and chemical features. Most nano-sized pores connect to millimeter-scale fractures, leading to multiscale transport. These nano-scale pore throats demonstrate non-classical flow behavior, such as non-negligible slip velocities and adsorbed gas layers at the boundary. As a result, classical computational fluid dynamics models do not capture the physics. In this work, we develop a coupling scheme for the multiple-relaxation-time (MRT) lattice Boltzmann (LB) method that integrates the Peng-Robinson equation of state into a pseudo-potential interaction model to capture the physics of methane flow in irregular networks of channels that represent nano-scale porous media. We use atomistic simulations to calibrate and validate our model in slit nano-channels. We propose a preconditioning scheme to initialize the coupled transport and adsorption simulation of methane in complex porous media. The results of this implementation of LB agree with Direct Simulation Monte Carlo (DSMC) and Molecular Dynamics (MD) simulations. We then scale up the LB implementation through vectorization and indirect addressing. We parallelize it using Message Passing Interface (MPI) and OpenMP frameworks to simulate transport and adsorption in complex media with a million lattices. Additionally, we analyze the differences between coupled and transport-only simulations in two case studies and show that considering phase behavior, i.e., adsorption, can significantly change the flow behavior. This work constitutes an important step towards bridging the gap between molecular flow and system-scale behavior of complex disordered porous media.

42 ENGINEERING↗
DOE OSTI2022

Organizational Principles of Hyporheic Exchange Flow and Biogeochemical Cycling in River Networks Across Scales

Hyporheic zones increase freshwater ecosystem resilience to hydrological extremes and global environmental change. However, current conceptualizations of hyporheic exchange, residence time distributions, and the associated biogeochemical cycling in streambed sediments do not always accurately explain the hydrological and biogeochemical complexity observed in streams and rivers. Specifically, existing conceptual models insufficiently represent the coupled transport and reactivity along groundwater and surface water flow paths, the role of autochthonous organic matter in streambed biogeochemical functioning, and the feedbacks between surface-subsurface ecological processes, both within and across spatial and temporal scales. While simplified approaches to these issues are justifiable and necessary for transferability, the exclusion of important hyporheic processes from our conceptualizations can lead to erroneous conclusions and inadequate understanding and management of interconnected surface water and groundwater environments. This is particularly true at the landscape scale, where the organizational principles of spatio-temporal dynamics of hyporheic exchange flow (HEF) and biogeochemical processes remain largely uncharacterized. This article seeks to identify the most important drivers and controls of HEF and biogeochemical cycling based on a comprehensive synthesis of findings from a wide range of river systems. We use these observations to test current paradigms and conceptual models, discussing the interactions of local-to-regional hydrological, geomorphological, and ecological controls of hyporheic zone functioning. This improved conceptualization of the landscape organizational principles of drivers of HEF and biogeochemical processes from reach to catchment scales will inform future river research directions and watershed management strategies.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2021

AENET–LAMMPS and AENET–TINKER : Interfaces for accurate and efficient molecular dynamics simulations with machine learning potentials

Machine-learning potentials (MLPs) trained on data from quantum-mechanics based first-principles methods can approach the accuracy of the reference method at a fraction of the computational cost. To facilitate efficient MLP-based molecular dynamics and Monte Carlo simulations, an integration of the MLPs with sampling software is needed. Here, we develop two interfaces that link the atomic energy network (ænet) MLP package with the popular sampling packages TINKER and LAMMPS. The three packages, ænet, TINKER, and LAMMPS, are free and open-source software that enable, in combination, accurate simulations of large and complex systems with low computational cost that scales linearly with the number of atoms. Scaling tests show that the parallel efficiency of the ænet–TINKER interface is nearly optimal but is limited to shared-memory systems. The ænet–LAMMPS interface achieves excellent parallel efficiency on highly parallel distributed memory systems and benefits from the highly optimized neighbor list implemented in LAMMPS. We demonstrate the utility of the two MLP interfaces for two relevant example applications: the investigation of diffusion phenomena in liquid water and the equilibration of nanostructured amorphous battery materials.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Deciphering the Cofilin Oligomers via Intermolecular Disulfide Bond Formation: A Coarse-Grained Molecular Dynamics Approach to Understanding Cofilin’s Regulation on Actin Filaments

