SEARCH · Search NASA

Results for “deep neural network (DNN)”

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 19 records

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Physics-based hybrid machine learning for critical heat flux prediction with uncertainty quantification

Critical heat flux (CHF) is a key quantity in nuclear system modeling due to its impact on heat transfer, safety margins, and reactor performance. This study develops and validates an uncertainty-aware hybrid modeling approach that combines machine learning with physics-based models to predict CHF in cases of dryout. The Biasi and Bowring empirical correlations were paired with three ML uncertainty quantification (UQ) techniques: deep neural network (DNN) ensembles, Bayesian neural networks (BNNs), and deep Gaussian processes (DGPs). A pure ML model without a base model was evaluated for comparison. Model performance was assessed under plentiful (7,350 points) and limited (9 points) training data scenarios using parity, uncertainty distributions, and calibration curves. Results show that the Biasi hybrid DNN ensemble achieved the best overall performance, with a mean absolute relative error of 1.846%, and well-calibrated uncertainty estimates. The BNN-based hybrids showed slightly higher error (2.14%) but superior uncertainty calibration. DGP models underperformed, with over 6% error and poor uncertainty calibration. All hybrid models outperformed pure machine learning configurations, demonstrating resistance against data scarcity. These findings indicate that hybrid modeling significantly improves predictive accuracy, interpretability, and resilience to data scarcity. The integration of uncertainty awareness provides actionable confidence in CHF predictions, which is vital for safety-critical decisions in nuclear applications. This hybrid approach offers a viable pathway for deploying ML models in reactor analysis tools while preserving domain knowledge and physical consistency.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

DOE OSTI2024

Achieving precise multiparameter measurements with distributed optical fiber sensor using wavelength diversity and deep neural networks

The development of advanced distributed optical fiber sensing systems that are capable of performing accurate and spatially resolved multiparameter measurements is of great interest to a wide range of scientific and industrial applications. Here, in this paper, we propose and experimentally demonstrate a wavelength diversity based advanced distributed optical fiber sensor system to accomplish multiparameter sensing while greatly enhancing measurement accuracy. A suite of deep neural network (DNN) algorithms are developed and verified for data denoising, rapid Brillouin frequency shift estimation, and vibration data event classification. As a proof-of-concept, we demonstrate the effectiveness of the proposed advanced wavelength diversity distributed fiber sensor system assisted by DNN for simultaneous, independent measurements of static strain, temperature, and acoustic vibrations over a 25 km long sensing fiber at 3 m spatial resolution. These results suggest the potential for an intelligent multiparameter monitoring system with enhanced performance in advanced structural health monitoring applications.

47 OTHER INSTRUMENTATION↗

NASA NTRSDate not supplied

Runway Sign Classifier: A DAL C Certifiable Machine Learning System

In recent years, the remarkable progress of Machine Learning (ML) technologies within the domain of Artificial Intelligence (AI) systems has presented unprecedented opportunities for the aviation industry, paving the way for further advancements in automation, including the potential for single pilot or fully autonomous operation of large commercial airplanes. However, ML technology faces major incompatibilities with existing airborne certification standards, such as ML model traceability and explainability issues or the inadequacy of traditional coverage metrics. Certification of ML-based airborne systems using current standards is problematic due to these challenges. This paper presents a case study of an airborne system utilizing a Deep Neural Network (DNN) for airport sign detection and classification. Building upon our previous work, which demonstrates compliance with Design Assurance Level (DAL) ”D”, we upgrade the system to meet the more stringent requirements of Design Assurance Level ”C”. To achieve DAL C, we employ an established architectural mitigation technique involving two redundant and dissimilar Deep Neural Networks. The application of novel ML-specific data management techniques further enhances this approach. This work is intended to illustrate how the certification challenges of ML-based systems can be addressed for medium criticality airborne applications.

Flight Software↗

NASA NTRSDate not supplied

Toward The Development of Hailstorm Climatologies Derived From Reanalyses and Infared/Passive Microwave Satellite Imagers

