Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “robust execution”

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 109 records · Page 6

The Geothermal Entrepreneurship Organization (GEO) Accelerating Technology Transfer, Testing and Adoption of Cutting-edge Extreme Environment Drilling

The Geothermal Entrepreneurship Organization launched in 2019 with the goal of building a geothermal innovation ecosystem at the University of Texas at Austin (UT Austin), and in the State of Texas at large. The theses underlying the work of GEO were 1) that with targeted advocacy, recruitment, organization, and coalition building, research institutions with legacy excellence in petroleum and geosystems engineering could become engines of geothermal innovation, research and development; 2) that startups were the appropriate vehicle to speed these innovations from the lab into the field, and building a geothermal startup ecosystem in Texas would not only advance next generation geothermal concepts into the field, but also help spur oil and gas engagement in the space, and 3) that with targeted engagement, education, and recruitment across stakeholders in the oil and gas industry and the State of Texas generally, the oil and gas industry, and other legacy oil and gas entities in the State could become sources of large scale deployment of geothermal energy. The overall goal was to create a ‘snowball’ effect, where targeted impactful actions would catalyze self-sustaining, organic growth of a new geothermal ecosystem in the State of Texas. That goal was achieved through GEO’s work. To test its theses, GEO began work by interviewing and recruiting UT Austin faculty and alumni into geothermal. At the beginning of the GEO project, there was no geothermal activity ongoing within the UT Austin Petroleum and Geosystems Engineering Department, the Bureau of Economic Geology, or the Jackson School of Geoscience, and many faculty approached had not before considered how their skillsets might apply in the space. By the end of the project period, three major research consortia focused on geothermal were launched as a result of GEO’s work, one at the Bureau of Economic Geology, one within the Petroleum and Geosystems Engineering Department, and another organized by GEO across six research institutions across the State of Texas, called the Texas Geothermal Institute. Geothermal curricula was launched at UT Austin, and UT Austin began attracting new geothermal enthusiasts into its faculty, including Dr. Silviu Livescu, former Chief Scientist of Baker Hughes. Startups recruited and mentored by GEO launched, raised funding, and deployed (or are currently deploying) their concepts in the field. By the end of the project period, the GEO concept expanded to faculty beyond UT Austin to other institutions, like Texas A&M, the University of Houston, and Rice University, and geothermal engagement began at those institutions as well. Multiple faculty members and alumni across these institutions launched geothermal startup companies, launched geothermal research consortia, and/or began teaching geothermal courses. In 2020, GEO launched what was to become the largest geothermal conference in the world by its second year, ‘PIVOT – From Hydrocarbons to Heat’, and the resulting momentum catalyzed the Society of Petroleum Engineers to launch a geothermal technical section, drove more startups to launch out of the ecosystem, and drove actors in the State of Texas, NGOs, and stakeholders globally to become engaged. Riding this momentum, the Texas Geothermal Energy Alliance was launched, the first ever industry association dedicated to advancing geothermal energy in the State of Texas. The Texas geothermal ecosystem after only two years of building and support is now robust, quickly growing, and self-sustaining. By 2021, the Texas geothermal ecosystem had attracted the attention of philanthropists, funding entities, media, and influencers outside of Texas, and GEO’s executive director was invited to give a TED talk about oil and gas engagement in building the future of geothermal energy, which elevated the success of the ecosystem to a global audience.

15 GEOTHERMAL ENERGY↗

EnergyPlus Model Context Protocol Server (EnergyPlus-MCP) v0.1

EnergyPlus-MCP is the first open-source Model Context Protocol server specifically designed for EnergyPlus building energy simulation. This innovative software enables AI assistants and other applications to interact programmatically with EnergyPlus through a standardized, secure interface, eliminating traditional technical barriers in building energy modeling. The software provides specialized tools across five functional domains: server management, model configuration and loading, comprehensive building component inspection, systematic model modification, and simulation execution with results visualization. Key features include automated HVAC system discovery and topology mapping, advanced schedule analysis, intelligent model validation, and interactive visualization capabilities. EnergyPlus-MCP's layered architecture ensures robust separation between protocol communication and domain expertise, enabling scalable deployment across organizations, educational institutions, and research teams. Unlike direct LLM approaches that suffer from inconsistent results and security gaps, EnergyPlus-MCP provides validated, reliable interactions while maintaining scientific rigor. This democratizes sophisticated building energy analysis, making EnergyPlus accessible to broader audiences through conversational interfaces and streamlined workflows.

