SEARCH · Engineering Papers

Results for “Prediction Accuracy”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

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

At least 307 records · Page 17

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Integration and Optimization of a Waste Heat Driven Organic Rankine Cycle for Power Generation in Wastewater Treatment Plants

The study focuses on achieving energy self-sufficiency in Wastewater Treatment Plants by proposing a comprehensive model for integrating, sizing, and optimizing an Organic Rankine Cycle system. The Organic Rankine Cycle system is designed to utilize waste heat from the gensets at As Samra Wastewater Treatment Plant in Jordan, where it will contribute to the overall electrical energy supply of the plant. Real data from As Samra Wastewater Treatment Plant is used to model and calculate the available waste heat using TRNSYS® software. The Organic Rankine Cycle model is then developed using ASPEN PLUS® software to explore the impact of operational parameters and determine their optimal values for maximizing the plant's energy profile. An economic analysis is conducted to assess the feasibility of the proposed model, considering system components, installation, operation, and maintenance costs. To optimize the Organic Rankine Cycle system, the study employs the Multi-Output Support Vector Regression technique to capture nonlinear relationships between independent variables (fluid type, turbine inlet pressure, turbine inlet temperature, turbine outlet pressure, and mass flow rate) and dependent variables (pump power input, waste heat input, and turbine specific work). The Osprey optimization algorithm is used to address the multi-objective optimization problem, with the proposed Pareto-based Osprey Optimization Algorithm and the Multi-Objective Particle Swarm Optimization technique being employed to evaluate critical performance and economic parameters such as system thermal efficiency, net power output, and the levelized cost of electricity. The results of the optimization strategies indicate that the M-SVR model's prediction accuracy is significantly improved after parameter optimization, with the model returning high R 2 and low Mean Square Error values of 0.991 and 0.00216, respectively. The Pareto-Based Osprey Optimization Algorithm optimizer identifies the best working fluid as Isobutane/Isopentane in a ratio of 66:34, with optimal turbine inlet pressure and temperature of 15 bars and 218 °C, respectively. In conclusion, the Organic Rankine Cycle model at these optimal conditions achieves a cycle efficiency of 19.93% and an Levelized Cost of Electricity value of 0.0353 USD/kWh.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2025

Techno-economic implications and cost of forecasting errors in solar PV power production using optimized deep learning models

Accurate solar Photovoltaic (PV) power forecasting is important for enhancing both the performance and economic feasibility of PV systems. This study evaluates several deep learning models, including Dense Neural Networks (DNN), Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), and a hybrid LSTMCNN model, for predicting PV power production one day in advance. Prior to optimization, the models exhibited relatively high errors, with the best model (DNN) achieving a Root Mean Square Error (RMSE) of 31.13 kW and a coefficient of determination (R 2 ) of 62.15 %. After employing Bayesian optimization, the LSTM-CNN model demonstrated the best performance, with the RMSE reduced to 9.79 kW and R 2 improved to 97.62 %, showcasing significant enhancement in predictive accuracy. Here, the economic evaluation considered three cases: rewards for underestimation (0.08 USD/kWh), no rewards, and penalties for both over-and underestimation (120 % of the utility tariff). In the rewards scenario, the LSTM-CNN model reduced the Levelized Cost of Electricity (LCOE) by 4 %, while in the penalty scenario, a backup diesel generator would have increased the LCOE by 49 %. Additionally, the LSTM-CNN model minimized financial losses, achieving the lowest penalties and maximizing net cash flow compared to other models, demonstrating its overall technical and economic superiority.

Deep learning↗

DOE OSTI2022

Forecasting battery capacity and power degradation with multi-task learning

Lithium-ion batteries degrade due to usage and exposure to environmental conditions, which affects their capability to store energy and supply power. Accurately predicting the capacity and power fade of lithium-ion battery cells is challenging due to intrinsic manufacturing variances and coupled nonlinear ageing mechanisms. In this paper, we propose a data-driven prognostics framework to predict both capacity and power fade simultaneously with multi-task learning. The model is able to predict the degradation trajectory of both capacity and internal resistance together with knee-points and end-of-life points accurately at early-life stage. The validation shows an average percentage error of 2.37% and 1.24% for the prediction of capacity fade and resistance rise, respectively. The model's ability to accurately predict the degradation, facing capacity and resistance estimation errors, further demonstrates the model's robustness and generalizability. Compared with single-task learning models for forecasting capacity and power degradation, the model shows a significant prediction accuracy improvement and computational cost reduction. This work presents the highlights of multi-task learning in the degradation prognostics for lithium-ion batteries.

