Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Residual learning”

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

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

At least 235 records · Page 13
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

A combinatorially complete epistatic fitness landscape in an enzyme active site

Protein engineering often targets binding pockets or active sites which are enriched in epistasis—nonadditive interactions between amino acid substitutions—and where the combined effects of multiple single substitutions are difficult to predict. Few existing sequence-fitness datasets capture epistasis at large scale, especially for enzyme catalysis, limiting the development and assessment of model-guided enzyme engineering approaches. We present here a combinatorially complete, 160,000-variant fitness landscape across four residues in the active site of an enzyme. Assaying the native reaction of a thermostable β-subunit of tryptophan synthase (TrpB) in a nonnative environment yielded a landscape characterized by significant epistasis and many local optima. These effects prevent simulated directed evolution approaches from efficiently reaching the global optimum. There is nonetheless wide variability in the effectiveness of different directed evolution approaches, which together provide experimental benchmarks for computational and machine learning workflows. The most-fit TrpB variants contain a substitution that is nearly absent in natural TrpB sequences—a result that conservation-based predictions would not capture. Thus, although fitness prediction using evolutionary data can enrich in more-active variants, these approaches struggle to identify and differentiate among the most-active variants, even for this near-native function. Overall, this work presents a large-scale testing ground for model-guided enzyme engineering and suggests that efficient navigation of epistatic fitness landscapes can be improved by advances in both machine learning and physical modeling.

biocatalysis↗
DOE OSTI2021

Anomaly detection in Hyper Suprime-Cam galaxy images with generative adversarial networks

ABSTRACT The problem of anomaly detection in astronomical surveys is becoming increasingly important as data sets grow in size. We present the results of an unsupervised anomaly detection method using a Wasserstein generative adversarial network (WGAN) on nearly one million optical galaxy images in the Hyper Suprime-Cam (HSC) survey. The WGAN learns to generate realistic HSC-like galaxies that follow the distribution of the data set; anomalous images are defined based on a poor reconstruction by the generator and outlying features learned by the discriminator. We find that the discriminator is more attuned to potentially interesting anomalies compared to the generator, and compared to a simpler autoencoder-based anomaly detection approach, so we use the discriminator-selected images to construct a high-anomaly sample of ∼13 000 objects. We propose a new approach to further characterize these anomalous images: we use a convolutional autoencoder to reduce the dimensionality of the residual differences between the real and WGAN-reconstructed images and perform UMAP clustering on these. We report detected anomalies of interest including galaxy mergers, tidal features, and extreme star-forming galaxies. A follow-up spectroscopic analysis of one of these anomalies is detailed in the Appendix; we find that it is an unusual system most likely to be a metal-poor dwarf galaxy with an extremely blue, higher-metallicity H ii region. We have released a catalogue with the WGAN anomaly scores; the code and catalogue are available at https://github.com/kstoreyf/anomalies-GAN-HSC; and our interactive visualization tool for exploring the clustered data is at https://weirdgalaxi.es.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2020

Mixed-precision iterative refinement using tensor cores on GPUs to accelerate solution of linear systems

Double-precision floating-point arithmetic (FP64) has been the de facto standard for engineering and scientific simulations for several decades. Problem complexity and the sheer volume of data coming from various instruments and sensors motivate researchers to mix and match various approaches to optimize compute resources, including different levels of floating-point precision. In recent years, machine learning has motivated hardware support for half-precision floating-point arithmetic. A primary challenge in high-performance computing is to leverage reduced-precision and mixed-precision hardware. We show how the FP16/FP32 Tensor Cores on NVIDIA GPUs can be exploited to accelerate the solution of linear systems of equations Ax = b without sacrificing numerical stability. The techniques we employ include multiprecision LU factorization, the preconditioned generalized minimal residual algorithm (GMRES), and scaling and auto-adaptive rounding to avoid overflow. We also show how to efficiently handle systems with multiple right-hand sides. On the NVIDIA Quadro GV100 (Volta) GPU, we achieve a 4×-5× performance increase and 5× better energy efficiency versus the standard FP64 implementation while maintaining an FP64 level of numerical stability.

