Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Reservoir Computing”

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 91 records · Page 5
All sourcesNASA NTRSDOE OSTI
NASA NTRS2017

Atmospheric Collapse on Early Mars: The Role of CO2 Clouds

The abundance of evidence that liquid water flowed on the surface early in Mars' history strongly implies that the early Martian atmosphere was significantly more massive than it is today. While it seems clear that the total CO2 inventory was likely substantially larger in the past, the fundamental question about the physical state of that CO2 is not completely understood. Because the temperature at which CO2 condenses increases with surface pressure, surface CO2 ice is more likely to form and persist as the atmospheric mass increases. For the atmosphere to remain stable against collapse, there must be enough energy, distributed planet wide, to stave off the formation of permanent CO2 caps that leads to atmospheric collapse. The presence of a "faint young sun" that was likely about 25 percent less luminous 3.8 billion years ago than the sun today makes this even more difficult. Several physical processes play a role in the ultimate stability of a CO2 atmosphere. The system is regulated by the energy balance between solar insolation, the radiative effects of the atmosphere and its constituents, atmospheric heat transport, heat exchange between the surface and the atmosphere, and latent heating/cooling. Specific considerations in this balance for a given orbital obliquity/eccentricity and atmospheric mass are the albedo of the caps, the dust content of the atmosphere, and the presence of water and/or CO2 clouds. Forget et al. show that, for Mars' current obliquity (in a circular orbit), CO2 atmospheres ranging in surface pressure from 500 hectopascals to 3000 hectopascals would have been stable against collapsing into permanent surface ice reservoirs. Soto et al. examined a similar range in initial surface pressure to investigate atmospheric collapse and to compute collapse rates. CO2 clouds and their radiative effects were included in Forget et al. but they were not included in Soto et al. Here we focus on how CO2 clouds affect the stability of the atmosphere against collapse.

Kahre, M. A.↗
DOE OSTI2024

Continuous integration data-driven platform of industrial-scale subsurface storage for real-time analytics

This project helped address the growing need for efficient and scalable models to support geological carbon and energy storage, which are crucial for achieving net-zero emissions. Traditionally accurate high-fidelity numerical models have been used to simulate relevant storage processes under a handful of processes, however such models are computationally demanding, making uncertainty quantification impractical. Consequently, we first developed a machine learning framework, based on Graph Neural Operators (GNOs), to improving the accuracy of model predictions for a fixed computational budget. We then developed an Ensemble of Improved Neural Operators (ENO), which uses bagging and Monte Carlo dropout techniques, to further improve prediction accuracy. Lastly, we developed the way to explain progressive transfer learning methods to reduce the amount of training data and computational cost of training (i.e., reduce trainable parameters) when using our models for multiple storage sites. Our numerical investigation, which used real-world case studies, demonstrated that our framework can significantly improve the safety and efficiency of geological storage operations, with potential applications in other domains such as geothermal reservoirs and climate modeling.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Upscaling Methods Applied to a Fine-Scale Reservoir Model

This study was conducted as part of the Southwest Regional Partnership on Carbon Sequestration (SWP) project to evaluate how upscaling fine-scale simulation models to coarse-scale simulation models impacted the results. The focus was on the Farnsworth Unit (FWU) and its Morrow' B' Sandstone reservoir, specifically the west half of the field. Due to data limitations and the geologic characteristics of the surrounding area, the upscaling was limited to the west half of the FWU rather than a broader basinscale model. The primary aim was to explore how upscaling impacts numerical simulation models, particularly regarding CO 2 -enhanced oil recovery (EOR) and storage capacity predictions. Upscaling was necessary to reduce computational demands when transitioning from high-resolution geological models to coarser grids, as large-scale simulations with finer grids can be computationally prohibitive. This study expands on previous work by the SWP to understand how additional upscaling, applied to already fine-scale numerical simulation models, affects reservoir performance simulations (Ampomah, Balch, & Grigg, 2015). This is key to understanding how loss of resolution can affect coarsescale model results that may be used for large sensitivity analyses, uncertainty quantifications, and training data for machine learning applications.

