Search NASA⌕ Search

SEARCH · Search NASA

Results for “error mitigation”

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 703 records · Page 39

Risk aware net load balancing in micro grids with high DER penetration

The rapid transformation of micro grids due to the accelerated integration of renewables, storage systems and IoT enabled monitoring and control has opened up new opportunities as well as challenges. Future micro grids will be characterized by high DER penetration and will require sophisticated net load balancing frameworks which explicitly consider the errors in prediction of load and generation due to uncertainty in weather conditions while making decisions. Traditional techniques for grid net load management which rely on isolated shaping of load and supply curves are inadequate and inefficient. For micro grids with high PV penetration, the intermittent and unpredictable nature of PV based energy generation can lead to dramatic and sudden supply demand imbalances thus requiring a holistic framework for balancing net load over the entire horizon. In this paper, we develop a sequential decision making framework for net load management that optimally balances the usage of storage and energy market transactions as a mechanism for mitigating supply demand imbalances (net load imbalances) over the horizon. Our framework specifically accounts for prediction uncertainty of future net load imbalances and minimizes the tail end risk of storage shortfall at the end of the horizon. Using qualitative analysis, we show that our framework achieves its objective of minimum cost net load balancing while accounting for the tail end risk.

14 SOLAR ENERGY↗

Calculating a minimum overlap period for successful intercalibration of soil moisture sensors

Abstract Long‐term in situ soil moisture monitoring inevitably requires sensors to be replaced. Ensuing discontinuities in the data record can be mitigated by intercalibration, however it is unclear how long the existing sensor needs to remain alongside the newly installed before there is enough overlapping data to generate a robust intercalibration. We used 154 pairs of established and newly installed sensors within the Marena, Oklahoma, In Situ Sensor Testbed to determine if there is a minimum overlap time that should be considered when planning upcoming replacements. Hourly observations of the existing sensor were linearly calibrated to those of the newly installed sensor with coefficients determined from overlap periods incremented by 30 days until a reference period of 2 years was reached. The resulting bias, root‐mean‐square error, and correlation coefficient for sensor pairs indicate that a minimum of 6 to 9 months of overlapping data are required to generate a successful intercalibration. Extending that to a full year before decommissioning the old sensor results in a stable intercalibration with higher confidence.

Agriculture↗

Green AI: Insights Into Deep Learning's Looming Energy Efficiency Crisis

As demands grow to integrate artificial intelligence into every aspect of industry, commerce, and life, deep learning's exploding energy cost has become a looming crisis, making AI systems a salient energy-efficiency challenge. One might expect that doubling a neural network's size would halve its error rate, or at least allow it to achieve greater performance given the same amount of time and energy. I will present clear and substantial scientific evidence which indicates that not only is this intuition wildly wrong, but that neural networks scale so poorly that to increase deep learning performance by only a small fraction can easily require an order of magnitude or more increase in computational resources and energy. Further, the marginal trade-off price of to increase model performance rapidly explodes as performance targets are increased. To address this challenge, I will provide a toolkit of techniques that can be applied today to mitigate the inefficiency of modern deep learning. And, I will conclude by illuminating a practical path forward towards efficient, Green AI.

artificial intelligence↗

Robust Estimation of Electron Density From Anatomic Magnetic Resonance Imaging of the Brain Using a Unifying Multi-Atlas Approach