Geostationary satellite imagers, such as those of the Geostationary Operational Environmental Satellite (GOES) and Meteosat series, provide both historical and near-real-time observations of cloud top patterns that are commonly associated with severe convection. Environmental conditions favorable for severe weather are thought to be represented well by reanalyses. Predicting exactly where convection and costly storm hazards like hail will occur using models or satellite imagery alone, however, is extremely challenging. The multivariate combination of satellite-observed cloud patterns with reanalysis environmental parameters, linked to United States Next Generation Weather Radar- (NEXRAD-) estimated Maximum Expected Size of Hail (MESH) using a deep neural network (DNN), enables estimation of potentially severe hail likelihood for any observed storm cell. These estimates are specifically designed to make hail likelihood distinctions based on satellite-indicated points of deep convection within environments favorable for storm development. We seek an approach that can be used to estimate climatological hailstorm frequency and risk throughout the historical satellite data record. This presentation demonstrates that statistical distributions of convective parameters from satellite and reanalysis show separation between non-severe/severe hailstorm classes for predictors including overshooting cloud top temperature and area characteristics, convective available potential energy, vertical wind shear, 500 hPa temperature, mid-level lapse rate, precipitable water, and convective inhibition. These complex, multivariate predictor relationships are exploited within a DNN to produce a hail likelihood metric with a critical success index of 0.504 and Heidke skill score of 0.403, which is exceptional among recent analogous hail studies. Furthermore, applications of the DNN to select case studies demonstrate good qualitative agreement between hail likelihood and MESH. These hail classifications are aggregated across an 11-year GOES-12/13 image database to derive a hail frequency and severity climatology, which denotes the Central Plains, the Midwest, and northwestern Mexico as being the most hail-prone regions within the domain studied. Opportunities for training and applying DNN-based hailstorm predictions to recently developed GOES-8/10/12/13/16 and Meteosat Second Generation convective storm detection and characterization climatologies over South America and South Africa, respectively, will also be presented.

Kristopher Bedka↗

NASA NTRS2022

Deriving Severe Hail Likelihood from Satellite Observations and Model Reanalysis Parameters using a Deep Neural Network

Geostationary satellite imagers, such as those of the Geostationary Operational Environmental Satellite (GOES) series, have been observing severe convection at 15–60-minute intervals for over 40 years. When properly assessed, such a data record can be valuable in efforts of estimating severe storm risk throughout the diurnal cycle based on automated detection of patterns consistently found atop severe storms. Furthermore, environmental conditions favorable for severe weather are well-known and are thought to be represented well by modern reanalysis products. Promoting resilience against such hazards on local and global scales is a chief goal the NASA Disasters program, which seeks to encourage use of satellite observations to mitigate risk. For instance, hail is the costliest severe weather hazard across the globe in terms of insured loss, but reporting inconsistencies for hail events globally make it difficult to develop models that can quantify the risk. Satellite observation and model reanalysis taken together have the potential to, with reasonable skill and specificity, characterize environmental conditions that are favorable for hazardous weather, and thereby enable creation of hazard climatologie. Such climatologies are particularly useful over regions without extensive radar networks or storm reporting. By mapping the multivariate combination of observed cloud features and reanalysis environmental parameters/indices to United States Next Generation Weather Radar (NEXRAD) radar-estimated Maximum Expected Size of Hail (MESH) by way of a deep neural network (DNN), estimates of likelihood for potentially severe hail can be produced. Such estimates are of greater complexity and efficiency than could be performed with previous multivariate or logistic regression analyses for observed points within convective systems. Statistical distributions of convective parameters from satellite and reanalysis are shown to highlight non-severe/severe class separation for well-known hailstorm predictors, e.g., overshooting cloud top characteristics, deep-layer wind shear, mid-level stability, helicity, and convective inhibition. These complex, multivariate predictor relationships are exploited within a DNN, which can efficiently produce a quantitative hail risk metric with better than 70% detection rate and under 30% false alarms. These hail classifications can then be aggregated across the satellite record to yield a hazard climatology for hail frequency and severity – knowledge of which is of particular interest to those who manage risk (e.g., insurers) and are seeking opportunities to identify hail-prone regions, particularly in developing nations. This NASA study uses satellite observations and model parameters in a DNN to perform climatological hailstorm analysis in support of catastrophe model development, with the hope of promoting risk resilience particularly in regions without adequate weather radar coverage.

Passive Remote Sensing↗

NASA NTRSDate not supplied

Safety Assessment of a Machine Learning-Based Aircraft Emergency Braking System: A Case Study

Machine Learning (ML) is revolutionizing many technological fields, but its use in aviation remains restricted due to stringent certification requirements. Efforts by the aviation community to establish standards for certifying ML-based systems are progressing, yet challenges persist, particularly with safety assessment methods for ML-based systems. This research addresses these challenges through a case study of an autonomous emergency braking system utilizing a computer vision deep neural network (DNN). We demonstrate a safety assessment process tailored to ML-specific concerns, such as low integrity and performance variability in quantitative safety analysis. This study can serve as an illustrative example to facilitate the discussion and convergence on certification aspects for ML-based systems within the aviation community.