02 PETROLEUM↗
NASA NTRS1971

Reward and uncertainty in exploration programs

A set of variables which are crucial to the economic outcome of petroleum exploration are discussed. These are treated as random variables; the values they assume indicate the number of successes that occur in a drilling program and determine, for a particular discovery, the unit production cost and net economic return if that reservoir is developed. In specifying the joint probability law for those variables, extreme and probably unrealistic assumptions are made. In particular, the different random variables are assumed to be independently distributed. Using postulated probability functions and specified parameters, values are generated for selected random variables, such as reservoir size. From this set of values the economic magnitudes of interest, net return and unit production cost are computed. This constitutes a single trial, and the procedure is repeated many times. The resulting histograms approximate the probability density functions of the variables which describe the economic outcomes of an exploratory drilling program.

Kaufman, G. M.↗
DOE OSTI2024

Quantum Thermodynamics of Nonequilibrium Processes in Lattice Gauge Theories

A key objective in nuclear and high-energy physics is to describe nonequilibrium dynamics of matter, e.g., in the early Universe and in particle colliders, starting from the standard model of particle physics. Classical computing methods, via the framework of lattice gauge theory, have experienced limited success in this mission. Quantum simulation of lattice gauge theories holds promise for overcoming computational limitations. Because of local constraints (Gauss’s laws), lattice gauge theories have an intricate Hilbert-space structure. This structure complicates the definition of thermodynamic properties of systems coupled to reservoirs during equilibrium and nonequilibrium processes. We show how to define thermodynamic quantities such as work and heat using strong-coupling thermodynamics, a framework that has recently burgeoned within the field of quantum thermodynamics. Our definitions suit instantaneous quenches, simple nonequilibrium processes undertaken in quantum simulators. To illustrate our framework, we compute the work and heat exchanged during a quench in a Z 2 lattice gauge theory coupled to matter in 1+1 dimensions. Here, the thermodynamic quantities, as functions of the quench parameter, evidence a phase transition. For general thermal states, we derive a simple relation between a quantum many-body system’s entanglement Hamiltonian, measurable with quantum-information-processing tools, and the Hamiltonian of mean force, used to define strong-coupling thermodynamic quantities.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2026

Differentiable multiphase flow model for physics-informed machine learning in reservoir pressure management

Accurate subsurface reservoir pressure control is extremely challenging due to geological heterogeneity and multiphase fluid-flow dynamics. Predicting behavior in this setting relies on high-fidelity physics-based simulations that are computationally expensive. Yet, the uncertain, heterogeneous properties that control these flows make it necessary to perform many of these expensive simulations, which is often prohibitive. To address these challenges, we introduce a physics-informed machine learning workflow that couples a fully differentiable multiphase flow simulator, which is implemented in the DPFEHM framework with a convolutional neural network (CNN). The CNN learns to predict fluid extraction rates from heterogeneous permeability fields to enforce pressure limits at critical reservoir locations. By incorporating transient multiphase flow physics into the training process, our method enables more practical and accurate predictions for realistic injection-extraction scenarios compared to previous works. To speed up training, we pretrain the model on single-phase, steady-state simulations and then finetune it on full multiphase scenarios, which dramatically reduces the computational cost. We demonstrate that high-accuracy training can be achieved with fewer than three thousand full-physics multiphase flow simulations – compared to previous estimates requiring up to ten million. This drastic reduction in the number of simulations is achieved by leveraging transfer learning from much less expensive single phase simulations.

25 ENERGY STORAGE↗
DOE OSTI2025

Modeling supercritical CO2 injection induced rupture of a minor fault embedded in a poroelastic layered reservoir-caprock system

CO2 injection for geologic carbon sequestration involves hydromechanical processes that lead to changes in fluid pressure and stresses that can activate existing faults. This paper presents a new method and workflow of modeling fault activation considering more complex three-dimensional geometry of natural faults using the TOUGH-FLAC multiphase fluid flow and geomechanical simulator. In this method and workflow, FLAC3D mechanical interfaces and TOUGH3 finite volume elements are discretized using computer aided design and gridding software along with a tailored mesh translation routine. The method and workflow are demonstrated with a model of a curved minor fault embedded in a poro-elastic layered reservoir-caprock system. The model is used for a comprehensive sensitivity analysis of fault responses to fault length, injection mass rate, injection schedule, well-fault distance, and well locations versus fault location. Four metrics (CO2 plume, shear state of fault, pressure and stress path at fault monitoring points) are selected to assess CO2 migration, pressure change, and the reactivation of faults. The results reveal that CO2 can bypass around the tip of the minor impermeable fault, building up pressure and poro-elastic stress on both sides that tends to impede fault rupture. Our study shows the benefit of carefully designing the injection to achieve the targeted final storage volume, starting at a relatively low rate for considerable time, and then ramping up the injection rate to the full rate of injection. The initial low injection has two distinct benefits: (1) it allows for the formation of an extensive CO2 plume with a much higher mobility through a low viscosity that will result in a lower pressure for a given injection rate, and (2) it allows for gradual build-up of horizontal poro-elastic stress within the reservoir that will tend to impede activation of steeply dipping faults. The injection scenario starting at a low injection rate, denoted here as conservative injection, can significantly reduce the risk of fault activation as high fluid mobility and reservoir strengthening poro-elastic stress has been established long before reaching the peak injection rates. Moreover, simultaneous injection in two injection wells on both sides of fault can provide further reservoir strengthening through poro-elastic stress buildup acting on a fault under normal faulting stress regime. The findings presented in the paper can provide practical and effective guidance on long-term, safe, and reliable geological CO2 storage.