25 ENERGY STORAGE↗

DOE OSTI2021

Inter-well connectivity detection in CO 2 WAG projects using statistical recurrent unit models

Routine well-wise injection and production measurements contain significant information on subsurface structure and properties. Data-driven technology that interprets surface data into subsurface structure or properties can assist operators in making informed decisions by providing a better understanding of field assets. Our machine-learning framework is built on the statistical recurrent unit (SRU) model and interprets well-based injection/production data into inter-well connectivity without relying on a geologic model. We test it on synthetic and field-scale CO 2 EOR projects utilizing the water-alternating-gas (WAG) process. SRU is a special type of recurrent neural network (RNN) that allows for better characterization of temporal trends, by learning various statistics of the input at different time scales. In our application, the complete states (injection rate, pressure and cumulative injection) at injectors and pressure states at producers are fed to SRU as the input and the phase rates at producers are treated as the output. Once the SRU is trained and validated, it is then used to assess the connectivity of each injector to any producer using permutation variable importance method, wherein inputs corresponding to an injector are shuffled and the increase in prediction error at a given producer is recorded as the importance (connectivity metric) of the injector to the producer. This method is tested in both synthetic and field-scale cases. The validation of the proposed data-driven inter-well connectivity assessment is performed using synthetic data from simulation models where inter-well connectivity can be easily measured using the streamline-based flux allocation. The SRU model is shown to offer excellent prediction performance on the synthetic case. Despite significant measurement noise and frequent well shut-ins imposed in the field-scale case, the SRU model offers good prediction accuracy, the overall relative error of the phase production rates at most producers ranges from 10% to 30%. It is shown that the dominant connections identified by the data-driven method and streamline method are in close agreement. This significantly improves confidence in our data-driven procedure. The novelty of this work is that it is purely data-driven method and can directly interpret routine surface measurements to intuitive subsurface knowledge. Furthermore, the streamline-based validation procedure provides physics-based backing to the results obtained from data analytics. This study results in a reliable and efficient data analytics framework that is well-suited for large field applications.

42 ENGINEERING↗

DOE OSTI2025

Quantifying spatial and vertical variations in soil C:N relationships in permafrost-affected landscapes

Permafrost regions are experiencing rapid changes that affect carbon (C) and nitrogen (N) cycles, with implications for vegetation dynamics and gas exchanges with the atmosphere. Soil C:N ratio is a key indicator of organic matter quality, yet spatial estimates of N stocks and C:N ratios lag behind those for C. We used quantile regression forests to compare direct and indirect digital soil mapping approaches for predicting soil C:N ratios at 0–30, 30–60, and 60–100 cm depths across a latitudinal transect in Alaska. The indirect approach – deriving C:N from separately predicted C and N stocks – outperformed direct mapping for the surface layer (0–30 cm), while direct mapping was marginally better at greater depths. However, prediction accuracy decreased with depth for both methods. Temperature and topography were the most important predictors. Both approaches overestimated low and underestimated high C:N ratios, with direct mapping showing greater bias. Our results underscore the challenges of modeling C:N ratios in heterogeneous, data-sparse permafrost soils, but also suggest that indirect mapping holds promise if supported by more extensive datasets.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

Regional-scale soil carbon predictions can be enhanced by transferring global-scale soil–environment relationships

Accurate modelling and mapping soil organic carbon are crucial for supporting soil health restoration and climate change mitigation at both regional and global scales. However, regional soil predictions often suffer from data scarcity and high prediction uncertainty. Utilizing a pre-trained global-to-regional soil carbon predictive model can be a potential solution to address this challenge. Despite its promise, how to construct and apply the global-scale model to enhance regional-scale soil carbon mapping remains largely unexplored. Here, we propose the Global Soil Carbon Pre-trained Model (GSoilCPM), a deep-learning-based domain adaptative model, to enhance regional-scale soil carbon predictions. Based on large amount of environmental covariate data and 106,167 soil samples across the globe, we verify our hypothesis of the effectiveness of this 'global-to-regional' modelling strategy. The pre-trained model can be then transferred and fine-tuned to bridge the regional- and global-scale soil–environment relationships. We applied and validated this modelling strategy in four regional-scale study areas, three in the Northern Hemisphere and one in the Southern Hemisphere, each with distinct environmental background. Compared to traditional modelling approaches as a baseline, four case studies all demonstrated significant improvement in prediction accuracy across diverse environments and varying data availabilities. The average percentage improvement across all regions is 10.93% (absolute values decreased by 1.20 g kg−1 averagely) in MAE and 29.04% (absolute values increased by 0.10 averagely) in CCC. The applicability and future horizons of using GSoilCPM were further discussed. We further reveal that regions with fewer soil samples or lower baseline accuracy benefit more from the pre-trained global model. Our findings highlight the advantages of leveraging the generalized knowledge from global models to enhance specifically localized soil modelling, positioning a potential paradigm shift in digital soil mapping, and far-reaching implications for soil monitoring and land management.