Purpose: To develop a reliable method to estimate electron density based on anatomic magnetic resonance imaging (MRI) of the brain. Methods and Materials: We proposed a unifying multi-atlas approach for electron density estimation based on standard T1- and T2-weighted MRI. First, a composite atlas was constructed through a voxelwise matching process using multiple atlases, with the goal of mitigating effects of inherent anatomic variations between patients. Next we computed for each voxel 2 kinds of conditional probabilities: (1) electron density given its image intensity on T1- and T2-weighted MR images; and (2) electron density given its spatial location in a reference anatomy, obtained by deformable image registration. These were combined into a unifying posterior probability density function using the Bayesian formalism, which provided the optimal estimates for electron density. We evaluated the method on 10 patients using leave-one-patient-out cross-validation. Receiver operating characteristic analyses for detecting different tissue types were performed. Results: The proposed method significantly reduced the errors in electron density estimation, with a mean absolute Hounsfield unit error of 119, compared with 140 and 144 (P<.0001) using conventional T1-weighted intensity and geometry-based approaches, respectively. For detection of bony anatomy, the proposed method achieved an 89% area under the curve, 86% sensitivity, 88% specificity, and 90% accuracy, which improved upon intensity and geometry-based approaches (area under the curve: 79% and 80%, respectively). Conclusion: The proposed multi-atlas approach provides robust electron density estimation and bone detection based on anatomic MRI. If validated on a larger population, our work could enable the use of MRI as a primary modality for radiation treatment planning.

62 RADIOLOGY AND NUCLEAR MEDICINE↗

Stochastic Microgrid Scheduling With Chance‐Constrained Resilience Consideration

Traditionally, it is assumed that microgrids transition seamlessly from grid‐connected operation to islanded mode in the event of sudden main grid outages. In reality, the islanding process, especially unintentional islanding, is rarely seamless. Instead, it is subject to voltage and frequency fluctuations caused by the instantaneous disconnection of the point of common coupling (PCC) switch, variations in loads and renewable generation output and even the protection tripping of distributed energy resources (DERs). To mitigate these fluctuations and facilitate a smooth islanding process, we propose a stochastic microgrid scheduling model that incorporates chance‐constrained resilience measures. Specifically, the resilience measure is defined as the probability of successful islanding (PSI), that is, the probability that a microgrid can mitigate the generation‐demand imbalance caused by the disconnection of the PCC switch, variations in load and renewable generation and DER tripping. This measure is modelled using chance constraints. Unlike existing reliability and resilience indices, which typically neglect the possibility of microgrid/DER failure under extreme events and assume their survival while primarily focussing on reducing impact duration or magnitude, the proposed PSI‐based framework explicitly addresses microgrid and DER survival during the islanding transition. The formulated nonlinear chance constraints are approximated using a multiinterval approach and equivalently represented as a mixed‐integer linear programming (MILP) formulation. Case study results validate the proposed method, showing that the PSI estimation error is reduced to less than 8%, compared to approximately 28% with existing methods. Various sensitivity analyses on the DER tripping rate and PSI settings were performed to validate the robustness of the proposed method. In particular, the necessity of accounting for DER tripping in the PSI calculation was demonstrated.

chance constrained optimization↗

Novel Lightweight, Low-Cost Heliostat for Concentrating Solar Power (SBIR Phase I Final Report)

The overall goal of this Department of Energy (DOE) SBIR Phase I project was to demonstrate the feasibility of the L.Garde, Inc. heliostat mirror facet for use in concentrated solar power applications. Prior to this Phase I project, L.Garde, Inc. developed a design for a lightweight and low cost mirror facet and successfully fabricated small scale (0.667 m 2 ) with a mirror surface flatness of 0.7 mrad. Therefore, the focus of the Phase I effort was to (1) demonstrate scalability by fabricating larger size mirrors while retaining the same mirror surface flatness, (2) demonstrate the design can withstand operating environment conditions through field testing, and (3) perform cost analysis to show the heliostat mirror facet design can meet DoE goals of < 12 kg/m2 and <$30/m 2 . During the Phase I project, L.Garde successfully fabricated large area (1.395 m 2 ) heliostat mirror facets, with a mass per unit area of 8 kg/m 2 and a cost of $29.80/m 2 . Surface flatness measurements (using contact probe technique) were performed on the mirror surface and results showed a flatness of 0.68 mrad, which were in agreement with previously fabricated small scale mirror facets. Slope error measurements was also performed on the mirror surface and results showed a slope error of 0.77 mrad which also was in agreement with previously fabricated small scale mirror facets. One large area mirror facet was subjected to a three (3) month field test. Surface flatness and slope error measurements were performed on the mirror surface after the field test and results were 0.663 mrad and 0.58 mrad respectively. The large scale heliostat mirror facets were also subjected to accelerated aging. However, during this exposure we observed failure due to the breaking of the mirror facets. Further investigation into the source of the failure showed that the mirror component alone showed signs of degradation during the same accelerated aging test. We believe that moisture ingress is occurring when subjected to high humidity, leading to buildup of water with the layers of protective paints and resulting in mirror breakage when water expands in freezing conditions. In order to mitigate or eliminate this issue, a new weatherproofing strategy may be implemented or a new mirror component may be used that is able to survive accelerated aging conditions.