GMRES↗
DOE OSTI2025

Three-dimensional reconstruction of inertial confinement fusion hot-spot plasma from x-ray and nuclear diagnostics on OMEGA

Multidimensional effects degrade the neutron yield and the compressed areal density of laser-direct-drive inertial confinement fusion implosions of layered deuterium–tritium cryogenic targets on the OMEGA Laser System with respect to 1D radiation-hydrodynamic simulation predictions. A comprehensive physics-informed 3D reconstruction effort is under way to infer hot-spot and shell conditions at stagnation from four x-ray and seven neutron detectors distributed around the OMEGA target chamber. Neutron diagnostics, providing measurements of the neutron yield, hot-spot flow velocity, and apparent ion-temperature distribution, are used to infer the mode-1 perturbation at stagnation. The x-ray imagers record the shape of the hot-spot plasma to diagnose mode-1 and mode-2 perturbations. A deep-learning convolutional neural network trained on an extensive set of 3D radiation-hydrodynamic simulations is used to interpret the x-ray and nuclear measurements to infer the 3D profiles of the hot-spot plasma conditions and the amount of laser energy coupled to the hot-spot plasma. A 3D simulation database shows that larger mode-1 asymmetries are correlated with higher hot-spot flow velocities and reduced laser-energy coupling and neutron yield. Three-dimensional hot-spot reconstructions from x-ray measurements indicate that higher amounts of residual kinetic energy are correlated with higher measured hot-spot flow velocities, consistent with 3D simulations.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

Using soil library hyperspectral reflectance and machine learning to predict soil organic carbon: Assessing potential of airborne and spaceborne optical soil sensing

Soil organic carbon (SOC) is a key variable to determine soil functioning, ecosystem services, and global carbon cycles. Spectroscopy, particularly optical hyperspectral reflectance coupled with machine learning, can provide rapid, efficient, and cost-effective quantification of SOC. However, how to exploit soil hyperspectral reflectance to predict SOC concentration, and the potential performance of airborne and satellite data for predicting surface SOC at large scales remain relatively underknown. Here, this study utilized a continental-scale soil laboratory spectral library (37,540 full-pedon 350–2500 nm reflectance spectra with SOC concentration of 0–780 g·kg –1 across the US) to thoroughly evaluate seven machine learning algorithms including Partial-Least Squares Regression (PLSR), Random Forest (RF), K-Nearest Neighbors (KNN), Ridge, Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) along with four preprocessed spectra, i.e. original, vector normalization, continuum removal, and first-order derivative, to quantify SOC concentration. Furthermore, by using the coupled soil-vegetation-atmosphere radiative transfer model, we simulated twelve airborne and spaceborne hyper/multi-spectral remote sensing data from surface bare soil laboratory spectra to evaluate their potential for estimating SOC concentration of surface bare soils. Results show that LSTM achieved best predictive performance of quantifying SOC concentration for the whole data sets (R 2 = 0.96, RMSE = 30.81 g·kg –1 ), mineral soils (SOC ≤ 120 g·kg –1 , R 2 = 0.71, RMSE = 10.60 g·kg –1 ), and organic soils (SOC > 120 g·kg –1 , R 2 = 0.78, RMSE = 62.31 g·kg –1 ). Spectral data preprocessing, particularly the first-order derivative, improved the performance of PLSR, RF, Ridge, KNN, and ANN, but not LSTM or CNN. We found that the SOC models of mineral and organic soils should be distinguished given their distinct spectral signatures. Finally, we identified that the shortwave infrared is vital for airborne and spaceborne hyperspectral sensors to monitor surface SOC. This study highlights the high accuracy of LSTM with hyperspectral/multispectral data to mitigate a certain level of noise (soil moisture <0.4 m 3 ·m –3 , green leaf area < 0.3 m 2 ·m –2 , plant residue <0.4 m 2 ·m –2 ) for quantifying surface SOC concentration. Forthcoming satellite hyperspectral missions like Surface Biology and Geology (SBG) have a high potential for future global soil carbon monitoring, while high-resolution satellite multispectral fusion data can be an alternative.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Attribution of heterogeneous stress distributions in low-grain polycrystals under conditions leading to damage