Deep learning↗

DOE OSTI2025

Physics augmented machine learning discovery of composition-dependent constitutive laws for 3D printed digital materials

Multi-material 3D printing, particularly through polymer jetting, enables the fabrication of digital materials by mixing distinct photopolymers at the micron scale within a single build to create a composite with tunable mechanical properties. Here, this work presents an integrated experimental and computational investigation into the composition-dependent mechanical behavior of 3D printed digital materials. We experimentally characterize five formulations, combining soft and rigid UV-cured polymers under uniaxial tension and torsion across three strain and twist rates. The results reveal nonlinear and rate-dependent responses that strongly depend on composition. To model this behavior, we develop a physics-augmented neural network (PANN) that combines a partially input convex neural network (pICNN) for learning the composition-dependent hyperelastic strain energy function with a quasi-linear viscoelastic (QLV) formulation for time-dependent response. The pICNN ensures convexity with respect to strain invariants while allowing non-convex dependence on composition. To enhance interpretability, we apply $L_0$ sparsification. For the time-dependent response, we introduce a multilayer perceptron (MLP) to predict viscoelastic relaxation parameters from composition. The proposed model accurately captures the nonlinear, rate-dependent behavior of 3D printed digital materials in both uniaxial tension and torsion, achieving high predictive accuracy for interpolated material compositions. This approach provides a scalable framework for automated, composition-aware constitutive model discovery for multi-material 3D printing.

Constitutive modeling↗

DOE OSTI2025

Pool boiling heat transfer evaluation of next-generation dielectric fluid: Opteon™ 2P50

The growing use of artificial intelligence has led to heavy thermal loads and high heat dissipation rates in data centers. Conventional air-cooled technologies are not able to fulfill these requirements. To overcome these challenges, two-phase immersion cooling (2PIC) has emerged as one of the leading technologies for high power-density chips. 2PIC increases the heat dissipation rate and efficiency of the system while reducing the footprint of the cooling equipment. A fluid with adequate dielectric properties, a suitable normal boiling temperature to maintain chip temperatures, and good material compatibility, is desired for 2PIC system. In this study, the pool boiling heat transfer of a new developmental dielectric fluid, Opteon™ 2P50, was experimentally investigated. The heat transfer coefficients at various heat fluxes (20–150 kW/m 2 ) and the critical heat flux were measured using a smooth aluminum surface. Compared with HFE-7100, Opteon™ 2P50 shows higher heat transfer coefficient (up to 59% higher) and a slightly lower value of critical heat flux (around 5.9% lower). The modified Cooper correlation with the optimized leading constant resulted in reliable prediction accuracy with a 5.3% mean absolute error percentage. Overall, these results indicate that the new dielectric fluid provides similar thermal performance to some legacy fluids.

2P50↗

DOE OSTI2024

A machine-learning-aided data recovery approach for predicting multi-material thermal behaviors in advanced test reactor capsules

Instrumented experiments conducted at test reactors are essential to the deployment of new advanced reactor systems. Designing new experiments and generating data on specific reactor conditions require significant investments in terms of both time and cost. Finite element analysis software can be used to create high-fidelity models of experiment environments in order to support the actual experiments, but computation time remains a concern in terms of applying outcomes to real-time usage of data (e.g., a digital twin [DT]). Here, the present research proposes a machine-learning (ML) aided approach to making temperature and displacement predictions based on the thickness of the outer gas gap on the experimental capsule used for in-pile demonstration of a novel new thermal conductivity probe in the Advanced Test Reactor (ATR). This capsule consisted of U10Zr fuel, a rodlet, sodium, and inner and outer capsules. Gas gaps existed between the fuel and the rodlet, and between the inner and the outer capsule. The learning data pertained to an experimental capsule's radial distributions of temperature and displacement, as obtained based on Abaqus and the physical features. For the first step of ML sequence, the temperature was predicted using three positional parameters. Next, the displacement was predicted using seven additional parameters. Each physical feature was normalized in order to be both nondimensional and standardized. The temperature and displacement predictions showed good agreement with the simulation results in all cases involving interpolation and extrapolation. Furthermore, data similarity enhancement increased the similarity between the training and the target data, thereby increasing the predictive accuracy of the ML models. In certain extrapolation cases involving limited original ML model accuracy, data similarity enhancement and data recovery was able to somewhat improve this accuracy.

