SEARCH · Engineering Papers

Results for “reservoir computing networks”

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.

SourceResearch connectionFrom yearThrough year

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

At least 73 records · Page 4

All sources NASA NTRS DOE OSTI

DOE OSTI2020

Sequentially coupled flow and geomechanical simulation with a discrete fracture model for analyzing fracturing fluid recovery and distribution in fractured ultra-low permeability gas reservoirs

More accurate characterization and prediction of the in-situ distribution of fracturing fluid in fractured reservoirs are needed for enhancing well productivity. In this study, an implicit-sequentially coupled flow/geomechanics simulator incorporating an efficient discrete fracture model is developed to model fluid distribution and recovery performance of ultra-low permeability gas reservoirs. The finite-volume and finite-element methods are used for space discretization of the flow and geomechanics equations, respectively, while the backward Euler method is employed for time discretization. The flow and geomechanics equations are solved sequentially based on fixed-stress splitting. An efficient discrete-fracture model is used to explicitly model the fractured system. Flexible unstructured gridding is employed to model arbitrarily-oriented fractures. The interrelations among pore volume, permeability and geomechanical conditions are considered dynamically using two-way coupled flow and geomechanics computations. The geometry of fracture (networks) due to hydraulic fracturing has significant impacts on the fracturing fluid recovery efficiency and ensuing fluid distribution. Under the same injection volume, the fracturing fluid recovery is higher when the fracture geometry is planar. Fluid recovery is relatively lower whenever natural fractures are activated during fracturing treatments; flowback time is also shortened when complex fracture network with enlarged fracture interface is present. Fracturing fluid in hydraulic fractures may leak off into the natural fractures and subsequently imbibes into the surrounding matrix due to capillarity effects. The fracturing fluid recovery and in-situ fluid distribution are sensitive to the shut-in duration and fracture closure behavior. This study analyzes the coupled flow-geomechanical responses of fractured gas reservoirs during the post-fracturing periods. Understanding the fate of the fracturing fluid can provide insights on, to some extent, the stimulated fracture volume, size of the water invasion zone, and efficiency of the fracturing design. The simulation predictions can also provide more accurate initial reservoir conditions (e.g. distributions of different phases and pressure) for long-term well performance estimation.

42 ENGINEERING↗

DOE OSTI2020

Transient flow modeling in fractured media using graphs

In this work, we describe a method to simulate transient fluid flows in fractured media using an approach based on graph theory. Our approach builds on past work where the graph-based approach was successfully used to simulate steady-state fluid flows in fractured media. We find a mean computational speedup of the order of 1400 from an ensemble of a 100 discrete fracture networks in contrast to the O(10 4 ) speedup that was obtained for steady-state flows earlier. However, the transient flows considered here involve an additional degree of complexity that was not present in the steady-state flows considered previously with a graph-based approach, that of time marching and solution of the flow equations within a time-stepping scheme. We verify our method with an analytical test case and demonstrate its use on a practical problem related to fluid flows in hydraulically fractured reservoirs. By enabling the study of transient flows, we create an opportunity for a wide set of possibilities where a steady-state approximation is not sufficient, such as the example motivated by hydraulic fracturing that we present here. This work validates the concept that graphs are able to reliably capture the topological properties of the fracture network and serve as effective surrogates in an uncertainty-quantification framework.

58 GEOSCIENCES↗

DOE OSTI2024

Predicting Geologic Behavior in Carbon Storage Projects Using Graph Neural Network

This study was invited to presented at NVIDIA's GTC conference to highlight the potential of Graph Neural Network as a novel and promising methodology for predicting pressure and saturation evolution in carbon storage projects. Carbon capture and storage (CCS) technology plays a pivotal role in mitigating greenhouse gas emissions, facilitating the transition to a low-carbon future. Effective management of subsurface reservoirs is essential to ensure the safe and efficient storage of captured carbon dioxide (CO₂). Accurate predictions of pressure and saturation over time are critical for evaluating the long-term performance and integrity of CCS projects. In recent years, Graph Neural Network (GNN) has emerged as a powerful framework for analyzing complex data in graph-structured domains. This abstract explores the application of GNN to forecast pressure and saturation evolution in carbon storage projects. Traditional numerical simulations of subsurface reservoirs have proven successful in providing pressure and saturation forecasts. However, these simulations involve massive amounts of computational effort and require extensive domain expertise for proper model calibration and validation. Graph Neural Operator offers an alternative approach that harnesses the inherent graph structure of reservoirs, where nodes represent reservoir grid cells and edges represent the geological connectivity between them.