Li, Han [Lawrence Berkeley National Laboratory (LB↗

Current Best Practices on Wildfire Risk Reduction for Electric Transmission and Distribution Systems

This report provides a set of best practices in response to Section 4(d) of Executive Order 14308, Empowering Commonsense Wildfire Prevention and Response. The information contained herein is expected to be used in conjunction with other materials at the Federal Energy Regulatory Commission Wildfire Risk Mitigation Technical Conference (Docket No. AD25-16-000), with possible direction to the North American Electric Reliability Corporation to take action. The objective of this report is to provide an overview of existing and emerging best practices currently employed or planned by utilities for wildfire mitigation, demonstrating how these efforts align with the executive order’s emphasis on reducing electric utility–caused wildfires while also balancing cost-effectiveness. Additionally, while most practices in utility-developed wildfire mitigation plans focus on risk reduction through robustness and operational reliability, this report also discusses best practices for resilience. The best practices are adopted from publicly available utility wildfire mitigation plans from the United States and Canada, recent findings from wildfire risk reduction research, and industry engagement.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Three practical workflow schedulers for easy maximum parallelism

Runtime scheduling and workflow systems are an increasingly popular algorithmic component in HPC because they allow full system utilization with relaxed synchronization requirements. There are so many special-purpose tools for task scheduling, one might wonder why more are needed. Use cases seen on the Summit supercomputer needed better integration with MPI and greater flexibility in job launch configurations. Preparation, execution, and analysis of computational chemistry simulations at the scale of tens of thousands of processors revealed three distinct workflow patterns. A separate job scheduler was implemented for each one using extremely simple and robust designs: file-based, task-list based, and bulk-synchronous. Comparing to existing methods shows unique benefits of this work, including simplicity of design, suitability for HPC centers, short startup time, and well-understood per-task overhead. All three new tools have been shown to scale to full utilization of Summit, and have been made publicly available with tests and documentation. This work presents a complete characterization of the minimum effective task granularity for efficient scheduler usage scenarios. Here, these schedulers have the same bottlenecks, and hence similar task granularities as those reported for existing tools following comparable paradigms.

97 MATHEMATICS AND COMPUTING↗

Integrating Applied Energy and BER Smart Data Capabilities to Develop a DOE Data Fabric for Energy-Water R&D

Focal Area(s): 1) Data acquisition and assimilation enabled by machine learning, AI, and advanced methods including experimental/network design/optimization, unsupervised learning (including deep learning), and hardware-related efforts involving AI (e.g., edge computing). Science Challenge: DOE R&D, including DOE’s Basic Energy Research (BER)’s Environmental Systems Science Division (EESSD) program and DOE’s applied energy research (AER) programs (EERE, FE, and NE) are producers and consumers of Earth systems datasets. This white paper focuses on the first topic area from the call in relation to how crosscutting resources and innovations from DOE’s EESSD and AER can be brought to bear to mutual benefit and more efficient energy-water, Earth system data resources through improved. The overarching challenge posed by this call focuses on how DOE can directly leverage artificial intelligence (AI) to engineer a substantial (paradigm-changing) improvement in Earth System Predictability? While stemming from DOE BER’s EESSD program, this is a challenge that is faced and also being addressed by DOE’s AER programs. Over the past decade plus, FE, EERE, and NE programs have made important strides towards addressing this need. These strides are in many ways highly complementary to EESSD’s MODEX efforts. Energy water systems spanning metocean to groundwater to surface water systems all are data driven whether for basic energy or applied energy. These are remote, multi-variate, complex natural, and in many cases engineered, systems. Key needs and challenges of both EESSD and AER include developing data-focused tools to enhance data search and discovery to fill in knowledge gaps (address sparse data challenge), and rapidly transform datasets, including disparate and multi-source data. Leveraging DOE on-premise computing (HPC, exascale) infrastructure supports the computing-intensive algorithms required to execute these data acquisition and transformation processes to derive enriched knowledge and data, driving AI/ML and big data analytics for these systems. The opportunity lies in combining BER and AER efforts to provide a more robust, advanced, efficient and complete computing data fabric to address energy-water data acquisition and assimilation needs which currently pose significant impediments to AI/ML predictions and research.