Cofilin, a key actin-binding protein, orchestrates the dynamics of the actomyosin network through its actin-severing activity and by promoting the recycling of actin monomers. Recent experimental work suggests that cofilin also forms functionally distinct oligomers through thiol post-translational modification (PTM) that encourages actin nucleation and assembly. Despite these advances, the structural conformations of cofilin oligomers that modulate actin activity remain elusive because there are combinatorial ways to oxidize thiols in cysteines to form disulfide bonds rapidly. This study employs molecular dynamics simulations to investigate human cofilin 1 as a case study for exploring cofilin dimers via disulfide bond formation. Using the free energy profiling, our simulations unveil a range of probable cofilin dimer structures not represented in current Protein Data Bank entries. These candidate dimers are characterized by their distinct population distributions and relative free energies. Of particular note is a dimer featuring an interface between cysteines 139 and 147 residues, which demonstrates stable free energy characteristics and intriguingly symmetrical geometry. In contrast, the experimentally proposed dimer structure exhibits a less stable free energy profile. Here, we also evaluate frustration quantification based on the energy landscape theory in the protein-protein interactions at the dimer interfaces. Notably, the 39-39 dimer configuration emerges as a promising candidate for forming cofilin tetramers, as substantiated by frustration analysis. Additionally, docking simulations with actin filaments further evaluate the stability of these cofilin dimer-actin complexes. Our findings thus offer a computational framework for understanding the role of thiol post-translational modification cofilin proteins in regulating oligomerization, and the subsequent cofilin-mediated actin dynamics in the actomyosin network.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Quantum coherent energy transport in the Fenna–Matthews–Olson complex at low temperature

In the primary step of natural light harvesting, the solar photon energy is captured in a photoexcited electron–hole pair, or an exciton, in chlorophyll. Its conversion to chemical potential occurs in the special pair reaction center, which is reached by downhill ultrafast excited-state energy transport through a network of chromophores. Being inherently quantum, transport could in principle occur via a matter wave, with vast implications for efficiency. How long a matter wave remains coherent is determined by the intensity by which the exciton is disturbed by the noisy biological environment. The stronger this is, the stronger the electronic coupling between chromophores must be to overcome the fluctuations and phase shifts. The current consensus is that under physiological conditions, quantum coherence vanishes on the 10-fs time scale, rendering it irrelevant for the observed picosecond transfer. Yet, at low-enough temperature, quantum coherence should in principle be present. Here, we reveal the onset of longer-lived electronic coherence at extremely low temperatures of ∼20 K. Using two-dimensional electronic spectroscopy, we determine the exciton coherence times in the Fenna–Matthew–Olson complex over an extensive temperature range. At 20 K, coherence persists out to 200 fs (close to the antenna) and marginally up to 500 fs at the reaction center. It decays markedly faster with modest increases in temperature to become irrelevant above 150 K. At low temperature, the fragile electronic coherence can be separated from the robust vibrational coherence, using a rigorous theoretical analysis. We believe that by this generic principle, light harvesting becomes robust against otherwise fragile quantum effects.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2026

Optimizing Cryo-Focused Pyrolysis GC/MS for Tracing Soil Organic Matter Across Diverse Ecosystems

The cycling of organic matter in terrestrial soils and sediments is central to a range of biogeochemical processes that regulate nutrient cycling, crop productivity, trace gas emissions, and contaminant transport. Pyrolysis-gas chromatography/mass spectrometry (py-GC/MS) is a powerful tool for characterizing bulk soil organic matter (SOM) at the molecular level. In this study, we used a cryo-focused py-GC/MS system to analyze soil samples from seven diverse ecosystems: vernal pool, prairie pothole, temperate forest, tropical forest, tundra, wildfire-affected boreal forest, and grassland. We addressed a key bottleneck in molecular-level SOM characterization by developing an automated data analysis pipeline to optimize py-GC/MS and complementary evolved gas analysis/mass spectrometry (EGA/MS) methods, incorporating advanced tools for peak deconvolution, developing a custom compound class library, and implementing fragmentation spectrum-based molecular networking for the first time. This improved workflow was applied to soil samples from all seven ecosystems, including multiple depths and density fractions. Our findings demonstrate that ecosystem type plays a dominant role in shaping compositional differences in SOM. We also identified trends in the source of SOM compounds (e.g., microbial vs plantderived) across soil depth and density fractions, which are critical for understanding persistence and turnover of SOM. Our molecular networking analysis indicated that although many compounds are widespread across ecosystems, others are restricted to specific environments, such as wetlands. This underscores the utility of molecular-level data in elucidating the complexity of SOM composition and the environmental drivers that shape it. Such molecular-level insights can deepen our knowledge of biogeochemical SOM cycles.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Echo state network for coarsening dynamics of charge density waves

An echo state network (ESN) is a type of reservoir computer that uses a recurrent neural network with a sparsely connected hidden layer. Compared with other recurrent neural networks, one great advantage of ESN is the simplicity of its training process. Yet, despite the seemingly restricted learnable parameters, ESN has been shown to successfully capture the spatial-temporal dynamics of complex patterns. Here we build an ESN to model the coarsening dynamics of charge-density waves (CDWs) in a semiclassical Holstein model, which exhibits a checkerboard electron density modulation at half-filling stabilized by a commensurate lattice distortion. The inputs to the ESN are local CDW order parameters in a finite neighborhood centered around a given site, while the output is the predicted CDW order of the center site at the next time step. Special care is taken in the design of couplings between hidden layer and input nodes to ensure lattice symmetries are properly incorporated into the ESN model. Since the model predictions depend only on CDW configurations of a finite domain, the ESN is scalable and transferrable in the sense that a model trained on dataset from a small system can be directly applied to dynamical simulations on larger lattices. Furthermore, our work opens avenues for efficient dynamical modeling of pattern formations in functional electron materials.