Safety certification↗

DOE OSTI2024

Bayesian reduced-order deep learning surrogate model for dynamic systems described by partial differential equations

We propose a reduced-order deep-learning surrogate model for dynamic systems described by time-dependent partial differential equations. This method employs space–time Karhunen–Loève expansions (KLEs) of the state variables and space-dependent KLEs of space-varying parameters to identify the reduced (latent) dimensions. Subsequently, a deep neural network (DNN) is used to map the parameter latent space to the state variable latent space. An approximate Bayesian method is developed for uncertainty quantification (UQ) in the proposed KL-DNN surrogate model. The KL-DNN method is tested for the linear advection–diffusion and nonlinear diffusion equations, and the Bayesian approach for UQ is compared with the deep ensembling (DE) approach, commonly used for quantifying uncertainty in DNN models. It was found that the approximate Bayesian method provides a more informative distribution of the PDE solutions in terms of the coverage of the reference PDE solutions (the percentage of nodes where the reference solution is within the confidence interval predicted by the UQ methods) and log predictive probability. The DE method is found to underestimate uncertainty and introduce bias. For the nonlinear diffusion equation, we compare the KL-DNN method with the Fourier Neural Operator (FNO) method and find that KL-DNN is 10% more accurate and needs less training time than the FNO method.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Explainable multi-fidelity Bayesian neural network for distribution system state estimation

Distribution System State Estimation (DSSE) is frequently constrained by limited real-time measurements, the uncertainties introduced by distributed energy resources, and the presence of bad data. To address them, this paper proposes an enhanced Multi-Fidelity Bayesian Neural Network (MFBNN) DSSE approach. A low-fidelity layer based on a Deep Neural Network (DNN) is first pre-trained on pseudo-measurement data to learn fundamental state features. Subsequently, a high-fidelity Bayesian Neural Network (BNN) layer leverages limited but high-quality real-time measurements to refine these features, thereby achieving accurate DSSE. Additionally, the deep SHapley Additive exPlanation (SHAP) is developed to quantify the influence of measurement data on DSSE through dual perspectives of global feature importance and local nodal contributions, establishing a hierarchical explainability framework for machine learning-based DSSE. Comparative studies conducted on the IEEE 13-bus system and a real-world 2135-node system from Dominion Energy demonstrate that the proposed method excels in estimation accuracy, even under situations of high noise levels, bad data, and missing data. Further comparisons with Weighted Least Squares (WLS) and other machine learning-based DSSE approaches verify that the proposed framework offers higher accuracy, improved interpretability, and enhanced robustness.

Bad data↗

NASA NTRSDate not supplied

A Deep Neural Network for Achieving Spectrally Consistent and Seamless Infrared Radiance Measurements Across Geostationary Satellite Domains

The NASA Clouds and the Earth's Radiant Energy System (CERES) project provides the scientific community with observed top-of-atmosphere (TOA) shortwave and longwave fluxes for climate monitoring and climate model validation. To achieve this goal, CERES relies on TOA broadband fluxes derived from geostationary satellite (GEO) imagery to account for the diurnal flux variations between the CERES observation intervals. Consistent global flux derivation depends on accurate and consistent cloud retrievals. Scene-dependent spectral measurement inconsistency of the instruments that make up the contiguous ring of GEO observations (GEO-Ring), as well as limb darkening effects, can cause discontinuities in derived cloud properties and radiative fluxes at the boundaries of adjacent imager domains. Although the algorithms utilize radiative transfer models to account for instrument-band-dependent atmospheric correction and viewing zenith angle (VZA) dependency, small discontinuities may persist due to uncertainties inherent to the multiple imager-specific algorithms. Furthermore, while hyperspectral-instrument-based spectral band adjustment factors may effectively account for spectrally induced bias, they are less effective at reducing variance owed to the specific composition of the viewed scene, which is challenging to robustly characterize. As such, this article highlights the use of a deep neural network (DNN) to resolve spectral-and VZA-induced biases between GEO-Ring imagers. The DNN uses available infrared (IR) channels from the GEO instruments, along with viewing and solar illumination geometry, to estimate homogenized, VIIRS-like IR radiances for use in the GEO cloud algorithm. This approach is effective at mitigating scene-dependent spectral variance and VZA dependency, resulting in consistent radiance measurements across the GEO-Ring, thereby leading toward a more seamless global cloud assessment.