54 ENVIRONMENTAL SCIENCES↗

ENHANCING SEISMIC CALIBRATION RESEARCH THROUGH SOFTWARE AUTOMATION AND SCIENTIFIC INFORMATION MANAGEMENT

The National Nuclear Security Administration (NNSA) Ground-Based Nuclear Explosion Monitoring Research and Development (GNEMRD) Program at LLNL continues to make significant progress enhancing the process of deriving seismic calibrations and performing scientific integration, analysis, and information management with software automation tools. Our tool efforts address the problematic issues of very large datasets and varied formats encountered during seismic calibration research. New information management and analysis tools have resulted in demonstrated gains in efficiency of producing scientific data products and improved accuracy of derived seismic calibrations. The foundation of a robust, efficient data development and processing environment is comprised of many components built upon engineered versatile libraries. We incorporate proven industry 'best practices' throughout our code and apply source code and bug tracking management as well as automatic generation and execution of unit tests for our experimental, development and production lines. Significant software engineering and development efforts have produced an object-oriented framework that provides database centric coordination between scientific tools, users, and data. Over a half billion parameters, signals, measurements, and metadata entries are all stored in a relational database accessed by an extensive object-oriented multi-technology software framework that includes stored procedures, real-time transactional database triggers and constraints, as well as coupled Java and C++ software libraries to handle the information interchange and validation requirements. Significant resources were applied to schema design to enable management of processing methods and station parameters, responses and metadata. This allowed for the development of merged ground-truth (GT) data sets compiled by the NNSA labs and AFTAC that include hundreds of thousands of events and tens of millions of arrivals. The schema design groundwork facilitated extensive quality-control and revalidation steps. In support of the GT merge effort, a comprehensive site merge process was also accomplished this year that included station site information for tens of thousands of entries from NNSA labs, AFTAC, NEIC, ISC, and IRIS. A core capability is the ability to rapidly select and present subsets of related signals and measurements to the researchers for analysis and distillation both visually (JAVA GUI client applications) and in batch mode (instantiation of multi-threaded applications on clusters of processors). RBAP Version 2 is one such example. Over the past year RBAP was significantly improved in capability and performance. A new role-based security model now allows fine-grain access control over all aspects of the tool's functions enabling researchers to share their work with others without fear of unintended parameter alterations. A new, faster and more reliable GIS mapping framework was added, as well as expanded powerful interactive plotting graphics. In addition, we implemented parent-child type projects to enhance calibration data management. Our specific automation methodology and tools improve the researchers ability to assemble quality-controlled research products for delivery into the NNSA Knowledge Base (KB). The software and scientific automation tasks provide the robust foundation upon which synergistic and efficient development of GNEMRD Program seismic calibration research may be built.

58 GEOSCIENCES↗

A Scalable HPC Insider Threat Monitoring System

Cyber Equations, Inc. is reporting on the results of its DOE SBIR Phase I project for the development of a Scalable HPC Insider Threat Monitoring System. This final report to the Department of Energy for Task DE-FOA-0001618 covers the period from 02/21/2017 to 02/20/2018 and summarizes the larger research accomplishments, which can be divided in theoretical and laboratory experiments. One of the many challenges for the U.S. Department of Energy (DOE) is the support of the high-performance computing (HPC) centers while providing quality information services, strategic vision, leadership, technical expertise, and capabilities necessary to enable the DOE to deliver effective, efficient, economical, and secure HPC services. In order to realize a secure DOE laboratory enterprise, DOE facilities operations must counter a wide range of cyber insider threats, from unsophisticated adversaries up to advanced, nation state sponsored actors. The DOE laboratories also presents an enormous insider attack surface of an ever-growing number of computers, networks, and devices all running a myriad of software. In addition, the DOE laboratories are connected to a variety of external organizations which multiplies the possibility of insider threat. During this SBIR project Cyber Equations developed a strategic combination of supervised and unsupervised machine learning techniques to control scale and classify whether entities, such as hosts, actors, or documents, are showing suspicious insider behavior. We conducted experiments using real cyber data to show that changes in observable behavior (e.g., changes in outbound traffic patterns) are indicative of attacks executing (e.g., insiders exfiltrating data, bots calling home, or an attack spreading). The features and methods we use, have been used in the anomaly detection research and development community for a significant amount of time and robust implementations are openly available. K-Means clustering, Decision Trees, and Support Vector Machine based classifiers are readily available through the R language and open source H20 machine learning framework. The Cyber Equations approach is novel in its use of these classifiers combined with Hadoop based parallel processing technology. The five stages of processing used by CyberInsider improve scalability and reduce the high number of false positives normally associated with network anomaly detection. In summary, the Cyber Equations has successfully accomplished all of its Phase I tasks and demonstrated the feasibility of the Insider Threat Monitoring System.