11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗

DOE OSTI2026

Two-phase flow numerical analysis of electrode geometry for alkaline water electrolyzers

Hydrogen is a promising component of a future energy-secure and efficient economy, but its competitiveness depends on reducing production costs. One strategy is to operate alkaline water electrolyzers at higher current densities to increase output. However, this intensifies performance losses due to gas bubble accumulation, which blocks transport pathways and deactivates electrochemically active surfaces. Enhancing bubble evacuation through electrode design is therefore essential. Previous studies have explored various approaches — such as modifying surface morphology, applying sonication or pressure modulation, and introducing surfactants — but these efforts have addressed a limited range of conditions due to the complexity of two-phase flow and electrode geometries. Experiments have also largely been focused on either cell level improvements, which lack the information necessary to isolate each contributing factor, or on modified geometries that are not relevant to practical cell operation. From a modeling perspective, conventional Eulerian multiphase models do not track the complex gas–liquid interfacial dynamics and often neglect surface tension and contact angle effects, reducing their predictive accuracy. To provide insights on the effects of different electrode geometries on the performance of alklaine water electrolyzers this work employs an immersed boundary volume-of-fluid method to simulate bubble behavior in 3D porous electrodes. Multiple base electrode geometries, typically used in practice, with varying porosity are evaluated under a constant surface gas generation rate. Simulation data is analyzed to quantify electrode gas coverage, bubble size dynamics and other relevant metrics. Results show that porosity strongly influences bubble accumulation on electrode surfaces, with higher porosity reducing gas coverage, and its not strictly dependent on the electrode geometry. However, the electrode’s base geometry significantly affects gas accumulation at the separator gap, independent of porosity. A foam electrode geometry resulted in the lowest gas coverage of all electrodes with a median volumetric gas coverage of 11%, but at the cost of a 70% reduction in active area compared with the largest surface area electrode, while gyroid electrodes showed the best trade-off between gas coverage, particularly at the separator surface, and electrochemically active area. In conclusion, the results highlight the need for holistic electrode design strategies.

Alkaline↗

DOE OSTI2020

A new flow pattern map for flow boiling of R410A in horizontal micro-fin tubes considering the effect of the helix angle

This paper presents an improved flow pattern map for flow boiling in horizontal micro-fin tubes considering the effect of helix angle. The proposed map is modified from the one developed for horizontal smooth tubes by Wojtan et al. (2005) and takes the early transition to annular flow due to micro-fin geometry into account. Visualization of R410A flow boiling is carried out through the transparent smooth and micro-fin tubes with 0°, 10° and 18° helix angle and plotted on the proposed map for comparison. The result shows that the flow pattern map for micro-fin tube with 0° helix angle is generally similar to that for the smooth tube. For the tube with 10° and 18° helix angle, the annular flow occurs at lower vapor quality and lower mass flux. The proposed map shows good agreements when compared with the visualization and reflects the downward shift (to lower mass flux and vapor quality conditions) of the SW-WA transition with the increase of the helix angle. In order to further validate the proposed model, the flow pattern transitions calculated from the equations are also compared with the experimental data of the micro-fin tube in literature. The results show that the modified map increase the prediction accuracy of the flow patterns in the micro-fin tube.

42 ENGINEERING↗

DOE OSTI2022

A gradient-based deep neural network model for simulating multiphase flow in porous media