Shih, Chung Yan↗

DOE OSTI2024

CO 2 storage site characterization using ensemble-based approaches with deep generative models

Estimating spatially distributed properties such as permeability from available sparse measurements is a great challenge in efficient subsurface CO 2 storage operations. In this paper, a deep generative model that can accurately capture complex subsurface structure is tested with an ensemble-based inversion method for accurate and accelerated characterization of CO 2 storage sites. We chose Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) for its realistic reservoir property representation and Ensemble Smoother with Multiple Data Assimilation (ES-MDA) for its robust data fitting and uncertainty quantification capability. WGAN-GP are trained to generate high-dimensional permeability fields from a low-dimensional latent space and ES-MDA then updates the latent variables by assimilating available measurements. Several subsurface site characterization examples including Gaussian, channelized, and fractured reservoirs are used to evaluate the accuracy and computational efficiency of the proposed method and the main features of the unknown permeability fields are characterized accurately with reliable uncertainty quantification. Furthermore, the estimation performance is compared with a widely-used variational, i.e., optimization-based, inversion approach, and the proposed approach outperforms the variational inversion method in several benchmark cases. We explain such superior performance by visualizing the objective function in the latent space: because of nonlinear and aggressive dimension reduction via generative modeling, the objective function surface becomes extremely complex while the ensemble approximation can smooth out the multi-modal surface during the minimization. This suggests that the ensemble-based approach works well over the variational approach when combined with deep generative models at the cost of forward model runs unless convergence-ensuring modifications are implemented in the variational inversion.

42 ENGINEERING↗

DOE OSTI2020

Using Machine Learning to Predict Future Temperature Outputs in Geothermal Systems

Optimizing the power output, and economic value, of geothermal power plants over decades of operation is a major challenge in renewable energy. Optimizing the output requires the ability to predict the mass flow rates and the output temperatures of production wells based on the inputs of injection wells, as well as the time history of the system. Machine Learning (ML) that incorporates the known physics of geothermal systems is one possible solution to this challenge. In this work, we explore the ability of ML algorithms to predict future temperature outputs based on historical data. Considering the challenges with obtaining an empirical dataset from field data that is large enough to enable reliable ML, we propose an alternate approach: developing a high-fidelity reservoir model and using computational resources to build a dataset that enables ML. As a first step towards achieving this goal, we present preliminary results from applying ML to predict the temperature timeseries of simple modeled geothermal systems. We describe the application of relevant state-of-the-art ML approaches, such as the Long Short-Term Memory (LSTM) networks and Convolutional Neural Networks (CNN), to extract temporal structures in the model data. We assess the accuracy of the forecasts we obtain, compare the selected approaches, and share the lessons learned that would inform the process of training and utilizing ML algorithms for larger and more complex geothermal systems.

GEOTHERMAL ENERGY↗

DOE OSTI2025

Continuous operation of a coherent 3,000-qubit system

Neutral atoms are a promising platform for quantum science, enabling advances in areas ranging from quantum simulations and computation to metrology, atomic clocks and quantum networking. Although atom losses typically limit these systems to a pulsed mode, continuous operation could substantially enhance cycle rates, remove bottlenecks in metrology and enable deep-circuit quantum evolution through quantum error correction. Here we demonstrate an experimental architecture for high-rate reloading and continuous operation of a large-scale atom-array system while realizing coherent storage and manipulation of quantum information. Our approach utilizes a series of two optical lattice conveyor belts to transport atom reservoirs into the science region, where atoms are repeatedly extracted into optical tweezers without affecting the coherence of qubits stored nearby. Using a reloading rate of 300,000 atoms in tweezers per second, we create over 30,000 initialized qubits per second, which we leverage to assemble and maintain an array of over 3,000 atoms for more than 2 hours. Furthermore, we demonstrate persistent refilling of the array with atomic qubits in either a spin-polarized or a coherent superposition state while preserving the quantum state of stored qubits. Our results pave the way for the realization of large-scale continuously operated atomic clocks, sensors and fault-tolerant quantum computers.