97 MATHEMATICS AND COMPUTING↗

Design and Licensing of Irradiated Uranyl Nitrate Liquid Containers and Applicable Loading and Packaging System - 18481

Irradiated highly enriched uranyl nitrate liquid (HEUNL) solutions are typically residual materials resulting from the processing of uranium target materials in the production of radioisotopes. Traditionally, these residual materials have been processed and stored at the site of origin, due to the lack of an option for packaging, transportation and disposition. Modern alternatives to process, stabilize, package and dispose of these materials have been developed, but until recently there has not been a viable Type B package solution that could be used to ship these materials in sufficient quantities to justify the cost of an off-site disposition strategy. For this reason, most facilities that generate irradiated HEUNL materials have implemented on-site storage tanks or containers, resulting in the significant accumulation of HEUNL inventories worldwide. This paper provides an overview of the design and licensing activities for the development of sealed irradiated HEUNL transport containers to permit safe transportation of this material in the NAC Legal Weight Truck (NAC-LWT) cask. A description of the robust HEUNL container, licensing and fabrication is also presented. In addition, NAC has developed a specialized loading system to optimize the process to load, package and un-package HEUNL materials to minimize worker exposure during loading, and execute the packaging process efficiently for safe transport and retrieval. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗

Trajectory Shaper: A Solution for Disrupted Cooperative Adaptive Cruise Control

Cooperative adaptive cruise control (CACC) can effectively reduce energy consumption, alleviate traffic congestion, and enhance safety. However, communication-related constraints and uncooperative vehicle users can disrupt CACC during real-world operations, significantly undermining the putative benefits of CACC. To alleviate the negative impacts of disrupted CACC, this study develops the trajectory shaper (TS) methods as backup solutions for two scenarios: (i) communication between vehicles is infeasible, and vehicles execute adaptive cruise control (ACC) using local sensor measurements; (ii) follower vehicles reject forming a cooperative platoon and execute their local distributed controllers using the information attained via communication. When communication is infeasible, a distributed TS is devised on each vehicle to modify the sensor measurements, enabling safe and efficient ACC operations. When communication is available but uncooperative agents are involved, the lead vehicle of the platoon executes a centralized TS to modify the information shared with uncooperative agents, achieving optimal platoon-level performance. The centralized and distributed TSs are implemented based on the model predictive control algorithms to yield optimal modifications on input information. Robustness is also factored to tackle model uncertainties during TS operations to ensure safety and efficiency. Numerical experiments validate the control performance of the proposed TSs.

Zhou, Anye [ORNL] (ORCID:0000000301455579)↗

Repositioning Quantum Cellular Automata for Dependable Quantum-Classical Systems

Quantum Cellular Automata (QCA) provides a structured model of distributed quantum computation with inherent locality and regularity properties that are suited to dependable execution. However, QCA remain largely absent from discussions on reproducibility, fault management, and orchestration in heterogeneous quantum-classical systems. We propose a dual-axis framework that situates QCA within both computation and physical realizability, revealing regions where robust, scalable, and hardware-constrained quantum dynamics may reside. By revisiting prior results through the lens of reproducibility and architecture resilience, we suggest that QCA offers a potential substrate for benchmarking and system-level co-design.

Stapleton, Nicholas [ORNL] (ORCID:0000000335305325↗

Scalable line and plane relaxation in a parallel structured multigrid solver

The efficient solution of sparse, linear systems that arise through the discretization of partial differential equations remains a key challenge for a range of high performance scientific simulations. One approach for reducing data movement and improving performance is by exposing and exploiting structure in a problem through the use of robust structured multilevel solvers. By choosing coarsening that preserves the structure of the problem, these methods maintain efficient structured computation and communication throughout the multigrid hierarchy. However, when coarsening is not permitted to be dependent on the operator, anisotropy must be addressed by the smoother — producing error compatible for coarse-grid correction with structured coarsening. Here, the components required in a scalable parallel structured solver are described with a focus on memory and communication efficiency of robust smoothers. While the implementation of communication and memory reduction techniques in smoothers integrated in a complete 3D solver present a significant engineering challenge, a novel approach is proposed that addresses these challenges systematically through a change to the solver’s execution model. Enabled by user-level threading paired with a set of data and communication abstractions, this approach permits seamless aggregation of communication in plane smoothers — directly reusing code for a 2D distributed multilevel cycle. Results show an effective reduction in communication costs for coarse-grid problems, and result in a speedup of 8.7x in smoothing routines shown in Fig. 12 using this approach. This produces a significant improvement to strong scalability while maintaining favorable weak scaling behavior. Finally, a parallel scaling study using a series of refined meshes is included that demonstrates the effectiveness of this approach in an application of interest.

