Oak Ridge National Laboratory Research Articles

Simulation of Boron Dose and Irradiation Time in Lung Cancer Treatment with Boron Neutron Capture Therapy (BNCT) Using MCNP-6

<p>Boron Neutron Capture Therapy (BNCT) is a cancer radiation treatment. This approach employs a boron carrier agent in the form of a chemical that is injected into the body and then travels to the cancer cells. In a lung cancer case study, BNCT treatment simulation was carried out using Monte Carlo N Particle (MCNP) software version 6.2. The goal of this study was to determine the most effective boron concentration and irradiation duration in lung cancer therapy utilizing the BNCT method. The geometry based on a phantom model created by Oak Ridge National Laboratory (ORNL). The simulated cancer geometry, which is placed in the right lung's middle lobe. The skin, ribs, and right lung are among the organs at risk. The skin, ribs, and right lung are among the organs at risk. The neutron source for the simulation is the collimator output from the Kartini Nuclear Reactor's thermal column. In this simulation, the variations in boron concentrations were 40 g/g, 45 g/g, 50 g/g, 55 g/g, and 60 g/g of cancer tissue at 5 g/g intervals. The researchers discovered a link between boron injection concentration and irradiation time, with higher boron injection concentrations resulting in shorter irradiation times. The volume of boron injected determines the effective dose absorbed by healthy tissue surrounding cancer cells. The effective boron concentration for lung cancer therapy is 60 g/g, with deterministic cell killing in the rib marrow and right lung. When utilizing a boron concentration of 60 g/g, the irradiation time is 20.4 minutes. Boron concentrations of 60 g/g are projected to create an effective irradiation time for BNCT-based lung cancer therapy based on the ALARA principle due to their shorter duration when compared to other concentration variations.</p>

Thermal deflection in neutron scattering sample environments at Oak Ridge National Laboratory.

The neutron sources at Oak Ridge National Laboratory use a wide suite of sample environment equipment to deliver extreme conditions for a number of experiments. Much of this instrumentation focuses on extremes of temperature, such as cryostats, closed-cycle refrigerators in both low and high temperature configurations, and radiant heating furnaces. When the temperature is controlled across a large range, thermal deflection effects can notably move the sample and affect its alignment in the beam. Here, we combine these sample environments with neutron imaging and machine vision to determine the motion of a representative sample with respect to the neutron beam. We find vertical sample displacement on the order of 1-2mm and horizontal displacement that varies from near-negligible to 1.2mm. While these deflections are not relevant for some of the beamlines at the first target station at the spallation neutron source and the high flux isotope reactor, they will become critical for upcoming instrumentation at the second target station, as well as any instruments targeting sub-mm samples, as neutron sources and optics evolve to smaller and more focused beams. We discuss mitigation protocols and potential modifications to the environment to minimize the effect of misalignment due to thermal deflection.

Incident beamline design for a modern cold triple axis spectrometer at the high flux isotope reactor

A modern cold triple axis spectrometer is being planned for the High Flux Isotope Reactor (HFIR) at Oak Ridge National Laboratory. Here, we describe the design of an incident beamline that will put a flux of ∼108ncm2s on a sample with an area of 2 cm x 2 cm. It takes current physical constraints at HFIR into account and it can accommodate both single and multiplexed analyzer-detector secondary spectrometers and large superconducting magnets. The proposed incident beamline includes a multi-channel guide with horizontal focusing, a neutron velocity selector, components to facilitate an incident beam polarization option, and a double-focusing pyrolytic graphite monochromator. This work describes the process of optimizing the guide system and monochromator and summarizes the expected performance of the incident beamline for non-polarized operation.

Federated Multiagent Deep Reinforcement Learning Approach via Physics-Informed Reward for Multimicrogrid Energy Management.