atomic and molecular physics↗

DOE OSTI2020

Interpretation of borehole strain measurements using surrogate modeling-based optimization

Interpreting strain data measured during well testing requires inverting poroelastic forward models set up to represent an aquifer or reservoir. One approach is to use stochastic methods to conduct the inversion. Subsurface parameters such as elastic modulus, permeability, and geometry of heterogeneities are estimated by searching the parameter space. This is feasible, but cumbersome, requiring more than a week of computation using many hundreds of computer nodes in one of our earlier analyses. This motivated us to consider alternative methods, including an artificial neural network (ANN) as a surrogate model.

Roudini, Soheil↗

DOE OSTI2020

Performance of Closed Loop Venturi Aspirated Aeration System: Experimental Study and Numerical Analysis with Discrete Bubble Model

In wastewater treatment plants, aeration plays a significant role as it encourages aerobic respiration of microbes, which are necessary to break down carbonaceous matter in the waste stream. This process can account for the majority of energy use in wastewater treatment plants. The aeration process is also necessary in odor control in lagoons and in the aquaculture industry. Generally, the aeration process is accomplished with compressors or blowers which can be of low efficiency due to ideal gas laws. This study introduces the idea of increasing aeration efficiency by looping water from a reservoir through a piping network which includes a venturi aspirator at its inlet. For this purpose, an experimental study has been conducted in a laboratory setup with a pump which pulls water from a tank, passes it through a Venturi aspirator and a helical piping network intended to increase bubble residence time, before depositing it back into the bulk fluid tank. This same process is modeled computationally, using a discrete bubble method (DBM), with good agreement with experiments. The overall purpose here is to determine the optimal configurations for standard aeration efficiency (SAE) and the standard oxygen transfer rate (SOTR). A parametric study has been implemented using the DBM based on different hydraulic and flow parameters. The model is also used to predict the SAE of a hypothetical aeration system. Results indicate that it is possible to achieve SAE values in the range of surface aerators or submersed jet aerators using the proposed aeration system with less complex components, thereby decreasing overall costs.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2023

Assessing pore network heterogeneity across multiple scales to inform CO2 injection models

Geologic heterogeneity is a key feature that must be considered when translations of scaled data are performed. This paper presents the assessment of geologic heterogeneity using a multiscale workflow that includes image analysis-based methods coupled with well log analysis to provide data in which fractals and machine learning methods estimate the carbon dioxide (CO 2 ) storage resource potential of a reservoir. The heterogeneity of rock properties of the complex Bell Creek reservoir in Montana, USA, was explored at the pore scale (~nm to mm), core scale (~mm to m), and well scale (~cm to m). The data used in this study included advanced image analysis of micro-CT (computed tomography) images (pore scale), thin sections (pore scale), plugs and core images (core scale) and well logs (well scale). The micro-CT images were segmented using a U-net segmentation approach into objects of pores and grains. Further, the segmented images were reconstructed into subvolumes of different sizes. Physical properties (porosity and permeability) and fractal dimensions were calculated for the various subvolumes, and Lorenz coefficient (Lc) values, a single parameter to describe the degree of heterogeneity within a pay zone section, were calculated from thin-section images and well logs. Porosity and fractal dimension values were used to estimate the 188-µm threshold of representative elementary volume (REV) in this study. Both the Lc and fractal dimension values were found to be negatively correlated. When these two parameters are combined, it is possible to discern differences in the complex porous networks of the samples analyzed in this study.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2025