We report simulation of multiphase flow in porous media is crucial for the effective management of subsurface energy and environment-related activities. The numerical simulators used for modeling such processes rely on spatial and temporal discretization of the governing mass and energy balance partial-differential equations (PDEs) into algebraic systems via finite-difference/volume/element methods. These simulators usually require dedicated software development and maintenance, and suffer low efficiency from a runtime and memory standpoint for problems with multi-scale heterogeneity, coupled-physics processes or fluids with complex phase behavior. Therefore, developing cost-effective, data-driven models can become a practical choice, and in this work, we choose deep learning approaches as they can handle high dimensional data and accurately predict state variables with strong nonlinearity. In this paper, we describe a gradient-based deep neural network (GDNN) constrained by the physics related to multiphase flow in porous media. We tackle the nonlinearity of flow in porous media induced by rock heterogeneity, fluid properties, and fluid-rock interactions by decomposing the nonlinear PDEs into a dictionary of elementary differential operators. We use a combination of operators to handle rock spatial heterogeneity and fluid flow by advection. Since the augmented differential operators are inherently related to the physics of fluid flow, we treat them as first principles prior knowledge to regularize the GDNN training. We use the example of pressure management at geologic CO 2 storage sites, where CO 2 is injected in saline aquifers and brine is produced, and apply GDNN to construct a predictive model that is trained with physics-based simulation data and emulates the physics process. We demonstrate that GDNN can effectively predict the nonlinear patterns of subsurface responses, including the temporal and spatial evolution of the pressure and saturation plumes. We also successfully extend the GDNN to convolutional neural network (CNN), namely gradient-based CNN (GCNN), and validate its capability to improve the prediction accuracy. GDNN has great potential to tackle challenging problems that are governed by highly nonlinear physics and enable the development of data-driven models with higher fidelity.

42 ENGINEERING↗

DOE OSTI2026

Identifying stochastic dynamics via finite expression methods

Modeling stochastic differential equations (SDEs) is crucial for understanding complex dynamical systems in various scientific fields. Recent methods often employ neural network-based models, which typically represent SDEs through a combination of deterministic and stochastic terms. However, these models usually lack interpretability and have difficulty in generalizing beyond their training domain. Here, this paper introduces the Finite Expression Method (FEX), a symbolic learning approach designed to derive interpretable mathematical representations of the deterministic component of SDEs. For the stochastic component, we integrate FEX with advanced generative modeling techniques to provide a comprehensive representation of SDEs. The numerical experiments on linear, nonlinear, and multidimensional SDEs demonstrate that FEX generalizes well beyond the training domain and delivers more accurate long-term predictions compared to neural network-based methods. The symbolic expressions identified by FEX not only improve prediction accuracy but also offer valuable scientific insights into the underlying dynamics of the systems.

Complex dynamical systems↗

DOE OSTI2026

Efficient data-driven regression for reduced-order modeling of spatial pattern formation

We present an efficient data-driven regression approach for constructing reduced-order models (ROMs) of reaction-diffusion systems exhibiting pattern formation. The ROMs are learned non-intrusively from available training data of physically accurate numerical simulations. The method can be applied to general nonlinear systems through the use of polynomial model form, while not requiring knowledge of the underlying physical model, governing equations, or numerical solvers. The process of learning ROMs is posed as a low-cost least-squares problem in a reduced-order subspace identified via Proper Orthogonal Decomposition (POD). Numerical experiments on classical pattern-forming systems–including the Schnakenberg and Mimura–Tsujikawa models–demonstrate that higher-order surrogate models significantly improve prediction accuracy while maintaining low computational cost. The proposed method provides a flexible, non-intrusive model reduction framework, well suited for the analysis of complex spatio-temporal pattern formation phenomena.

Data-driven modeling↗

DOE OSTI2026

Low Activity Waste Glass Optimization with Property Models from Machine Learning, Part 2: Experimental Validation and Active Learning

The United States Department of Energy is responsible for managing legacy nuclear waste stored in underground tanks at the Hanford Site. To treat the waste, it is planned as the current baseline to separately vitrify low-activity waste (LAW) and high-level waste fractions. Previously, machine learning (ML) based glass property models (e.g., chemical durability, viscosity, electrical conductivity and SO3 solubility) were developed with prediction uncertainties. A waste glass optimization approach was then established to enable the capability of using these ML models in LAW glass formulation. In this study, the previous ML models were first experimentally validated, and the results were incorporated back into the database to update the ML models. The updated models and formulations showed increased waste loading while reducing the failure rate, demonstrating improved predictive accuracy, reduced uncertainties, and the effectiveness of active learning in guiding high-dimensional, nonlinear LAW glass design. This represents the first experimental validation of ML based LAW glass formulation, with practical benefits such as higher waste loading, shorter mission duration, and lower operational risk.