The utilization of large-scale distributed renewable energy (RE) promotes the development of the multimicrogrid (MMG), which raises the need of developing an effective energy management method to minimize economic costs and keep self energy sufficiency. The multiagent deep reinforcement learning (MADRL) has been widely used for the energy management problem because of its real-time scheduling ability. However, its training requires massive energy operation data of microgrids (MGs), while gathering these data from different MGs would threaten their privacy and data security. Therefore, this article tackles this practical yet challenging issue by proposing a federated MADRL (F-MADRL) algorithm via the physics-informed reward. In this algorithm, the federated learning (FL) mechanism is introduced to train the F-MADRL algorithm, thus ensures the privacy and the security of data. In addition, a decentralized MMG model is built, and the energy of each participated MG is managed by an agent, which aims to minimize economic costs and keep self energy sufficiency according to the physics-informed reward. At first, MGs individually execute the self-training based on local energy operation data to train their local agent models. Then, these local models are periodically uploaded to a server and their parameters are aggregated to build a global agent, which will be broadcasted to MGs and replace their local agents. In this way, the experience of each MG agent can be shared and the energy operation data are not explicitly transmitted, thus protecting the privacy and ensuring data security. Finally, experiments are conducted on Oak Ridge National Laboratory distributed energy control communication laboratory MG (ORNL-MG) test system, and the comparisons are carried out to verify the effectiveness of introducing the FL mechanism and the outperformance of our proposed F-MADRL.

Cross sections of neutral-current neutrino scattering on 98,100Mo isotopes

Coherent elastic neutrino–nucleus scattering (CEνNS) is a neutral-current low-energy electro-weak reaction-channel detected recently by the COHERENT experiment at the Oak Ridge National Laboratory (ORNL), USA, in the Spallation Neutron Source facility. The extremely weak signal on the CsI detector of the first experiment and on the liquid Ar of the repeated COHERENT experiment is the energy-recoil due to the neutrino–nucleus interaction, where the nucleus is elastically scattered as a whole while simultaneously the neutrino goes out. Today, several promising nuclear detectors are on the way to be employed in designed and ongoing experiments. In our present work, we provide predictions for incoherent scattering cross sections of low-energy neutrinos on 98,100Mo isotopes obtained with the deformed shell model employed previously for similar predictions in other electroweak processes. We mention that, Mo detector medium has been used previously in the MOON and NEMO double beta decay experiments.

Assessing contemporary Arctic habitat availability for a woolly mammoth proxy

Interest continues to grow in Arctic megafaunal ecological engineering, but, since the mass extinction of megafauna ~ 12–15 ka, key physiographic variables and available forage continue to change. Here we sought to assess the extent to which contemporary Arctic ecosystems are conducive to the rewilding of megaherbivores, using a woolly mammoth (M. primigenius) proxy as a model species. We first perform a literature review on woolly mammoth dietary habits. We then leverage Oak Ridge National Laboratories Distributive Active Archive Center Global Aboveground and Belowground Biomass Carbon Density Maps to generate aboveground biomass carbon density estimates in plant functional types consumed by the woolly mammoth at 300 m resolution on Alaska’s North Slope. We supplement these analyses with a NASA Arctic Boreal Vulnerability Experiment dataset to downgrade overall biomass estimates to digestible levels. We further downgrade available forage by using a conversion factor representing the relationship between total biomass and net primary productivity (NPP) for arctic vegetation types. Integrating these estimates with the forage needs of woolly mammoths, we conservatively estimate Alaska’s North Slope could support densities of 0.0–0.38 woolly mammoth km−2 (mean 0.13) across a variety of habitats. These results may inform innovative rewilding strategies.

Mitigating Missing Rate and Early Cyberattack Discrimination Using Optimal Statistical Approach with Machine Learning Techniques in a Smart Grid

In the Industry 4.0 era of smart grids, the real-world problem of blackouts and cascading failures due to cyberattacks is a significant concern and highly challenging because the existing Intrusion Detection System (IDS) falls behind in handling missing rates, response times, and detection accuracy. Addressing this problem with an early attack detection mechanism with a reduced missing rate and decreased response time is critical. The development of an Intelligent IDS is vital to the mission-critical infrastructure of a smart grid to prevent physical sabotage and processing downtime. This paper aims to develop a robust Anomaly-based IDS using a statistical approach with a machine learning classifier to discriminate cyberattacks from natural faults and man-made events to avoid blackouts and cascading failures. The novel mechanism of a statistical approach with a machine learning (SAML) classifier based on Neighborhood Component Analysis, ExtraTrees, and AdaBoost for feature extraction, bagging, and boosting, respectively, is proposed with optimal hyperparameter tuning for the early discrimination of cyberattacks from natural faults and man-made events. The proposed model is tested using the publicly available Industrial Control Systems Cyber Attack Power System (Triple Class) dataset with a three-bus/two-line transmission system from Mississippi State University and Oak Ridge National Laboratory. Furthermore, the proposed model is evaluated for scalability and generalization using the publicly accessible IEEE 14-bus and 57-bus system datasets of False Data Injection (FDI) attacks. The test results achieved higher detection accuracy, lower missing rates, decreased false alarm rates, and reduced response time compared to the existing approaches.