deep learning↗

DOE OSTI2025

Predicting critical heat flux with uncertainty quantification and domain generalization using conditional variational autoencoders and deep neural networks

Deep generative models (DGMs) can generate synthetic data samples that closely resemble the original dataset, addressing data scarcity. In this work, we developed a conditional variational autoencoder (CVAE) to augment critical heat flux (CHF) data used for the 2006 Groeneveld lookup table. To compare with traditional methods, a fine-tuned deep neural network (DNN) regression model was evaluated on the same dataset. Both models achieved small mean absolute relative errors, with the CVAE showing more favorable results. Uncertainty quantification (UQ) was performed using repeated CVAE sampling and DNN ensembling. The DNN ensemble improved performance over the baseline, while the CVAE maintained consistent results with less variability and higher confidence. Both models achieved small errors inside and outside the training domain, with slightly larger errors outside. Altogether, the CVAE performed better than the DNN in predicting CHF and exhibited better uncertainty behavior.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗

NASA NTRS2021

Dynamic fire and smoke detection and classification for flashover prediction

Flashover is a dangerous phenomenon caused by near-simultaneous ignition of exposed materials. It is one of the major causes of firefighter fatalities. Research has been done using CMOS vision cameras combined with thermal sensors to perform remote detection and dynamic classification of fire and smoke patterns. Tests and experiments have been done to detect fire and smoke remotely. The inexpensive visible and infrared sensors used in the tests corroborate and closely follow the detailed trends recorded by the more expensive (and less mobile) radiometers and thermocouples. Deep neural networks (DNN) have been used to detect, classify and track fire and smoke areas. Real-time segmentation is utilized to measure the fire and smoke boundaries. The segmentations are used to dynamically monitor fluctuations in temperature, fire size and smoke progression in the monitored areas. A fire and smoke progression curve has been drawn to predict the flashover point. In the paper, data analysis and preliminary results will be shown. Keywords: Flashover, fire, smoke, deep learning, visible and infrared vision

Chow, Edward↗

DOE OSTI2024

Newton-Raphson AC Power Flow Convergence Based on Deep Learning Initialization and Homotopy Continuation

Power flow forms the basis of many power system studies. With the increased penetration of renewable energy, grid planners tend to perform multiple power flow simulations under various operating conditions and not just selected snapshots at peak or light load conditions. Getting a converged AC power flow (ACPF) case remains a significant challenge for grid planners especially in large power grid networks. This paper proposes a two-stage approach to improve Newton-Raphson ACPF convergence and was applied to a 6102 bus Electric Reliability Council of Texas (ERCOT) system. The first stage utilizes a deep learning-based initializer with data re-training. Here a deep neural network (DNN) initializer is developed to provide better initial voltage magnitude and angle guesses to aid in power flow convergence. This is because Newton-Raphson ACPF is quite sensitive to the initial conditions and bad initialization could lead to divergence. The DNN initializer includes a data re-training framework that improves the initializer's performance when faced with limited training data. The DNN initializer successfully solved 3,285 cases out of 3,899 non-converging dispatch and performed better than random forest and DC power flow initialization methods. ACPF cases not solved in this first stage are then passed through a hot-starting algorithm based on homotopy continuation with switched shunt control. The hot-starting algorithm successfully converged 416 cases out of the remaining 614 non-converging ACPF dispatch. In conclusion, the combined two-stage approach achieved a 94.9% success rate, by converging a total of 3,701 cases out of the initial 3,899 unsolved cases.

Deep learning↗

DOE OSTI2024

Deep-learning-derived planetary boundary layer height from conventional meteorological measurements

Abstract. The planetary boundary layer (PBL) height (PBLH) is an important parameter for various meteorological and climate studies. This study presents a multi-structure deep neural network (DNN) model, which can estimate PBLH by integrating the morning temperature profiles and surface meteorological observations. The DNN model is developed by leveraging a rich dataset of PBLH derived from long-standing radiosonde records augmented with high-resolution micro-pulse lidar and Doppler lidar observations. We access the performance of the DNN with an ensemble of 10 members, each featuring distinct hidden-layer structures, which collectively yield a robust 27-year PBLH dataset over the southern Great Plains from 1994 to 2020. The influence of various meteorological factors on PBLH is rigorously analyzed through the importance test. Moreover, the DNN model's accuracy is evaluated against radiosonde observations and juxtaposed with conventional remote sensing methodologies, including Doppler lidar, ceilometer, Raman lidar, and micro-pulse lidar. The DNN model exhibits reliable performance across diverse conditions and demonstrates lower biases relative to remote sensing methods. In addition, the DNN model, originally trained over a plain region, demonstrates remarkable adaptability when applied to the heterogeneous terrains and climates encountered during the GoAmazon (Green Ocean Amazon; tropical rainforest) and CACTI (Cloud, Aerosol, and Complex Terrain Interactions; middle-latitude mountain) campaigns. These findings demonstrate the effectiveness of deep learning models in estimating PBLH, enhancing our understanding of boundary layer processes with implications for improving the representation of PBL in weather forecasting and climate modeling.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2025