14 SOLAR ENERGY↗

Adaptive Cyber-Physical Resilience for Building Control Systems

The main goal of the project is to develop an AI-based process layer cybersecurity suite for detection, isolation and mitigation of cyber-attack effects on operation of building energy management systems (BEMS). The following constituent key technologies were developed under the program towards fulfilling the program objectives: (1) developed a high fidelity BEMS testbed for generation of training data and validation of developed technologies; (2) developed a physics informed ML based attack detection and localization module (ADL) capable of detecting high impact stealthy attacks (HISA - attacks causing 30% energy utilization but no immediate visible impact otherwise) with 98% accuracy; (3) developed a methodology to determine ’representative days’ to limit the data required for training; (4) developed a virtual sensing system that can reconstruct affected sensors with 10% error for the same HISA set; (5) developed a resilient model predictive control system that can continue operation of the BEMS without jeopardizing stability for the HISA set; and (6) integrated and deployed all the constituent modules and demonstrated the efficacy of the technology in real-time in a hardware in loop simulation.

42 ENGINEERING↗

A Greenhouse-Gas Information System - Monitoring and Validating Emissions Reporting and Mitigation - Chapter 2: Requirements Framework

The present study on a proposed greenhouse-gas information system (GHGIS) was undertaken without the benefit of requirements and specifications that will ultimately drive its choices and architecture. The discussion in this chapter attempts to develop a requirements framework that can be relied on to make choices between desired accuracy, precision, and confidence, vs. cost, schedule, and other elements. The accuracy or precision of the GHGIS (top-down) components required to validate reporting and international commitments depends on factors determined by the nature of the commitments as well as the goals of the users. The present study focuses on the task of measuring GHG emissions and attributing anthropogenic surface fluxes. This chapter explores possible emissions pathways that depart from targets and makes a number of assumptions about the needs of users to detect and quantify such departures, regardless of whether they are the result of inadvertent or willful reporting errors. Such user needs would be used to set GHGIS requirements.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗

Suppression of fiber modal noise induced radial velocity errors for bright emission-line calibration sources

Modal noise in optical fibers imposes limits on the signal-to-noise ratio (S/N) and velocity precision achievable with the next generation of astronomical spectrographs. This is an increasingly pressing problem for precision radial velocity spectrographs in the near-infrared (NIR) and optical that require both high stability of the observed line profiles and high S/N. Many of these spectrographs plan to use highly coherent emission-line calibration sources like laser frequency combs and Fabry-Perot etalons to achieve precision sufficient to detect terrestrial-mass planets. These high-precision calibration sources often use single-mode fibers or highly coherent sources. Coupling light from single-mode fibers to multi-mode fibers leads to only a very low number of modes being excited, thereby exacerbating the modal noise measured by the spectrograph. We present a commercial off-the-shelf solution that significantly mitigates modal noise at all optical and NIR wavelengths, and which can be applied to spectrograph calibration systems. Our solution uses an integrating sphere in conjunction with a diffuser that is moved rapidly using electrostrictive polymers, and is generally superior to most tested forms of mechanical fiber agitation. We demonstrate a high level of modal noise reduction with a narrow bandwidth 1550 nm laser. Our relatively inexpensive solution immediately enables spectrographs to take advantage of the innate precision of bright state-of-the art calibration sources by removing a major source of systematic noise.