High pressure neutron diffraction study of magnetic ordering in erbium

We have studied magnetic ordering in polycrystalline erbium at high pressures up to 32 GPa and low temperatures down to 10 K using neutron diffraction techniques at the Spallation Neutron Source at Oak Ridge National Laboratory, USA. For the hexagonal close-packed (hcp) phase, strong nuclear and magnetic satellite intensities permit a simultaneous refinement of the nuclear and magnetic structures. At 1 GPa of applied pressure, a modulation vector q=γc∗ with γ≈2/7 for the c-axis modulated and cycloidal phases is consistent with prior single-crystal studies at low pressures. At 6.7 GPa in the hcp phase, we find γ≈0.31, indicating a reduction in the period of the magnetic structure with respect to the crystal lattice. The magnetic ordering temperature at 6.7GPa is slightly above 60 K. At 32 GPa in the double hexagonal close-packed phase, the magnetic scattering constrains the magnetic ordering temperature to 25±5 K. Our neutron diffraction study demonstrates that the magnetic ordering persists in the high-pressure double hexagonal close-packed phase of erbiumto the highest pressure of 32 GPa.

Equilibrium core modeling of a pebble bed reactor similar to the Xe-100 with SCALE

As the nuclear industry moves towards licensing and constructing advanced reactors, new attention has been focused on the advanced reactor designs that have past operational experience, such as pebble-bed high-temperature gas-cooled reactors (PB-HTGRs). Pebble-bed reactor designs have many advantages, such as their higher operating temperatures and online refueling capabilities. However, high-fidelity computational modeling of pebble-bed reactor designs, from reactor startup to operation at equilibrium, is more challenging compared to conventionally fueled reactors due to the continuous movement of the fuel pebbles through the reactor during operation. In previous work at Oak Ridge National Laboratory (ORNL), the SCALE Leap-In method for Cores at Equilibrium (SLICE) was developed around tools within the SCALE code system. This iterative method can effectively generate pebble-bed reactor zone-wise fuel inventories at equilibrium core operation within a reasonable computational time. The objective of this work was to further verify the ORNL SLICE method and to investigate the impact of considering temperature profiles during the application of the method. The SLICE method was applied to a modular high-temperature gas-cooled reactor design based upon publicly available design specifications of the Xe-100 pebble-bed reactor. Upon comparing the results from the SLICE method to published literature, the differences in the eigenvalue keffective were on the order of several hundred pcm (percent millirho). To investigate one possible cause of these differences, a study looking at the sensitivity of the full-core equilibrium keffective and discharge nuclide inventory to temperature was performed by developing equilibrium cores of two additional temperature profiles. From this temperature study, differences on the order of hundreds of pcm for the full-core equilibrium keffective, and up to 15% difference for the discharge inventories were found. These results indicated the strong dependence on temperature that needs to be considered for future work in equilibrium modeling of PB-HTGRs.

Key results from examinations of seven high burnup pressurized water reactor spent nuclear fuel rods

At present, spent nuclear fuel (SNF) assemblies discharged from US commercial power plants are placed into dry storage following a short cooling time (<10 years) in the plant’s spent fuel pool. The process of packaging the spent fuel into dry-storage canisters includes a drying step to remove residual water from the canister. During the drying process, the fuel rod cladding may reach temperatures as high as 400°C. Oak Ridge National Laboratory (ORNL) is performing destructive examinations of high burnup (HBU) (>45 GWd/MTU) SNF rods to address knowledge and data gaps related to extended interim storage and eventual transportation for disposal. The rods examined include four different kinds of fuel rod cladding: standard Zircaloy-4 (Zirc-4), low-tin (LT) Zirc-4, ZIRLO, and M5. Three rods were subjected to a thermal transient to assess the effects of decay-heat-driven high temperatures expected during vacuum drying of the fuel as it is prepared for interim dry storage. The examinations focus on the composite fuel rod performance, as compared with the performance of defueled rod cladding, and establish the baseline mechanical properties of a fuel rod before interim dry storage. The key results of these examinations are presented, including the measured mechanical and fatigue properties, observations of cladding hydrogen pickup and hydride reorientation effects on rod performance, effects of the simulated drying temperatures on rod performance, and general conclusions of SNF performance in extended interim dry storage and transport. The rods were found to be strong and durable in the expected loading conditions, even considering the formation of radial hydrides associated with vacuum drying. The combined testing provides a broad body of data supporting extended interim storage and transportation performance of HBU spent fuel.