In high-purity polycrystalline metallic materials, voids tend to favor grain boundaries as nucleation sites due to the elevated stress states produced by granular interactions and the weakened grain boundary from the relative atomic disorder. To quantify the key factors of this elevated stress state, simple compression of a small multi-grain cylinder of body-centered cubic tantalum was simulated using a single crystal plasticity model that incorporates non-Schmid effects. Four increasingly complex synthetic microstructures were created to tractably incorporate grain boundary interactions, and a statistically significant number of combinations were performed by varying the initial crystallographic orientations of the microstructure. Most of these simulations produce the maximum von Mises stress on a grain boundary and less frequently at the multi-grain junctions. To build a statistical model for the maximum von Mises stress at the grain boundary, physically based features that could contribute to the elevated stress state were selected. Then, a learning algorithm based on information theory was used to identify which of these features contributed the most information to the data set. The identified features include a grain’s propensity to accommodate both elastic and plastic deformations and their directional components. The misalignment of the direction of each grain’s mechanical response was found to be strongly correlated to the magnitude of the stress near the grain boundary. For all of the synthetic microstructures, the statistical models produce a residual distribution that is nearly Gaussian with a variance of, at most, 10% of the prior distribution. The successful performance of the statistical model implies the correct identification of the physical features that cause severe stress localization in polycrystalline materials. The statistical models constructed here can be used to formulate a physically motivated void nucleation model which is sensitive to a microstructure’s propensity to produce elevated stress states. As a result, these statistical models also enable the design of material microstructures, in which the crystallographic orientation is chosen to resist void nucleation.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Review of Analogous Basins

Sedimentary basins comprise extensive porous sandstone and carbonate reservoirs capable of hosting economically significant greenfield and brownfield residual oil zones (ROZs). Several basins in the United States, including the intracratonic Illinois Basin (ILB), have stacked, predominantly siliciclastic ROZs that are potential targets for tertiary recovery of petroleum and for storing large volumes of anthropogenic carbon in the subsurface. The rocks in these basins share facies and depositional settings with many reservoirs that have already been major producers in primary production and, in some cases, as carbon dioxide enhanced oil recovery (CO 2 -EOR)targets. The lessons learned from field data collection and testing of these intervals in a basin like the ILB have broad applications to analogous basins with potential ROZs.

02 PETROLEUM↗
DOE OSTI2025

Enhancing Drinking Water Quality Modeling: Leveraging Physics Informed Neural Networks for Learning with Imperfect Reaction Models and Partial Data

Chemical kinetics models, typically formulated as systems of ordinary or partial differential equations, are valuable tools for simulating drinking water quality. However, these models often face inaccuracies due to discrepancies between the laboratory and the real-world conditions, as well as limitations in experimental analytical methods, hindering the accurate representation of the true underlying chemical mechanisms. In this study, we propose a Physics Informed Neural Network (PINN), using the eXtreme Theory of Functional Connections, to improve the prediction of chemical concentrations over time. The PINN method accounts for imperfect chemical models and incorporates partial data to improve predictions. Focusing on reactions describing water disinfection residual and disinfectant byproduct formation, which are crucial for public health and regulatory compliance, we demonstrate that the PINN model is able to accurately predict the concentrations of chemical species across various pH values. Notably, the model extends its accuracy to predict concentrations of chemical species not originally included in its training data. The developed method can be extended to a variety of chemical systems, offering a wide array of potential applications.

13 HYDRO ENERGY↗
DOE OSTI2020

Extended Physics-Informed Neural Networks (XPINNs): A Generalized Space-Time Domain Decomposition Based Deep Learning Framework for Nonlinear Partial Differential Equations

Here we propose a generalized space-time domain decomposition approach for the physics-informed neural networks (PINNs) to solve nonlinear partial differential equations (PDEs) on arbitrary complex-geometry domains. The proposed framework, named eXtended PINNs ( X P I N N s ), further pushes the boundaries of both PINNs as well as conservative PINNs (cPINNs), which is a recently proposed domain decomposition approach in the PINN framework tailored to conservation laws. Compared to PINN, the XPINN method has large representation and parallelization capacity due to the inherent property of deployment of multiple neural networks in the smaller subdomains. Unlike cPINN, XPINN can be extended to any type of PDEs. Moreover, the domain can be decomposed in any arbitrary way (in space and time), which is not possible in cPINN. Thus, XPINN offers both space and time parallelization, thereby reducing the training cost more effectively. In each subdomain, a separate neural network is employed with optimally selected hyperparameters, e.g., depth/width of the network, number and location of residual points, activation function, optimization method, etc. A deep network can be employed in a subdomain with complex solution, whereas a shallow neural network can be used in a subdomain with relatively simple and smooth solutions. We demonstrate the versatility of XPINN by solving both forward and inverse PDE problems, ranging from one-dimensional to three-dimensional problems, from time-dependent to time-independent problems, and from continuous to discontinuous problems, which clearly shows that the XPINN method is promising in many practical problems. The proposed XPINN method is the generalization of PINN and cPINN methods, both in terms of applicability as well as domain decomposition approach, which efficiently lends itself to parallelized computation. The XPINN code is available on h t t p s : / / g i t h u b . c o m / A m e y a J a g t a p / X P I N N s .