Cao, Meng↗
NASA NTRS1982

The use of LANDSAT data to monitor the urban growth of Sao Paulo Metropolitan area

Urban growth from 1977 to 1979 of the region between Billings and the Guarapiranga reservoir was mapped and the problematic urban areas identified using several LANDSAT products. Visual and automatic interpretation techniques were applied to the data. Computer compatible tapes of LANDSAT multispectral scanner data were analyzed through the maximum likelihood Gaussian algorithm. The feasibility of monitoring fast urban growth by remote sensing techniques for efficient urban planning and control is demonstrated.

Dejesusparada, N.↗
NASA NTRS1990

Initial steps toward automation of a propellant processor

This paper presents the results from an experimental study aimed at ultimately automating the mixing of propellants in order to minimize unintended variations usually attributed to human error. The water heater and delivery system of a one-pint Baker-Perkins (APV) vertical mixer are automated with computer control. Various innovations are employed to introduce economy and low thermal inertia. Some of these include twin heaters/reservoirs instead of one large reservoir, a compact water mixer for achieving the desired temperature quickly, and thorough insulation of the entire water system. The completed system is tested during two propellant mixes. The temperature uniformly is proven through careful measurements employing several local thermocouples.

Schallhorn, Paul↗
DOE OSTI2025

Applying a Multisector Scenario Framework to Evaluate Past and Future Public Surface Water Supply Infrastructure Strategies in Texas

Datasets supporting the index model and scenario analysis used in evaluating surface water supply strategies across different water system types in Texas. These data underpin the scenario development and application of five key indicators: Water Availability Index (WAI), Water Quality Index (WQI), Energy Requirement Index (ERI), Water Treatment Cost (WTC), and Water Infrastructure Cost (WIC). The datasets are organized by system type—stream reaches (flowlines), waterbodies, and reservoirs—and include both raw and standardized index values. The integrated datasets also provide scenario classifications (original and adjusted) based on infrastructure and planning priorities, enabling comparison across Shared Socioeconomic Pathways (SSPs). Additional strategy-level data are included to support evaluation of state-level new reservoir projects in relation to cost and availability tradeoffs. Please refer to the README file provided in Files for more details. Descriptions of the datasets are provided below. Dataset(s) Descriptions Folder: Index_model_database.zip Subfolder: Stream_reach.zip Fl_wf.csv, Fl_wq.csv, Fl_er.csv, Fl_wf_wtcUV.csv, Fl_wf_wtcnoUV.csv, Fl_allfac_wic1.csv, Fl_allfac_wic2.csvDatasets for computing WAI, WQI, ERI, WTC, and WIC for surface water systems classified as stream reaches (flowlines). Subfolder: Waterbody.zip Wb_wf.csv, Wb_wq.csv, Wb_er.csv, Wb_wf_wtcUV.csv, Wb_wf_wtcnoUV.csv, Wb_allfac_wic1.csv, Wb_allfac_wic2.csvEquivalent index model datasets for waterbodies, reflecting hydrologic and infrastructure attributes specific to impounded natural systems. Subfolder: Reservoir.zip Rs_wf.csv, Rs_wq.csv, Rs_er.csv, Rs_wf_wtcUV.csv, Rs_wf_wtcnoUV.csv, Rs_allfac_wic1.csv, Rs_allfac_wic2.csvIndex model datasets specific to regulated reservoir systems, incorporating both resource indicators and cost parameters. Folder: Integrated data.zip combined_merged_data.csv, combined_merged_data_scenario.csvDatasets integrating index model indicators (both raw and scaled) with scenario classifications, including adjustments reflecting SSP-aligned transitions and planning shifts. Folder: Additional data.zip wai_supplystrat_wic_merged.csvCurated dataset capturing proposed major reservoir-based municipal water supply strategies in Texas. Integrates site-level planning data with estimated capital infrastructure costs and water availability scores for comparative assessment.