An adaptive and stability-promoting layerwise training approach for sparse deep neural network architecture

This work presents a two-stage adaptive framework for progressively developing deep neural network (DNN) architectures that generalize well for a given training data set. In the first stage, a layerwise training approach is adopted where a new layer is added each time and trained independently by freezing parameters in the previous layers. We impose desirable structures on the DNN by employing manifold regularization, sparsity regularization, and physics-informed terms. We introduce a ε – δ – stability-promoting concept as a desirable property for a learning algorithm and show that employing manifold regularization yields a ε – δ stability-promoting algorithm. Further, we also derive the necessary conditions for the trainability of a newly added layer and investigate the training saturation problem. In the second stage of the algorithm (post-processing), a sequence of shallow networks is employed to extract information from the residual produced in the first stage, thereby improving the prediction accuracy. Numerical investigations on prototype regression and classification problems demonstrate that the proposed approach can outperform fully connected DNNs of the same size. Moreover, by equipping the physics-informed neural network (PINN) with the proposed adaptive architecture strategy to solve partial differential equations, we numerically show that adaptive PINNs not only are superior to standard PINNs but also produce interpretable hidden layers with provable stability. As a result, we also apply our architecture design strategy to solve inverse problems governed by elliptic partial differential equations.

42 ENGINEERING↗

DOE OSTI2025

Multi-objective surrogate-assisted calibration of CPFEM models using macroscopic response and in situ EBSD measurements of grain reorientation trajectories

Crystal plasticity finite element method (CPFEM) models are widely used to simulate the deformation behaviour of polycrystalline materials, but their calibration is often limited by their high computational cost and the non-convexity of the optimisation landscape. Here, this study develops a multi-objective surrogate-assisted calibration workflow that couples a multi-objective genetic algorithm (MOGA) with an adaptively trained deep neural network (DNN) surrogate model to efficiently identify CPFEM parameters from experimental data. The workflow is demonstrated on three crystal plasticity (CP) formulations of increasing complexity — Voce hardening (VH), two-coefficient latent hardening (LH2), and six-coefficient latent hardening (LH6) — using in situ electron backscatter diffraction (EBSD) measurements of Alloy 617 under uniaxial tensile loading. The CPFEM models are calibrated against the experimentally observed stress–strain response and reorientation trajectories of eight grains, then validated against eight additional trajectories and overall texture evolution. Across the CP formulations, the macroscopic response was reproduced reliably, while differences emerged in the robustness and accuracy of the grain-scale predictions. Including grain reorientation trajectories in the multi-objective calibration improved texture evolution predictions and filtered out physically inconsistent parameter sets that can arise from calibrating against only the stress–strain data. The workflow also demonstrates good transferability of calibrated parameters from a low- to a high-fidelity microstructural model. These results provide practical guidance for integrating in situ microstructural data into CPFEM through efficient, repeatable, and physically meaningful multi-objective calibration.

Crystal plasticity finite element method↗

DOE OSTI2025

A hybrid numerical and machine learning framework for evaluating the performance of a 780 cm 2 aqueous organic redox flow battery