A dataset of recorded electricity outages by United States county 2014–2022

In this Data Descriptor, we present county-level electricity outage estimates at 15-minute intervals from 2014 to 2022. By 2022 92% of customers in the 50 US States, Washington DC, and Puerto Rico are represented. These data have been produced by the Environment for Analysis of Geo-Located Energy Information (EAGLE-ITM), a geographic information system and data visualization platform created at Oak Ridge National Laboratory to map the population experiencing electricity outages every 15 minutes at the county level. Although these data do not cover every US customer, they represent the most comprehensive outage information ever compiled for the United States. The rate of coverage increases through time between 2014 and 2022. We present a quantitative Data Quality Index for these data for the years 2018–2022 to demonstrate temporal changes in customer coverage rates by FEMA region and indicators of data collection gaps or other errors.

New process allows full recovery of starting materials from tough polymer composites

On February 8, 2024, the Oak Ridge National Laboratory, announced, that inventors at the Department of Energy's Oak Ridge National Laboratory have designed a closed-loop path for synthesizing an exceptionally tough carbon-fiber-reinforced polymer, or CFRP, and later recovering all of its starting materials.

Implementation of a laser-neutron pump-probe capability for inelastic neutron scattering.

Knowledge about nonequilibrium dynamics in spin systems is of great importance to both fundamental science and technological applications. Inelastic neutron scattering (INS) is an indispensable tool to study spin excitations in complex magnetic materials. However, conventional INS spectrometers currently only perform steady-state measurements and probe averaged properties over many collision events between spin excitations in thermodynamic equilibrium, while the exact picture of re-equilibration of these excitations remains unknown. In this paper, we report on the design and implementation of a time-resolved laser-neutron pump-probe capability at hybrid spectrometer (beamline 14-B) at the Spallation Neutron Source (SNS) at Oak Ridge National Laboratory. This capability allows us to excite out-of-equilibrium magnons with a nanosecond pulsed laser source and probe the resulting dynamics using INS. Here, we discussed technical aspects to implement such a capability in a neutron beamline, including choices of suitable neutron instrumentation and material systems, laser excitation scheme, experimental configurations, and relevant firmware and software development to allow for time-synchronized pump-probe measurements. We demonstrated that the laser-induced nonequilibrium structure factor is able to be resolved by INS in a quantum magnet. The method developed in this work will provide SNS with advanced capabilities for performing out-of-equilibrium measurements, opening up an entirely new research direction to study out-of-equilibrium phenomena using neutrons.

Numerical Simulation of the Effect of Molten Salt Channel Number on Temperature Distribution in the Molten Salt Core Reactor

A critical aspect in the design of a nuclear reactor that needs to be considered is thermal analysis. This parameter relates to molten salt circulation, which serves as a fuel, and coolant in Molten Salt Reactor (MSR) core reactors. This study simulates the temperature distribution performance of the MSR core by considering the effect of the number of molten salt channels with inlet temperature variations. Knowing the temperature distribution will predict the characteristics of heat transfer in the form of natural convection for the survival of the reactor. The reactor used a Molten Salt Breeder Reactor (MSBR) design developed by Oak Ridge National Laboratory (ORNL). The Ansys software was used to simulate a 3D model under steady-state conditions. The geometry was divided into two regions: solid (graphite material) and fluid (molten salt). The thickness of the moderator and radius of the molten salt channel were 0.0508 and 0.0208 m, respectively. The moderator height was 1.98 m. The number of molten salt channels varied up to four. The results showed a temperature difference of 9 to 15 K when the channel increased from one to four at 839 K inlet temperature.