79 ASTRONOMY AND ASTROPHYSICS↗

Completely Positive Map for Noisy Driven Quantum Systems Derived by Keldysh Expansion

Accurate modeling of decoherence errors in quantum processors is crucial for analyzing and improving gate fidelities. To increase the accuracy beyond that of the Lindblad dynamical map, several generalizations have been proposed, and the exploration of simpler and more systematic frameworks is still ongoing. In this paper, we introduce a decoherence model based on the Keldysh formalism. This formalism allows us to include non-periodic drives and correlated quantum noise in our model. In addition to its wide range of applications, our method is also numerically simple, and yields a CPTP map. These features allow us to integrate the Keldysh map with quantum-optimal-control techniques. We demonstrate that this strategy generates pulses that mitigate correlated quantum noise in qubit state-transfer and gate operations.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

MODELING AND PARAMETRIC STUDY OF END-GAS AUTOIGNITION TO ALLOW THE REALIZATION OF ULTRA-LOW EMISSIONS, HIGH-EFFICIENCY HEAVY-DUTY SPARK-IGNITED NATURAL GAS ENGINES

Engine knock and misfire are barriers to pathways leading to high-efficiency Spark-Ignited (SI) Natural Gas (NG) engines. The general tendency to knock is highly dependent on engine operating conditions and the fuel reactivity. The problem is further complicated by the low emission limits and the wide range of chemical reactivity in pipeline-quality natural gas. Depending on the region and the source of the natural gas, its reactivity, described by its Methane Number (MN), which is analogous to the Octane Number for liquid SI fuels, can span from 65 to 95. In order to realize diesel-like efficiencies, SI NG engines must be designed to operate at high Brake Mean Effective Pressures (BMEP), near or beyond knock limits, over a wide range of fuel reactivity. This requires a deep understanding of the combustion-engine interactions pertaining to flame propagation and End-Gas Autoignition (EGAI), i.e., the autoignition of the unburned gas (end gas) ahead of the flame front. However, EGAI, if controlled, provides an opportunity to increase SI NG engine efficiency by increasing the combustion rate and the total fraction of burned fuel, mitigating the effects of the slow flame speeds characteristic of natural gas fuels, which generally reduce BMEP and increase unburned hydrocarbon emissions. For this reason, to realize diesel-like efficiencies and ultra-low emissions on SI NG engines, this work proposes the study of the main parameters influencing the modeling and prediction of NG EGAI to allow for its control. In this work, a novel EGAI detection and onset determination method was developed to reliably quantify EGAI for data analysis and engine control. The new method allowed the prediction of EGAI on SI NG engines without the need to use engine- and operating-condition-dependent thresholds and reduced the error in quantifying the fraction of the total energy released by the EGAI event by up to 40%pts. One- and three-dimensional engine models were then developed to study the engine/fuel interactions that lead to NG EGAI and its performance benefits. These models, although having decent agreement with experimental data, showed the need to account for NOx chemistry when predicting NG EGAI due to a consistently later prediction of the EGAI onset (~1.65 crank-angle degrees) and thus, a new reduced chemical mechanism for real NG fuels was developed containing NOx chemistry. The new reduced mechanism improved the EGAI onset prediction agreement to within ±0.5 crank-angle degrees and decreased simulation time during combustion by nearly 50% when using the further reduced AREIS50NOx chemical mechanism. These models were then used to study the role of NG composition on EGAI, evaluate the engine/fuel interactions leading to NG EGAI, and perform engine optimization while leveraging EGAI to increase thermal efficiency. Piston design optimization combined with a Controlled EGAI (C-EGAI) combustion mode allowed a Heavy-Duty (HD) SI NG engine to operate at diesel-like efficiencies, i.e., Brake Thermal Efficiency (BTE) ≥44%. Experimental and modeling data analysis revealed that earlier and faster heat release increases combustion efficiency by an average of 1%pts, increases work transferred to the piston resulting in a decrease in exhaust losses by 50% depending on the engine operating condition while slightly increasing heat losses. Finally, the simulation results revealed an opportunity to further enhance the BTE (up to 50%) by enabling C-EGAI combustion at leaner conditions, λ=1.4-1.6.