ChemComp: A Compilation Framework for Computing with Chemical Reaction Networks

The acceleration of scientific computation, data analytics, and artificial intelligence is driving a surge in computational requirements. Yet, state-of-the-art high-performance computing systems are approaching physical limitations that impede further significant improvements in energy efficiency. As we move towards post-exascale computing systems, innovative approaches are necessary to overcome this barrier in power consumption. Novel analog and hybrid digital-analog architectures hold promise for enhancing energy efficiency by several orders of magnitude. Biochemical computation stands out among the various solutions being explored due to its potential to enable new classes of devices with immense computational capabilities. These devices can capitalize on the inherent efficacy of biological cells in solving optimization problems and are scalable through increasing reaction system size or vessel capacity, potentially satisfying scientific computing's high-performance requirements. Nonetheless, several theoretical and practical limitations persist, including problem formulation and mapping to chemical reaction networks (CRNs) and implementation of actual CRN devices. In this paper, we propose a framework for biochemical computation using systems chemistry. We present the initial components of our approach: an abstract chemical reaction dialect implemented as a multi-level intermediate representation (MLIR) compiler extension and a pathway to represent mathematical problems with CRNs. To showcase the potential of this approach, we emulate a simplified chemical reservoir device. This work lays the groundwork for leveraging chemistry's computing potential in creating energy-efficient, high-performance computing systems tailored to contemporary computational needs.

artificial intelligence↗

DOE OSTI2024

Collective dynamics and long-range order in thermal neuristor networks

Abstract In the pursuit of scalable and energy-efficient neuromorphic devices, recent research has unveiled a novel category of spiking oscillators, termed “thermal neuristors.” These devices function via thermal interactions among neighboring vanadium dioxide resistive memories, emulating biological neuronal behavior. Here, we show that the collective dynamical behavior of networks of these neurons showcases a rich phase structure, tunable by adjusting the thermal coupling and input voltage. Notably, we identify phases exhibiting long-range order that, however, does not arise from criticality, but rather from the time non-local response of the system. In addition, we show that these thermal neuristor arrays achieve high accuracy in image recognition and time series prediction through reservoir computing, without leveraging long-range order. Our findings highlight a crucial aspect of neuromorphic computing with possible implications on the functioning of the brain: criticality may not be necessary for the efficient performance of neuromorphic systems in certain computational tasks.

Science & Technology - Other Topics↗

DOE OSTI2025

Three-Dimensional Pore Networks in Miocene Stevens Sandstone of California: Implications for CO 2 Geologic Storage

The Miocene Stevens Sandstone in the San Joaquin Basin of California is increasingly recognized as a promising candidate for CO 2 geological storage due to the enormous storage capacity, proven sealing, and existing infrastructure. In this study, computed microtomography imaging and pore network modeling were employed to investigate the influence of pore geometry and wettability on the CO 2 injectivity and residual trapping. Image analysis revealed that a significant fraction of the cement and matrix consists of microporous regions. The microporosity can substantially increase the overall pore space, yet its contribution to permeability remains modest, particularly in samples with low permeability. The intrinsic heterogeneity of turbidite reservoirs further complicates the reservoir properties among different layers. Two-phase flow simulations under varying wettability conditions (water-wet, weak water-wet, and neutral-wet) demonstrated that the CO 2 injection is predominantly controlled by macropores. CO 2 invades microporous regions only after these larger pores are filled. The presence of microporosity leads to a decrease in both initial and residual CO 2 saturations, with the magnitude of the reduction being influenced by wettability. Neutral-wet scenarios exhibit higher CO 2 mobility and thus lower residual trapping than water-wet scenarios. The results imply that heterogeneity in pore geometry and cement distribution across different layers can result in stratified CO 2 flow pathways, complicating efforts to predict injection performance. Overall, the Stevens Sandstone shows considerable promise for CO 2 geologic storage, but effective implementation will require detailed characterization of the pore structure as well as the integration of reactive fluid flow to account for potential mineral dissolution and fines migration.