Lu, Xiaonan (ORCID:0000000179708148)↗

DOE OSTI2023

Accelerating matrix-centric graph processing on GPUs through bit-level optimizations

Even though it is well known that binary values are common in graph applications (e.g., adjacency matrix), how to leverage the phenomenon for efficiency has not yet been adequately explored. This paper presents a systematic study on how to unlock the potential of the bit-level optimizations of graph computations that involve binary values. It proposes a two-level representation named Bit-Block Compressed Sparse Row (B2SR) and presents a series of optimizations to the graph operations on B2SR by the intrinsics of modern GPUs. It additionally introduces Deep Reinforcement Learning (DRL) as an efficient way to best configure the bit-level optimizations on the fly. Additionally, the DQN-based adaptive tile size selector with dedicated model training can reach 68% prediction accuracy. Evaluations on NVIDIA Pascal and Volta GPUs show that the optimizations bring up to 40× and 6555× for essential GraphBLAS kernels SpMV and SpGEMM, respectively, making GraphBLAS-based BFS accelerate up to 433×, SSSP, PR, and CC up to 35×, and TC up to 52×.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2026

Mechanistic mass transfer in hollow fiber membrane solvent extraction for bio-based isobutanol

Membrane solvent extraction (MSE) has emerged as a promising method for selectively recovering bioproducts from complex aqueous streams. Bio-isobutanol, a next-generation feedstock for biofuel, remains challenging to recover because of its low concentration and the presence of inhibitory substances. This study explores the potential of hollow fiber (HF) MSE for bio-isobutanol recovery and systematically examines the coupled effects of fiber packing, shell-side flow dynamics, and aqueous chemistry on performance. A resistance-in-series model is applied to understand mass transfer in the HF MSE modules, quantify local resistances, and validate overall performance. The results show that increasing the fiber packing provides a larger interfacial area but induces poor flow distribution and channeling, hindering effective isobutanol transport. Meanwhile, increasing the shell-side velocity improves isobutanol recovery due to reductions in the boundary layer thickness. The presence of salts, added to mimic fermentation broth, increases the partition coefficient through salting-out effects, further improving isobutanol flux. A modified correlation for the shell-side mass transfer coefficient (k s,ϕ+v ), integrating geometric and hydrodynamic effects, was developed and validated. The proposed model achieves highly predictive accuracy (r 2 = 0.9808) across a wide range of conditions, outperforming previous models. The findings provide mechanistic insight into the interaction of geometric packing, hydrodynamics, and chemistry in governing mass transfer in HF MSE. Overall, this work demonstrates the potential of HF MSE for efficient bio-isobutanol recovery and also provides practical guidelines on critical factors (packing fraction, partition coefficient, and shell-side velocity), aiding in the design and scaling of MSE systems for resource recovery.

Aqueous chemistry↗

DOE OSTI2025

Fast-RF-Shimming: Accelerate RF shimming in 7T MRI using deep learning

Ultrahigh field (UHF) Magnetic Resonance Imaging (MRI) offers an elevated signal-to-noise ratio (SNR), enabling exceptionally high spatial resolution that benefits both clinical diagnostics and advanced research. However, the jump to higher fields introduces complications, particularly transmit radiofrequency (RF) field ($B^{+}_{1}$) inhomogeneities, manifesting as uneven flip angles and image intensity irregularities. These artifacts can degrade image quality and impede broader clinical adoption. Traditional RF shimming methods, such as Magnitude Least Squares (MLS) optimization, effectively mitigate $B^{+}_{1}$ inhomogeneity, but remain time-consuming. Recent machine learning approaches, including RF Shim Prediction by Iteratively Projected Ridge Regression and other deep learning architectures, suggest alternative pathways. Although these approaches show promise, challenges such as extensive training periods, limited network complexity, and practical data requirements persist. In this paper, we introduce a holistic learning-based framework called Fast-RF-Shimming, which achieves a 5000 × speed-up compared to the traditional MLS method. In the initial phase, we employ random-initialized Adaptive Moment Estimation (Adam) to derive the desired reference shimming weights from multi-channel $B^{+}_{1}$ fields. Next, we train a Residual Network (ResNet) to map $B^{+}_{1}$ fields directly to the ultimate RF shimming outputs, incorporating the confidence parameter into its loss function. Finally, we design Non-uniformity Field Detector (NFD), an optional post-processing step, to ensure the extreme non-uniform outcomes are identified. Comparative evaluations with standard MLS optimization underscore notable gains in both processing speed and predictive accuracy, which indicates that our technique shows a promising solution for addressing persistent inhomogeneity challenges.

Deep learning↗