2-dimensional systems↗
DOE OSTI2020

Hydrogen-Bond-Driven Chemical Separations: Elucidating the Interfacial Steps of Self-Assembly in Solvent Extraction

Chemical separations, particularly liquid extractions, are pervasive in academic and industrial laboratories, yet a mechanistic understanding of the events governing their function are obscured by interfacial phenomena that are notoriously difficult to measure. In this work, we investigate the fundamental steps of ligand self-assembly as driven by changes in the interfacial H-bonding network using vibrational sum frequency generation. Our results show how the bulk pH modulates the interfacial structure of extractants at the buried oil/aqueous interface via the formation of unique H-bonding networks that order and bridge ligands to produce self-assembled aggregates. These extended H-bonded structures are key to the subsequent extraction of Co2+ from the aqueous phase in promoting micelle formation and subsequent ejection of the said micelle into the oil phase. The combination of static and time-resolved measurements reveals the events underlying complexities of liquid extractions at high [Co2+]:[ligand] ratios by showing an evolution of interfacially assembled structures that are readily tuned on a chemical basis by altering the compositions of the aqueous phase. The results of this work point to new principles to design-applied separations through the manipulation of surface charge, electrostatic screening, and the associated H-bonding networks that arise at the interface to facilitate organization and subsequent extraction.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Neural-network learning of SPOD latent dynamics

Here, we aim to reconstruct the latent space dynamics of high dimensional, quasi-stationary systems using model order reduction via the spectral proper orthogonal decomposition (SPOD). The proposed method is based on three fundamental steps: in the first, once that the mean flow field has been subtracted from the realizations (also referred to as snapshots), we compress the data from a high-dimensional representation to a lower dimensional one by constructing the SPOD latent space; in the second, we build the time-dependent coefficients by projecting the snapshots containing the fluctuations onto the SPOD basis and we learn their evolution in time with the aid of recurrent neural networks; in the third, we reconstruct the high-dimensional data from the learnt lower -dimensional representation. The proposed method is demonstrated on two different test cases, namely, a compressible jet flow, and a geophysical problem known as the Madden-Julian Oscillation. An extensive comparison between SPOD and the equivalent POD-based counterpart is provided and differences between the two approaches are highlighted. The numerical results suggest that the proposed model is able to provide low rank predictions of complex statistically stationary data and to provide insights into the evolution of phenomena characterized by specific range of frequencies. The comparison between POD and SPOD surrogate strategies highlights the need for further work on the characterization of the interplay of error between data reduction techniques and neural network forecasts.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

A gradient-based deep neural network model for simulating multiphase flow in porous media

We report simulation of multiphase flow in porous media is crucial for the effective management of subsurface energy and environment-related activities. The numerical simulators used for modeling such processes rely on spatial and temporal discretization of the governing mass and energy balance partial-differential equations (PDEs) into algebraic systems via finite-difference/volume/element methods. These simulators usually require dedicated software development and maintenance, and suffer low efficiency from a runtime and memory standpoint for problems with multi-scale heterogeneity, coupled-physics processes or fluids with complex phase behavior. Therefore, developing cost-effective, data-driven models can become a practical choice, and in this work, we choose deep learning approaches as they can handle high dimensional data and accurately predict state variables with strong nonlinearity. In this paper, we describe a gradient-based deep neural network (GDNN) constrained by the physics related to multiphase flow in porous media. We tackle the nonlinearity of flow in porous media induced by rock heterogeneity, fluid properties, and fluid-rock interactions by decomposing the nonlinear PDEs into a dictionary of elementary differential operators. We use a combination of operators to handle rock spatial heterogeneity and fluid flow by advection. Since the augmented differential operators are inherently related to the physics of fluid flow, we treat them as first principles prior knowledge to regularize the GDNN training. We use the example of pressure management at geologic CO 2 storage sites, where CO 2 is injected in saline aquifers and brine is produced, and apply GDNN to construct a predictive model that is trained with physics-based simulation data and emulates the physics process. We demonstrate that GDNN can effectively predict the nonlinear patterns of subsurface responses, including the temporal and spatial evolution of the pressure and saturation plumes. We also successfully extend the GDNN to convolutional neural network (CNN), namely gradient-based CNN (GCNN), and validate its capability to improve the prediction accuracy. GDNN has great potential to tackle challenging problems that are governed by highly nonlinear physics and enable the development of data-driven models with higher fidelity.

42 ENGINEERING↗