geospatial↗
DOE OSTI2025

Deep Learning for Subsurface Flow: A Comparative Study of U‐Net, Fourier Neural Operators, and Transformers in Underground Hydrogen Storage

Subsurface flow research is essential for the sustainable management of natural resources and the environment. Deep learning (DL) has significantly advanced this field by developing efficient and accurate surrogate models to replace computationally expensive physics‐based simulations. These surrogate models are commonly used to predict the spatiotemporal evolution of state variables, such as gas saturation and reservoir pressure, in heterogeneous geological formations. Despite the various DL models applied to this task, there is a lack of studies systematically comparing their performance. This absence of comparative analysis leads to somewhat arbitrary DL model selection in subsurface flow research, resulting in suboptimal performance and potentially inaccurate predictions. To bridge this gap, we conduct a systematic comparison study of three popular DL architectures—U‐Net, Fourier Neural Operators (FNO), and Segmentation Transformer (SETR)—in surrogate modeling of underground hydrogen storage (UHS). We focus on UHS due to its promise of enhancing clean energy resilience and its cyclic operational conditions that represent common scenarios in various subsurface applications. We evaluate the models based on accuracy, training cost, and inference speed. The comparison shows that U‐Net achieves the highest accuracy, followed by SETR and FNO. Despite its lower accuracy, FNO has the highest inference speed. SETR offers competitive accuracy with the least training memory usage, demonstrating the potential of transformers in learning subsurface flow. Our results provide guidance for selecting DL models for surrogate modeling in a wide range of subsurface flow problems.

42 ENGINEERING↗
NASA NTRS1992

Time-dependent quasi-one-dimensional simulations of high enthalpy pulse facilities

A numerical methodology is presented for simulating the time-dependent reacting flow inside the entire length of high enthalpy pulse facilities. The methodology is based on a finite-volume TVD scheme for the quasi-1D Euler equations coupled with finite-rate chemistry. A moving mesh and tracking of gas interfaces are used to overcome certain numerical difficulties associated with these types of flows. Simulation results of a helium driven shock tube show that computations can be used to predict the off-tailored behavior of shock tubes and tunnels. Particular attention is given to computations of the flow through the NASA Ames 16-inch combustion driven shock tunnel which show the influence of nonuniformities in the driver section on the reservoir conditions; and the effect of finite secondary diaphragm opening times on the chemical composition of the test flow in the HYPULSE expansion tube.

Wilson, Gregory J.↗
DOE OSTI2026

HydroDCM: Hydrological Domain-Conditioned Modulation for Cross-Reservoir Inflow Prediction

Deep learning models have shown promise in reservoir inflow prediction, yet their performance often deteriorates when applied to different reservoirs due to distributional differences, referred to as the domain shift problem. Domain generalization (DG) solutions aim to address this issue by extracting domain-invariant representations that mitigate errors in unseen domains. However, in hydrological settings, each reservoir exhibits unique inflow patterns, while some metadata beyond observations like spatial information exerts indirect but significant influence. This mismatch limits the applicability of conventional DG techniques to many-domain hydrological systems. To overcome these challenges, we propose HydroDCM, a scalable DG framework for cross-reservoir inflow forecasting. Spatial metadata of reservoirs is used to construct pseudo-domain labels that guide adversarial learning of invariant temporal features. During inference, HydroDCM adapts these features through light-weight conditioning layers informed by the target reservoir’s metadata, reconciling DG’s invariance with location-specific adaptation. Experiment results on 30 real-world reservoirs in the Upper Colorado River Basin demonstrate that our method substantially outperforms state-of-the-art DG baselines under many-domain conditions and remains computationally efficient.