Classification of intrusion cyber‐attacks in smart power grids using deep ensemble learning with metaheuristic‐based optimization

AbstractThe most advanced power grid design, known as a ‘smart power grid’, integrates information and communication technology (ICT) with a conventional grid system to enable remote management of electricity distribution. The intelligent cyber‐physical architecture enables bidirectional, real‐time data sharing between electricity suppliers and consumers through smart meters and advanced metering infrastructure (AMI). Data protection issues, such as data tampering, firmware exploitation, and the leakage of sensitive information arise due to the smart power grid's substantial reliance on ICT. To maintain reliable and efficient power distribution, these issues must be identified and resolved quickly. Intrusion detection is essential for providing secure services and alerting system administrators in the case of adversary attacks. This paper proposes an intrusion classification scheme that identifies several types of cyber attacks on modern smart power grids. Grey‐Wolf metaheuristic optimization‐based feature selection is used to learn non‐linear, overlapping, and complex electrical grid properties. An extended deep‐stacked ensemble technique is advanced by putting predictions from weak learners (CNNs) into a meta‐learner (MLP). The outcomes of this approach are explained and confirmed using explainable AI (XAI). The publicly available dataset from Mississippi State University and Oak Ridge National Laboratory (MSU‐ORNL) is used to conduct experiments. The experimental results show that the proposed method achieved a peak accuracy of 96.6% while scrutinizing the original MSU‐ORNL data feature set and a maximum accuracy of 99% when analysing the selected feature set. Therefore, the proposed intrusion classification scheme may protect smart power grid systems against cyber security attacks.

A study on out-of-field leakage of an accelerator-based neutron beam for boron neutron capture therapy.

More and more accelerator-based boron neutron capture therapy (AB-BNCT) facilities are under the construction or commissioning stage, and the neutron beam characteristic measurements at each facility will start soon. In addition to the in-field neutron beam properties, the leakage of neutron beam is also important, which is related to the side effects of the patient. In the Virtual Technical Meeting on Advances in Boron Neutron Capture Therapy held by International Atomic Energy Agency (IAEA) in July 2020, the issue of the out-of-field leakage in BNCT was addressed. Heron Neutron Medical Corporation has been working on the beam design for China Medical University Hsinchu Hospital AB-BNCT research center. To evaluate the out-of-field leakage, both beam profile analysis and whole-body dose calculation are performed. An Oak Ridge National Laboratory (ORNL) Medical Internal Radiation Dose (MIRD) mathematical phantom is used to calculate the whole-body dose. For the estimated irradiation time which is set to be the time required for 80% of tumor dose to reach 20 Gy-w, the relative biological effectiveness weighted dose of abdomen region is less than 40 mGy-w and the whole-body dose is 104 mSv. The beam profile calculational result shows that the neutron ambient dose equivalent at 15 cm from the field edge is 11 mSv/Gy-w and drops to 5 mSv/Gy-w at 26 cm from the field edge. The gamma ray ambient dose equivalent is less than 1 mSv/Gy-w starting from 10 cm from the field edge. Although the neutron out-of-field leakage of the beam design is higher than that of the initially proposed guideline by IAEA in 2020, the whole-body dose, however, is reasonably low. Both the whole-body dose evaluation and the beam profile analysis are useful in the beam design consideration. The whole-body dose calculation together with the beam profile analysis can also be helpful in reaching an acceptable recommendation for the out-of-field leakage for BNCT neutron beam, a job wished to be accomplished in the near future as proposed in the 2023 IAEA's report on Advances in Boron Neutron Capture Therapy.

Inelastic neutron scattering: A unique tool to study hydrogen in materials

Inelastic neutron scattering (INS) spectroscopy can measure the vibrational spectra of materials on the whole range of vibrational motions (0–4400 cm-1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^{-1}$$\\end{document}) and effectively open up the field of neutron spectroscopy. Unlike optical spectroscopy, INS is a technique mainly used to study hydrogen-containing materials due to the high cross section of hydrogen and the lack of selection rules. The VISION spectrometer at the SNS in Oak Ridge National Laboratory has a flux at low energy transfers up to 40 times over its predecessors and has unprecedented sensitivity. Neutrons penetrate easily through materials, metals in particular, making complex sample environments and gas dosing relatively easy. Comparison of the INS spectra with computer models is rigorous and necessary to interpret INS data. This paper presents examples of the technique’s unique capabilities for studying metal hydrides and molecular hydrogen in confinement.Graphical abstract

Post-irradiation examination of commercial tantalum alloys following neutron irradiation