Bestel, Diego Bernardi↗

A Moving Target Defense Control Framework for Cyber-Physical Systems

This paper considers the problem of efficiently and securely controlling cyber-physical systems that are operating in uncertain, and adversarial environments. To mitigate sensor, actuator attacks, and performance loss due to such attacks, we formulate a secure control algorithm that consists of a proactive and a reactive defense mechanism. The proactive mechanism, which is based on the principles of moving target defense, utilizes a stochastic switching structure to dynamically and continuously alter the parameters of the system, while hindering the attacker's ability to conduct successful reconnaissance to the system. The unpredictability of the current actuator and sensor is optimized using an information entropy measure, which is induced by probabilistic switching. The reactive mechanism on the other side, detects potentially attacked components, namely sensors and actuators, by leveraging online data to compute an integral Bellman error. A rigorous mathematical framework is presented to guarantee the stability of the equilibrium point of the closed-loop system, and provide a quantified bound on the performance loss when utilizing both reactive and proactive mechanisms. Simulation results show the efficacy of the proposed approaches on a benchmark aircraft model.

42 ENGINEERING↗

SU-F-T-249: Application of Human Factors Methods: Usability Testing in the Radiation Oncology Environment

Purpose: As a quality improvement measure, we undertook this work to incorporate usability testing into the implementation procedures for new electronic documents and forms used by four affiliated radiation therapy centers. Methods: A human factors specialist provided training in usability testing for a team of medical physicists, radiation therapists, and radiation oncologists from four radiotherapy centers. A usability testing plan was then developed that included controlled scenarios and standardized forms for qualitative and quantitative feedback from participants, including patients. Usability tests were performed by end users using the same hardware and viewing conditions that are found in the clinical environment. A pilot test of a form used during radiotherapy CT simulation was performed in a single department; feedback informed adaptive improvements to the electronic form, hardware requirements, resource accessibility and the usability testing plan. Following refinements to the testing plan, usability testing was performed at three affiliated cancer centers with different vault layouts and hardware. Results: Feedback from the testing resulted in the detection of 6 critical errors (omissions and inability to complete task without assistance), 6 non-critical errors (recoverable), and multiple suggestions for improvement. Usability problems with room layout were detected at one center and problems with hardware were detected at one center. Upon amalgamation and summary of the results, three key recommendations were presented to the document’s authors for incorporation into the electronic form. Documented inefficiencies and patient safety concerns related to the room layout and hardware were presented to administration along with a request for funding to purchase upgraded hardware and accessories to allow a more efficient workflow within the simulator vault. Conclusion: By including usability testing as part of the process when introducing any new document or procedure into clinical use, associated risks can be identified and mitigated before patient care and clinical workflow are impacted.

60 APPLIED LIFE SCIENCES↗

Implementation of a Time-domain Cosmic-Ray-Muon Tagger for the NEXUS Low-background Cryogenic Facility

Quantifying the effects of radiation on the operation of qubits both as quantum information systems as well as particle detectors has emerged as a pressing issue in quantum science in recent years. We present an overview of the design, operation, and deployment of a 90-$\mathrm{in}^2$ three-panel muon detector for use in the NEXUS experimental facility at Fermilab to temporally isolate correlated errors in qubits and determine if they possess an astrophysical origin. Constructed with three scintillator-attached PMTs read out with NIM modules in a triply-coincident logic scheme, we measure a surface-level muon luminosity of 9.7425 muons per second---consistent with an average surface-level cosmic-ray flux of approximately one muon per square centimeter per minute. Integrating the NIM modules with an MCC 128 DAQ HAT and Raspberry Pi, a Python script records exactly when a muon struck the detector and writes a timestamp to a log file for follow-up cross referencing. This experiment will broadly contribute to further studies aimed at understanding the source and mitigation of information loss in qubits.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Implementation of a Time-domain Cosmic-ray-muon Tagger for the NEXUS Low-background Cryogenic Facility