fluids↗

DOE OSTI2023

Iterative multi-task learning and inference from seismic images

Seismic interpretation aims to extract quantitative and interpretable attributes from a seismic image produced using some migration method to inform characteristics of a subsurface reservoir or target of interest. Current paradigms for computing seismic attributes mostly rely on single-task algorithms. We develop an iterative, multi-task machine learning method to learn and infer multiple attributes from a seismic image. This method is composed of two stages: a multi-task inference stage and a multi-modal, multi-task refinement stage. The basic mechanism of this method is that we train a multi-task inference neural network (NN) to estimate a set of attributes, including a relative geological time (RGT), a denoised higher-resolution (DHR) seismic image, and multiple fault attributes (including probability, dip, and strike), from a low-resolution, noisy seismic image; then we input the inferred attributes to a multi-task refinement NN to enhance the raw inference results iteratively. The two multi-task NNs are trained separately based on synthetic seismic images and associated attributes generated by a geological modeling algorithm. The software we intend to release is a PyTorch implementation of this multi-task learning method for both 2D and 3D cases along with scripts to run the training/validation. The algorithm and software can be a useful tool for automatic seismic interpretation.

Gao, Kai↗

DOE OSTI2020

Modeling Nanoconfinement Effects Using Active Learning

Predicting the spatial configuration of gas in nanopores of is relevant in applications such as fluid flow forecasting and hydrocarbon reserves estimation. For example, shale reservoirs have suffered from computationally intractable multiscale problems, since fluid properties such as viscosity, density, and adsorption must be calculated by using expensive molecular dynamics (MD) simulations within each nanopore, whereas flow through these connected nanopores must be simulated at the micrometer scale. We utilize machine learning techniques to quickly and accurately model nanoscale confinement effects as an important step toward bridging the nano and micro scales. Our workflow is based on building and training physics-based deep-neural-networks models by learning from a database of MD calculations. The model accounts for the adsorption phenomenon by predicting the statistical distribution of gas inside nanopores. Because large databases of MD calculations are expensive to create, we investigate active learning (AL) as a data set construction strategy. In this workflow, new data are selected based on the model uncertainty via the query-by-committee approach. We show that our workflow obtains accurate models that generalize to real scanning electron microscopy geometries with 1/10th of the number of MD calculations required vs random data set generation. Our method enables the possibility of modeling nanoconfinement effects at the mesoscale, where complex connected sets of nanopores affect flow.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2020

Evolutionary Optimization for Neuromorphic Systems

Designing and training an appropriate spiking neural network for neuromorphic deployment remains an open challenge in neuromorphic computing. In 2016, we introduced an approach for utilizing evolutionary optimization to address this challenge called Evolutionary Optimization for Neuromorphic Systems (EONS). In this work, we present an improvement to this approach that enables rapid prototyping of new applications of spiking neural networks in neuromorphic systems. We discuss the overall EONS framework and its improvements over the previous implementation. We present several case studies of how EONS can be used, including to train spiking neural networks for classification and control tasks, to train under hardware constraints, to evolve a reservoir for a liquid state machine, and to evolve smaller networks using multi-objective optimization.

Schuman, Catherine↗

DOE OSTI2024

Fracture Characterization Via AI‐Assisted Analysis of Temperature Logs

Abstract Fractures control fluid flow, mass transport, and heat transfer in a geothermal reservoir. This makes accurate characterization of fracture networks a prerequisite for optimal design and control of a reservoir's exploitation. We develop a deep‐learning procedure to identify fracture locations via interpretation of temporally and spatially continuous downhole temperature measurements. A long short‐term memory fully convolutional network (LSTM‐FCN) is used both to capture long‐term dependencies in sequential temperature data and to distill local features around fractures. A wellbore and fractured‐reservoir thermal model is established to generate temperature data for network training. The trained LSTM‐FCN exhibits a unique ability to detect multiple fractures intersecting a borehole. We use the LSTM‐FCN algorithm to evaluate the effectiveness of different‐stage wellbore temperature measurements on fracture detection in a complex fractured system. Our experiments reveal that the use of various‐stage temperature information as an input feature set improves the robustness of fracture detection to noise interference. This study indicates the practical feasibility of obtaining accurate fracture‐network reconstructions from temperature signals, at reasonable computational cost.