Post irradiation examination of two commercial tantalum alloys (based on Ta-8 %W) revealed significant irradiation hardening following neutron irradiation in the High Flux Isotope Reactor at Oak Ridge National Laboratory. Tensile samples of commercial Ta alloys T-111 and ASTAR-811C were irradiated to a total neutron fluence (E > 0.1 MeV) in the range (2–4)x1021 n/cm2 (0.39–0.75 dpa) at an irradiation temperature near 900 °C. Tensile testing conducted at room temperature and at 800 °C revealed significant irradiation hardening under all test conditions. Samples that were tensile tested at room temperature exhibited brittle failure, whereas ductility was maintained for elevated temperature testing. The irradiation hardening and embrittlement noted for both alloys was attributed to irradiation-induced dislocation loop formation as confirmed through scanning transmission electron microscopy analysis. Corresponding energy dispersive x-ray spectroscopy revealed radiation-induced segregation of Hf in these loop populations. This Hf enrichment is shown to result in eventual co-precipitation of elongated (Hf,O)-rich precipitates along the dislocation loops. These results show that irradiation hardening is enhanced via irradiation-enhanced precipitation at elevated irradiation temperatures. Consequently, the minimum recommended operating temperature window for Ta alloys should be increased to account for observed hardening/embrittlement at irradiation temperatures as high as 900 °C (1,173 K).

Optimization of the Second Target Station cold source moderators using an automated workflow

The Second Target Station (STS) at the US Department of Energy’s Oak Ridge National Laboratory is designed to become the world’s highest peak-brightness spallation source of cold neutrons. Successful completion of the STS, which is currently in the preliminary design phase, will provide transformative new capabilities to examine novel materials for future technologies. At STS, neutrons will be generated by spallation reactions in a solid tungsten target. They will be moderated and thermalized in two cold (20 K) para-hydrogen moderators. Careful optimization of these moderators is essential to the project’s success. To find optimal moderator designs, an advanced optimization workflow integrates high-fidelity neutronics calculations using the Monte Carlo N-Particle (MCNP) transport code MCNP6.2 with state-of-the-art optimization algorithms in the Dakota optimization toolkit. For each design iteration, a parametrized solid CAD geometry is generated in Creo and automatically converted into an unstructured mesh geometry by Attila 4MC for the neutronics calculation with MCNP. Iterations repeat until optimal designs are found. This paper presents the results of a sensitivity and optimization study for the cylindrical and tube moderators. Both moderators can be optimized for maximum peak brightness, maximum time-integrated brightness, or any combination between these extremes. Maximum peak brightness is achieved by using smaller optimal dimensions of the moderators, whereas maximum time-integrated brightness is achieved by using larger dimensions. A Pareto front details the designs that optimally balance both brightness metrics. The Pareto front can be found in only 40–110 iterations with 4–5 design parameters when using the efficient global and Pareto-set optimization algorithms in Dakota. Additionally, important engineering constraints can be taken into account, such as the coupling between the cylindrical moderator radius and aluminum vessel wall thicknesses required to ensure structural integrity of the vessels. This interaction has a significant impact on the resulting optimal designs. Our new, highly efficient, fully automated optimization workflow will be used to optimize additional STS components in the future and can be adopted for design and optimization studies at other experimental neutron and accelerator facilities.

Calibration of the 2-Phase Bubble Tracking Model for Liquid Mercury Target Simulation with Machine Learning Surrogate Models

The Spallation Neutron Source (SNS) at Oak Ridge National Laboratory is one of the most powerful accelerator-driven neutron sources in the world. The intense protons strike on SNS’s mercury target to provide bright neutron beams, which also leads to severe fluid-structure interactions inside the target. Prediction of resultant loading on the target is difficult particularly when helium gas is injected into mercury to reduce the loading and mitigate the pitting damage on vessel walls. A 2-phase material model that incorporates the Rayleigh-Plesset (R-P) model is expected to address this multi-physics problem. However, several uncertain parameters in the R-P model require intensive simulations to determine their optimal values. With the help of machine learning and the measured target strain, we have studied the major uncertain parameters in this R-P model and developed a framework to identify optimal parameters that significantly reduce the discrepancy between simulations and experimental strains. The preliminary results show the possibility of using this mercury/helium mixture and surrogate models to predict a better match of target strain response when the helium gas is injected.