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Deep inference of simulated strong lenses in ground-based surveys

The large number of strong lenses discoverable in future astronomical surveys will likely enhance the value of strong gravitational lensing as a cosmic probe of dark energy and dark matter. However, leveraging the increased statistical power of such large samples will require further development of automated lens modeling techniques. We show that deep learning and simulation-based inference (SBI) methods produce informative and reliable estimates of parameter posteriors for strong lensing systems in ground-based surveys. We present the examination and comparison of two approaches to lens parameter estimation for strong galaxy-galaxy lenses — Neural Posterior Estimation (NPE) and Bayesian Neural Networks (BNNs). We perform inference on 1-, 5-, and 12-parameter lens models for ground-based imaging data that mimics the Dark Energy Survey (DES). We find that NPE outperforms BNNs, producing posterior distributions that are more accurate, precise, and well-calibrated for most parameters. For the 12-parameter NPE model, the calibration is consistently within <10% of optimal calibration for all parameters, while the BNN is rarely within 20% of optimal calibration for any of the parameters. Similarly, residuals for most of the parameters are smaller (by up to an order of magnitude) with the NPE model than the BNN model. This work takes important steps in the systematic comparison of methods for different levels of model complexity.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2025

Novel artificial neural network model for instantaneous power losses and operational efficiency mapping of MW-scale vanadium redox flow battery for improved technoeconomic analysis

A novel data-driven, machine-learning-based method for modeling the instantaneous power losses of a distribution-sited 2 MW/8MWh vanadium redox flow battery (VRFB), a grid-scale electrochemical storage technology, is introduced and compared against benchmark empirical modeling approaches, including symmetric and asymmetric models, as well as a recent convex hull modeling approach. The novel loss modeling method introduces several advantages over the benchmark models and over simplistic efficiency estimates, the most significant of which is that the model can accurately reflect the stepwise and non-linear parasitic losses associated with the duty cycles of mechanical auxiliary systems like pump motor drives and blower fans. Residuals of the models are compared; the proposed data driven model features significantly improved accuracy over the benchmark models. The model's coefficient of determination is also improved relative to that of the benchmark models. Furthermore, a novel method for visualization of operational efficiency of the grid-scale storage technology is introduced. To demonstrate the benefits of the novel data-driven method for modeling the VRFB, the benchmark models and the proposed models are embedded into an Open DSS distribution network model to study two applications of the grid-scale electrical storage system: load leveling for grid support and energy arbitrage. This article demonstrates that the accuracy of the instantaneous power loss model significantly impacts the understanding of the state of charge of the VRFB. In turn, the accuracy of the efficiency modeling of the VRFB impacts the understanding of the potential economic value and technical benefits to the distribution network operators. In conclusion, the presented power loss modeling approach is, therefore, highly relevant for utility-stakeholders, battery asset owners, system engineers, system designers, and financial planners interested in evaluating or optimizing the operation of grid-scale VRFBs.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2026

Monitoring of Liquid Metal Reactor Heater Zones with Recurrent Neural Network Learning of Temperature Time Series

Advanced high-temperature fluid reactors (ARs), such as sodium fast reactors (SFRs) and molten salt cooled reactors (MSCRs) utilize high-temperature fluids at ambient pressure. To melt the fluid during reactor startup and prevent fluid freezing during cooldown, the thermal–hydraulic systems of such ARs include heater zones consisting of specific heaters with controllers, temperature sensors, and thermal insulation. The failure of heater zones due to insulation material degradation or improper installation, resulting in parasitic heat losses, can lead to fluid freezing. The detection of faults using a heat-transfer model is difficult because of a lack of knowledge of the experimental details. Data-driven machine learning of heater zone temperature time series offers a viable alternative. In this study, we benchmarked the performance of recurrent neural networks (RNNs) in an analysis of heat-up transient temperature time series of heater zones installed on a liquid sodium vessel. The RNN models include long short-term memory (LSTM) and gated recurrent unit (GRU) networks, as well as their bi-directional variants, BiLSTM and BiGRU. Anomalous temperature points were designated using a percentile-based threshold applied to residual fluctuations in the detrended temperature time series. Additionally, the impact of the exponentially weighted moving average (EWMA) method on detection accuracy was examined. The RNN models’ performance was assessed using precision, recall, and F 1 score metrics. Results demonstrated that RNN models effectively detect anomalies in temperature time series with the best models for each heater zone achieving F 1 scores of over 93%. To explain the variations in RNN model performance across different heater zones, we used Kullback–Leibler (KL) divergence to quantify the relative entropy between training and testing data, and the Detrended Fluctuation Analysis (DFA) to assess long-range temporal correlations. For datasets with strong long-range correlations and minimal relative entropy between training and testing data, GRU is the best-performing model. When the data exhibits weaker long-term correlations and a significant relative entropy between training and testing distributions, BiGRU shows the best performance. For the data sets with intermediate values of both KL divergence and DFA, the best performance is obtained with LSTM and BiLSTM, respectively.