Hu, Pengfei [ORNL] (ORCID:0009000367130950)↗
DOE OSTI2024

ML-based Dimension Reduction Strategies

Deep learning (DL)--based surrogate models have achieved success in various applications in carbon capture and storage (CCS). However, the model training on high-dimensional spaces is computationally expensive and impractical for large-scale and complex geological models, because the models usually contain hundreds of thousands to millions of grid cells, each with a set of parameters. Furthermore, the high cost of generating training data with sufficient variation is another limitation of model training on high-dimensional spaces, which may result in overfitting and reduce the model efficiency and prediction performance. We proposed the workflow incorporating dimension reduction methods and deep learning models, which aim to extract the latent variables of input parameters and output state variables, and then build the mapping function at the latent spaces. The proposed workflow can significantly reduce the computational complexity in solving both forward and inverse problems compared to models trained on high-dimensional spaces. Dimensionality reduction models showed great potential in workflows for fast reservoir simulation, history matching, prior model generation, visualization, and more, ultimately enhancing DL model performance in related SMART Work Packages.

Hosseini, Seyyed↗
DOE OSTI2025

COMPUTATION FLUID DYNAMICS ANALYSIS FOR GENERIC SMALL MODULAR REACTOR CONTAINMENT SEPARATE EFFECTS TEST

It is desirable for fourth-generation Small Modular Reactors to be passively cooled in standard and accident operations. Passive Containment Cooling Systems can reject heat from the containment structure, without using pumps or blowers. The targeted design containment structure is a large, domed, stainless steel, cylindrical vessel. In a postulated Design Basis Accident, steam will flash inside containment. Steam condensation occurs on the inner containment wall and transfers heat through the steel containment into a large body of water known as the annular reservoir (AR) surrounding the vessel serving as the ultimate heat sink. Natural circulation drives the flow in the AR and heat will be released to the environment by evaporation of water. Unique containment geometry requires a separate effects test (SET) facility for the verification and validation of the computer code and evaluation model development and assessment for reactor licensing efforts. In this study, STAR-CCM+, a computational fluid dynamics (CFD) code was used to inform the decision-making process on the design of the SET. The CFD simulation modeled, a two-phase turbulent flow with fluid film development and heat transfer for different containment geometries. The Reactor Excursion and Leak Analysis Program will also be used in a code-to-code verification against the CFD results.

21 - SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLAN↗
NASA NTRS1992

Real gas flow parameters for NASA Langley 22-inch Mach 20 helium tunnel

A computational procedure was developed which can be used to determine the flow properties in hypersonic helium wind tunnels in which real gas behavior is significant. In this procedure, a three-coefficient virial equation of state and the assumption of isentropic nozzle flow are employed to determine the tunnel reservoir, nozzle, throat, freestream, and post-normal shock conditions. This method was applied to a range of conditions which encompasses the operational capabilities of the LaRC 22-Inch Mach 20 Helium Tunnel. Results are presented graphically in the form of real gas correction factors which can be applied to perfect gas calculations. Important thermodynamic properties of helium are also plotted versus pressure and temperature. The computational scheme used to determine the real-helium flow parameters was incorporated into a FORTRAN code which is discussed.

Hollis, Brian R.↗
NASA NTRS2005

SCB Quantum Computers Using iSWAP and 1-Qubit Rotations

Units of superconducting circuitry that exploit the concept of the single- Cooper-pair box (SCB) have been built and are undergoing testing as prototypes of logic gates that could, in principle, constitute building blocks of clocked quantum computers. These units utilize quantized charge states as the quantum information-bearing degrees of freedom. An SCB is an artificial two-level quantum system that comprises a nanoscale superconducting electrode connected to a reservoir of Cooper-pair charges via a Josephson junction. The logical quantum states of the device, .0. and .1., are implemented physically as a pair of charge-number states that differ by 2e (where e is the charge of an electron). Typically, some 109 Cooper pairs are involved. Transitions between the logical states are accomplished by tunneling of Cooper pairs through the Josephson junction. Although the two-level system contains a macroscopic number of charges, in the superconducting regime, they behave collectively, as a Bose-Einstein condensate, making possible a coherent superposition of the two logical states. This possibility makes the SCB a candidate for the physical implementation of a qubit. A set of quantum logic operations and the gates that implement them is characterized as universal if, in principle, one can form combinations of the operations in the set to implement any desired quantum computation. To be able to design a practical quantum computer, one must first specify how to decompose any valid quantum computation into a sequence of elementary 1- and 2-qubit quantum gates that are universal and that can be realized in hardware that is feasible to fabricate. Traditionally, the set of universal gates has been taken to be the set of all 1-qubit quantum gates in conjunction with the controlled-NOT (CNOT) gate, which is a 2-qubit gate. Also, it has been known for some time that the SWAP gate, which implements square root of the simple 2-qubit exchange interaction, is as computationally universal as is the CNOT operation.

Williams, Colin↗