Yang, Xiaoyu↗

DOE OSTI2025

ChemComp: Compiling and Computing with Chemical Reaction Networks

The exponential growth in computing demands driven by scientific computing, data analytics, and artificial intelligence is pushing conventional CMOS-based high-performance computing systems to their physical and energy efficiency limits. As we approach the era of post-exascale computing, disruptive approaches are necessary to overcome these barriers and achieve substantial gains in energy efficiency. Analog and hybrid digital-analog computing systems have emerged as promising alternatives, offering the potential for orders-of-magnitude improvements in efficiency. Among these, biochemical computing stands out as a novel paradigm capable of leveraging the natural efficiency of chemical reactions, which have shown promise in solving optimization problems by converging to steady states. By scaling up reaction networks or reaction vessel sizes, biochemical systems present an opportunity to meet the high-performance demands of modern computing tasks. Despite their promise, significant theoretical and practical challenges remain, particularly in formulating and mapping computational problems to chemical reaction networks (CRNs) and designing viable biochemical computing devices. This paper addresses these challenges by introducing new ideas to ChemComp, a compilation and emulation framework for chemical computation. This work describes the mechanisms through which solutions to ordinary differential equations (ODEs) that can be represented as CRN systems can be achieved. Furthermore, we explain the design principles of an ODE dialect implemented as a multi-level intermediate representation (MLIR) compiler extension that will be coupled with existing infrastructure. We demonstrate the potential of our framework through a case study emulating a simplified chemical reservoir computing device. This work establishes foundational tools and methodologies necessary to harness the computational power of chemistry, paving the way for the development of energy-efficient, high-performance computing systems tailored to contemporary and future computational needs.

Bohm Agostini, Nicolas↗

DOE OSTI2022

Optimization of Water-Alternating-CO2 Injection Field Operations Using a Machine-Learning-Assisted Workflow

Summary This paper will present a robust workflow to address multiobjective optimization (MOO) of carbon dioxide (CO2)-enhanced oil recovery (EOR)-sequestration projects with a large number of operational control parameters. Farnsworth unit (FWU) field, a mature oil reservoir undergoing CO2 alternating water injection (CO2-WAG) EOR, will be used as a field case to validate the proposed optimization protocol. The expected outcome of this work would be a repository of Pareto-optimal solutions of multiple objective functions, including oil recovery, carbon storage volume, and project economics. FWU’s numerical model is used to demonstrate the proposed optimization workflow. Because using MOO requires computationally intensive procedures, machine-learning-based proxies are introduced to substitute for the high-fidelity model, thus reducing the total computation overhead. The vector machine regression combined with the Gaussian kernel (Gaussian-SVR) is used to construct proxies. An iterative self-adjusting process prepares the training knowledge base to develop robust proxies and minimizes computational time. The proxies’ hyperparameters will be optimally designed using Bayesian optimization to achieve better generalization performance. Trained proxies will be coupled with multiobjective particle swarm Optimization (MOPSO) protocol to construct the Pareto-front solution repository. The outcomes of this workflow will be a repository containing Pareto-optimal solutions of multiple objectives considered in the CO2-WAG project. The proposed optimization workflow will be compared with another established methodology using a multilayer neural network (MLNN) to validate its feasibility in handling MOO with a large number of parameters to control. Optimization parameters used include operational variables that might be used to control the CO2-WAG process, such as the duration of the water/gas injection period, producer bottomhole pressure (BHP) control, and water injection rate of each well included in the numerical model. It is proved that the workflow coupling Gaussian-SVR proxies and the iterative self-adjusting protocol is more computationally efficient. The MOO process is made more rapid by squeezing the size of the required training knowledge base while maintaining the high accuracy of the optimized results. The outcomes of the optimization study show promising results in successfully establishing the solution repository considering multiple objective functions. Results are also verified by validating the Pareto fronts with simulation results using obtained optimized control parameters. The outcome from this work could provide field operators an opportunity to design a CO2-WAG project using as many inputs as possible from the reservoir models. The proposed work introduces a novel concept that couples Gaussian-SVR proxies with a self-adjusting protocol to increase the computational efficiency of the proposed workflow and to guarantee the high accuracy of the obtained optimized results. More importantly, the workflow can optimize a large number of control parameters used in a complex CO2-WAG process, which greatly extends its utility in solving large-scale MOO problems in various projects with similar desired outcomes.

Energy & Fuels↗