97 MATHEMATICS AND COMPUTING↗

WARP

WARP, which can stand for ``Weaving All the Random Particles,'' is a three-dimensional (3D) continuous energy Monte Carlo neutron transport code developed at UC Berkeley to efficiently execute on NVIDIA graphics processing unit (GPU) platforms. WARP accelerates Monte Carlo simulations while preserving the benefits of using the Monte Carlo method, namely, that very few physical and geometrical simplifications are applied. WARP is able to calculate multiplication factors, neutron flux distributions (in both space and energy), and fission source distributions for time-independent neutron transport problems. It can run in both criticality or fixed source modes, but fixed source mode is currently not robust, optimized, or maintained in the newest version. WARP can transport neutrons in unrestricted arrangements of parallelepipeds, hexagonal prisms, cylinders, and spheres. The goal of developing WARP is to investigate algorithms that can grow into a full-featured, continuous energy, Monte Carlo neutron transport code that is accelerated by running on GPUs. The crux of the effort is to make Monte Carlo calculations faster while producing accurate results. Modern supercomputers are commonly being built with GPU coprocessor cards in their nodes to increase their computational efficiency and performance. GPUs execute efficiently on data-parallel problems, but most CPU codes, including those for Monte Carlo neutral particle transport, are predominantly task-parallel. WARP uses a data-parallel neutron transport algorithm to take advantage of the computing power GPUs offer.

Bergmann, RyanM. [University of California - Berke↗

WARP

WARP, which can stand for ``Weaving All the Random Particles,'' is a three-dimensional (3D) continuous energy Monte Carlo neutron transport code developed at UC Berkeley to efficiently execute on NVIDIA graphics processing unit (GPU) platforms. WARP accelerates Monte Carlo simulations while preserving the benefits of using the Monte Carlo method, namely, that very few physical and geometrical simplifications are applied. WARP is able to calculate multiplication factors, neutron flux distributions (in both space and energy), and fission source distributions for time-independent neutron transport problems. It can run in both criticality or fixed source modes, but fixed source mode is currently not robust, optimized, or maintained in the newest version. WARP can transport neutrons in unrestricted arrangements of parallelepipeds, hexagonal prisms, cylinders, and spheres. The goal of developing WARP is to investigate algorithms that can grow into a full-featured, continuous energy, Monte Carlo neutron transport code that is accelerated by running on GPUs. The crux of the effort is to make Monte Carlo calculations faster while producing accurate results. Modern supercomputers are commonly being built with GPU coprocessor cards in their nodes to increase their computational efficiency and performance. GPUs execute efficiently on data-parallel problems, but most CPU codes, including those for Monte Carlo neutral particle transport, are predominantly task-parallel. WARP uses a data-parallel neutron transport algorithm to take advantage of the computing power GPUs offer.

Bergmann, Ryan M.↗

Algorithms and analyses for stochastic optimization for turbofan noise reduction using parallel reduced-order modeling

Simulation-based optimization of acoustic liner design in a turbofan engine nacelle for noise reduction purposes can dramatically reduce the cost and time needed for experimental designs. Because uncertainties are inevitable in the design process, a stochastic optimization algorithm is posed based on the conditional value-at-risk measure so that an ideal acoustic liner impedance is determined that is robust in the presence of uncertainties. A parallel reduced-order modeling framework is developed that dramatically improves the computational efficiency of the stochastic optimization solver for a realistic nacelle geometry. The reduced stochastic optimization solver takes less than 500 s to execute. Additionally, well-posedness and finite element error analyses of the state system and optimization problem are provided.