Quantifying the effects of radiation on the operation of qubits both as quantum information systems as well as particle detectors has emerged as a pressing issue in quantum science in recent years. We present an overview of the design, operation, and deployment of a 90-$\mathrm{in}^2$ three-panel muon detector for use in the NEXUS experimental facility at Fermilab to temporally isolate correlated errors in qubits and determine if they possess an astrophysical origin. Constructed with three scintillator-attached PMTs read out with NIM modules in a triply-coincident logic scheme, we measure a surface-level muon luminosity of 9.7425 muons per second---consistent with an average surface-level cosmic-ray flux of approximately one muon per square centimeter per minute. Integrating the NIM modules with an MCC 128 DAQ HAT and Raspberry Pi, a Python script records exactly when a muon struck the detector and writes a timestamp to a log file for follow-up cross referencing. This experiment will broadly contribute to further studies aimed at understanding the source and mitigation of information loss in qubits.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Unveiling the Potential of MeshGraphNets for Predicting Subsurface Evolution in Carbon Storage Projects

This is the conference paper accompanying an oral presentation “Unveiling the Potential of MeshGraphNets for Predicting Subsurface Evolution in Carbon Storage Projects” at the 17th International Conference on Greenhouse Gas Control Technologies GHGT-17 held in Calgary, Canada, October 20-24 , 2024. Carbon capture and storage (CCS) technology is critical for mitigating climate change but requires effective subsurface reservoir management to ensure safe containment of injected CO2. Accurate predictions of reservoir pressure and saturation are essential for assessing long-term CCS performance. Traditional numerical simulations, while effective, are computationally intensive, time-consuming, and constrained by data discretization. Previous work has shown the effectiveness of MeshGraphNets (MGN), a graph-based machine learning framework, as an innovative alternative for predicting reservoir behavior. MGN leverages graph neural networks (GNNs) and mesh representations to model complex geological formations, offering superior adaptability across different discretizations and reservoir configurations. Classic MGN implementations utilize an autoregressive technique to predict future behavior based on current predictions, but this technique is hampered by error accumulation over time. To enhance the model accuracy in time-series predictions, this study implemented a multi-step rollout strategy that integrates autoregressive predictions during training to stabilize prediction of saturation over time. Using the Illinois Basin – Decatur Project (IBDP) dataset, comprising 100 simulations of CO2 injection, pressure, and saturation changes, the framework demonstrated its ability to learn spatial dependencies and temporal dynamics. With inputs including permeabilities, porosities, and injection rates, MGN accurately predicted CO2 plume evolution over time, even with limited training data. Moreover, the addition of a multi-step rollout procedure during training improved the ability of MGN to predict stably over time by ~15%. This research positions MGN, enhanced with multi-step rollout capabilities, as a robust and efficient tool for CCS applications. It advances the field by enabling precise, computationally efficient predictions of reservoir behavior, providing a foundation for the broader adoption of machine learning frameworks in CCS and other geoscience domains.