Aqueous organic redox flow battery (AORFB) is a promising cost-competitive technology for large-scale energy storage. Among existing work, the dihydroxyphenazine (DHP)-based AORFB has demonstrated high energy density and low capacity degradation in 10 cm2 cells during lab tests. However, its commercial-scale performance in more complex environments remains unknown, posing a barrier for commercialization. To address this gap, this work presents a comprehensive performance evaluation of a 780 cm 2 DHP-based AORFB by combining physics-based numerical model, machine learning (ML)-based surrogate models, and ML-derived sensitivity quantification. Specifically, we first select 12 key battery parameters that include 10 physicochemical quantities and 2 operation quantities, then select 6 performance metrics that include energy efficiency (EE), discharging capacity, charging energy, and power losses due to concentration, activation, and ohmic over-potentials. With such selection, 12800 combinations of the 12 parameters are subsequently generated using the Latin Hypercube Sampling method. These combinations, together with 38 pre-defined State of Charge, are then integrated to a validated AORFB model developed in COMSOL to compute the performance metrics. With both input parameters and performance metrics, 60 deep neural network (DNN) surrogate models are then trained to approximate the relationship between the 10 physicochemical quantities and 6 performance metrics at each flow rate and current density. Sensitivity scores are then calculated based on the DNN models. Two additional sensitivity analysis tools, i.e., MARS, and SHAP, are also used to cross-validate the sensitivity scores from the DNN. The results demonstrate that 1) the standard potential ranks the first in controlling EE and charging energy, 2) the membrane conductivity is most critical for power loss and EE, and 3) specific area and reaction rate control activation power loss.

25 ENERGY STORAGE↗

DOE OSTI2025

An investigation on machine learning predictive accuracy improvement and uncertainty reduction using VAE-based data augmentation

The confluence of ultrafast computers with large memory, rapid progress in Machine Learning (ML) algorithms, and the availability of large datasets place multiple engineering fields at the threshold of dramatic progress. However, a unique challenge in nuclear engineering is data scarcity because experimentation on nuclear systems is usually more expensive and time-consuming than most other disciplines. One potential way to resolve the data scarcity issue is deep generative learning, which uses certain ML models to learn the underlying distribution of existing data and generate synthetic samples that resemble the real data. In this way, one can significantly expand the dataset to train more accurate predictive ML models. In this study, our objective is to evaluate the effectiveness of data augmentation using variational autoencoder (VAE)-based deep generative models. We investigated whether the data augmentation leads to improved accuracy in the predictions of a deep neural network (DNN) model trained using the augmented data. Additionally, the DNN prediction uncertainties are quantified using Bayesian Neural Networks (BNN) and conformal prediction (CP) to assess the impact on predictive uncertainty reduction. To test the proposed methodology, we used TRACE simulations of steady-state void fraction data based on the NUPEC Boiling Water Reactor Full-size Fine-mesh Bundle Test (BFBT) benchmark. Here, we found that augmenting the training dataset using VAEs has improved the DNN model’s predictive accuracy, improved the prediction confidence intervals, and reduced the prediction uncertainties.

Bayesian neural network↗

DOE OSTI2025

Resistive Switching of Spinel Li 4 Ti 5 O 12 Lithium-Ion Battery Material for Neuromorphic Computing

The rapid rise of AI has exposed significant limitations in conventional Von Neumann computing architecture, particularly in regard to speed and energy efficiency. To address these challenges, researchers are exploring a brain-inspired neuromorphic architecture that mimics biological neural networks, enabling massive parallel processing with reduced power consumption for complex AI computational demands. Recent interest has focused on utilizing battery electrodes and solid electrolyte materials for their resistive switching properties in developing a neuromorphic architecture. These properties are precisely tuned through local- and bulk-level chemical composition modifications via voltage bias stimuli. In this study, we demonstrate fabricating a three-terminal lithium-ion electrochemical transistor based on lithium titanium oxide (Li 4 Ti 5 O 12 ), a popular lithium-ion battery anode material. We deposited and characterized LTO thin films using RF sputtering, demonstrating a 6 orders of magnitude increase in electronic conductivity upon lithiation, with conductivity plateauing after 20% lithiation. Density functional theory calculations revealed transformation from the insulating to conducting state, supported by experimental characterization through X-Ray Photoelectron Spectroscopy (XPS) and Direct Current (DC) polarization analyses. The fabricated transistor consisted of LTO as the channel layer, gold as source/drain terminals, lithium phosphorus oxynitride (LiPON) as the lithium-ion conductor, and copper as the gate terminal. The device exhibited clear hysteresis in transfer characteristics due to lithium insertion/extraction processes. Long-term potentiation (LTP) and long-term depression (LTD) measurements showed an asymmetric ratio of 1.425 and maximum/minimum conductance ratio of 7.83. When implemented in a deep neural network (DNN) for MNIST handwritten digit recognition, the device achieved 92.03% accuracy over 20 training epochs. Detailed transport mechanism analysis revealed the crucial role of oxygen vacancies and interface effects in device operation. Our preliminary findings establish LTO-based lithium-ion electrochemical transistors as promising candidates for energy-efficient neuromorphic computing applications, offering potential solutions to traditional Von Neumann architecture limitations.

25 ENERGY STORAGE↗