97 MATHEMATICS AND COMPUTING↗

An end-to-end workflow for executing a classically bootstrapped variational quantum algorithm on an academic quantum computer

Academic quantum computing platforms often face unique challenges in executing quantum workloads due to fragmented software environments and limited engineering support. Unlike commercial ecosystems, academic devices typically evolve without full-stack integration in mind, making it difficult to run complex applications—such as variational quantum algorithms (VQA)—reliably and efficiently. Issues such as incompatible software layers and lack of automated job management significantly increase the overhead of theory-experiment collaboration. To address these challenges, we develop a modular, end-to-end workflow that decouples application-layer code from low-level hardware control, automates circuit submission and result collection, and supports fine-grained circuit-level job scheduling and recovery. The architecture employs a dual-end application programming interface (API) design, enabling robust operation across unstable or resource-constrained hardware backends. For practical use, the framework is lightweight and user-friendly, allowing rapid prototyping of full-stack workflows using basic Python tools. We validate this workflow on a high-fidelity trapped-ion quantum computer by demonstrating a variational quantum eigensolver (VQE) experiment with a classically bootstrapped ansatz initialization technique. The system successfully executed over 60,000 circuits across multiple molecular test cases with minimal human intervention, highlighting the framework’s effectiveness in enabling reproducible, resilient quantum experimentation in academic settings.

Clifford↗

Improving robustness and computational efficiency using modern C++

For nearly two decades, the C++ programming language has been the dominant programming language for experimental HEP. The publication of ISO/IEC 14882:2011, the current version of the international standard for the C++ programming language, makes available a variety of language and library facilities for improving the robustness, expressiveness, and computational efficiency of C++ code. However, much of the C++ written by the experimental HEP community does not take advantage of the features of the language to obtain these benefits, either due to lack of familiarity with these features or concern that these features must somehow be computationally inefficient. In this paper, we address some of the features of modern C+-+, and show how they can be used to make programs that are both robust and computationally efficient. We compare and contrast simple yet realistic examples of some common implementation patterns in C, currently-typical C++, and modern C++, and show (when necessary, down to the level of generated assembly language code) the quality of the executable code produced by recent C++ compilers, with the aim of allowing the HEP community to make informed decisions on the costs and benefits of the use of modern C++.

Paterno, M.↗

File-Based Data Flow in the CMS Filter Farm

During the LHC Long Shutdown 1, the CMS Data Acquisition system underwent a partial redesign to replace obsolete network equipment, use more homogeneous switching technologies, and prepare the ground for future upgrades of the detector front-ends. The software and hardware infrastructure to provide input, execute the High Level Trigger (HLT) algorithms and deal with output data transport and storage has also been redesigned to be completely file- based. This approach provides additional decoupling between the HLT algorithms and the input and output data flow. All the metadata needed for bookkeeping of the data flow and the HLT process lifetimes are also generated in the form of small “documents” using the JSON encoding, by either services in the flow of the HLT execution (for rates etc.) or watchdog processes. These “files” can remain memory-resident or be written to disk if they are to be used in another part of the system (e.g. for aggregation of output data). We discuss how this redesign improves the robustness and flexibility of the CMS DAQ and the performance of the system currently being commissioned for the LHC Run 2.

Andre, J. M.↗

Physics-informed machine learning with differentiable programming for heterogeneous underground reservoir pressure management

Abstract Avoiding over-pressurization in subsurface reservoirs is critical for applications like CO $$_2$$ 2 sequestration and wastewater injection. Managing the pressures by controlling injection/extraction are challenging because of complex heterogeneity in the subsurface. The heterogeneity typically requires high-fidelity physics-based models to make predictions on CO $$_2$$ 2 fate. Furthermore, characterizing the heterogeneity accurately is fraught with parametric uncertainty. Accounting for both, heterogeneity and uncertainty, makes this a computationally-intensive problem challenging for current reservoir simulators. To tackle this, we use differentiable programming with a full-physics model and machine learning to determine the fluid extraction rates that prevent over-pressurization at critical reservoir locations. We use DPFEHM framework, which has trustworthy physics based on the standard two-point flux finite volume discretization and is also automatically differentiable like machine learning models. Our physics-informed machine learning framework uses convolutional neural networks to learn an appropriate extraction rate based on the permeability field. We also perform a hyperparameter search to improve the model’s accuracy. Training and testing scenarios are executed to evaluate the feasibility of using physics-informed machine learning to manage reservoir pressures. We constructed and tested a sufficiently accurate simulator that is 400 000 times faster than the underlying physics-based simulator, allowing for near real-time analysis and robust uncertainty quantification.

54 ENVIRONMENTAL SCIENCES↗