Holcomb, Paul↗

Novel application of neutrinos to evaluate U.S. nuclear weapons performance

There is a growing realization that neutrinos can be used as a diagnostic tool to better understand the inner workings of a nuclear weapon. Robust estimates demonstrate that an Inverse Beta Decay (IBD) neutrino scintillation detector built at the Nevada Test Site with a 1000-ton active target mass at a standoff distance of 500 m would detect thousands of antineutrino events per nuclear test. This would provide less than 4% statistical error on the measured antineutrino rate and 5% error on antineutrino energy. Extrapolating this to an error on the test device explosive yield requires knowledge from evaluated nuclear databases, non-equilibrium fission rates, and assumptions on internal neutron fluxes. Initial calculations demonstrate that the total number of neutrinos emitted per fission in the first 10 3 s after a short pulse of 239 Pu fission is about a factor of two less than that from Pu fissioning under steady state conditions. Furthermore, there are significant energy spectral differences as a function of time after the pulse that must be considered. These and other model dependencies will be discussed in the paper. In the absence of nuclear weapons testing, many of the technical and theoretical challenges of a full nuclear test could be mitigated with a low cost smaller scale 20 ton fiducial mass IBD demonstration detector placed near a pulsed reactor. Potential reactors include the Texas A&M University TRIGA 1 GW–10 ms pulsed facility or the Sandia Annular Core Research Reactor. The short duty cycle and repeatability of pulses would provide critical real environment testing and measurements, which would be valuable for planning a possible real test shot in the future. Furthermore, the antineutrino rate as a function of time data would provide unique constraints on fission databases and model assumptions. Finally, there are impactful science drivers such as sensitive searches for ∼1 eV 2 sterile neutrinos and ∼MeV scale axions.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

Improving Subsurface Stress Characterization for Carbon Dioxide Storage Projects by Incorporating Machine Learning Techniques

The overall objective of this project is to develop a framework for reliable characterization and prediction of the state of stress in the overburden and underburden (including the basement) in CO 2 storage reservoirs using machine learning and integrated geomechanics and geophysical methods. Specifically, we propose to develop workflow encompassing of technologies and/or methods to predict stress and pressure changes due to CO 2 injection in an active tertiary recovery site and their impacts on subtle fault activation, fractures and occurrence of microseismic events and compare responses to field observations. In this project, we anticipate using dataset from the Farnsworth field Unit (FWU) which is operated by Purdure Petroleum. A novel elastic-waveform VSP inversion technique will be used to estimate high-resolution spatial and temporal changes of elastic moduli in CO 2 storage reservoirs, which will be combined with velocity-stress relationship derived from laboratory tests to obtain subsurface pressure and stress. Clustered microseismic data will be jointly inverted for improved focal mechanisms. Least-squares reverse-time migration of microseismic waveform data will be performed to directly image fracture/fault zones. Additionally, a deep neural network machine learning technique with convolutional and recurrent layers will be used for learning the spectro-temporal structures in microseismic waveforms. The results of this geotechnical data analysis will be integrated to develop a high-resolution 3D mechanical earth model extending from the overburden sealing formations to the underburden including the basement. Mechanical properties will be derived through integration of mechanical logs, tests, available results from chemo-mechanical laboratory tests, and elastic inversion of seismic data using a combination of Bayesian and stochastic methods as well as machine learning technique. Failure features (faults/fractures) will be represented and/or modeled based on seismic and core data analysis. A transient hydrodynamic-geomechanical model will be developed through coupling with the calibrated FWU reservoir simulation model. The full physics coupled model will be used to train a reduced order proxy model using machine learning algorithm for estimating stress which will then be used with appropriate constitutive relationships and forward seismological models to simulate pressure changes and induced microseismicity. An advanced optimization framework will be developed to perform a history match to minimize error between field observations and simulated. The history matched proxy model will be verified against the full-physics equivalent. The field observations that will be used in the coupled model calibration process include pressure/stress inverted from VSP, moment magnitude from microseismic analysis, real time downhole pressure measurements, production and injection data. Parameter sensitivity and uncertainty analysis will be performed to characterize the impact of model parameter uncertainty on stress estimates. The proposed project will have significant impact on future field implementation of the proposed technology. Because the project field site is an ongoing CO 2 EOR development, the value of the new technology will be demonstrated in an operational context and evaluated as a viable risk mitigation strategy. Cost/benefit will be evaluated together with the various commercial incentives for CO 2 sequestration available to oil and gas operators. The extensive available dataset and ongoing data acquisition under the SWP Phase III work plan provides flexibility for investigation of multiple approaches and reduces technical risk.

58 GEOSCIENCES↗