gated recurrent unit↗
DOE OSTI2024

Barium stars as tracers of s -process nucleosynthesis in AGB stars

Barium (Ba) stars help to verify asymptotic giant branch (AGB) star nucleosynthesis models since they experienced pollution from an AGB binary companion and thus their spectra carry the signatures of the slow neutron capture process (s process). For a large number (180) of Ba stars, we searched for AGB stellar models that match the observed abundance patterns. We aim to uncover any systematic deviations of the sample abundances from the predictions of the nucleosynthesis models. We employed three machine learning algorithms as classifiers: a Random Forest method, developed for this work, and the two classifiers used in our previous study. Compared to that work, we also expanded our observational sample with 11 Ba stars available in the supersolar metallicity range. We studied the statistical behaviour of the different s-process elements in the observational sample to investigate if the AGB models systematically under- or overpredict the abundances observed in the Ba stars and show the results in the form of violin plots of the residuals between spectroscopic abundances and model predictions. We inspected the correlations between the observed [Fe/H], the s-process elemental abundances, and the residuals. We employed the [Zr/Fe] and [Nb/Fe] abundances as a thermometer to constrain the operational temperature that rules the production of these elements in the sample stars, assuming a steady-state s process. We also investigated the mass distribution of the identified polluter AGB stars and the behaviour of the δ parameter, which describes the fraction of accreted AGB material relative to the Ba star envelope. We find a significant trend in the residuals that implies an underproduction of the elements just after the first s-process peak (Nb, Mo, and Ru) in the models relative to the observations. This may originate from a neutron-capture process (e.g. the intermediate neutron-capture process, i process) not yet included in the AGB models of metallicity from solar to roughly 1/5 solar, corresponding to the range of the Ba stars. Correlations are found between the residuals of these peculiar elements, suggesting a common origin for the deviations from the models. In addition, there is a weak metallicity dependence of the residuals of these elements. The s-process temperatures derived with the [Zr/Fe] – [Nb/Fe] thermometer have an unrealistic value for the majority of our stars. The most likely explanation is that at least a fraction of these elements are not produced in a steady-state s process, and instead may be due to processes not included in the AGB models. The mass distribution of the identified models confirms that our sample of Ba stars was polluted by low-mass AGB stars (< 4 M ⊙ ). Most of the matching AGB models require low accreted mass, but a few systems with high accreted mass are needed to explain the observations.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2020

Applying Improved Optical Recognition with Machine Learning on Sorting Cu Impurities in Steel Scrap

Annually, 20–55 million tons of electronic waste (e-waste) is produced worldwide (5% of all municipal solid waste). Although e-waste embodies only 2% of America’s municipal waste, it accounts for a significantly larger proportion of the heavy metals and flame retardants present in the waste stream. Currently, less than 20% of all e-waste is recycled in the United States because the heterogeneity of the feedstock limits the opportunity for reuse in high value products and processing of the waste itself is often too costly to justify handling. To address this concern, the aims of this study are: 1) to identify the major plastic and metal compositions within electronic shredder residue (ESR), 2) to formulate solvents and processing conditions to separate 90% of the plastics targeted from consumer shred ESR, and 3) to develop a process design model to estimate the cost and energy efficiency of the proposed solvent-based processing. In this study, a pre-sorted heterogeneous ESR feedstock (one where aluminum, magnetic components, and hazardous battery materials removed by an e-waste recycling facility) was used, with the major compositions of the ESR characterized. It was found that 25 wt.% of the feedstock was composed of plastics, 6 wt.% rubber, 27 wt.% printed circuit boards, 23% wire, and the remainder metals and capacitors. Within the plastic portion, polystyrene (PS, 40 wt.%), acrylonitrile butadiene styrene (ABS, 25 wt.%), and styrene-acrylonitrile (SAN, 9wt.%) were identified to compose the majority of the screened plastics using Fourier transform infrared spectroscopy (FTIR). Next, selective solvents were screened using Hansen Solubility Parameter Theory (HSP) for dissolving PS and ABS. The pre-screening results show that methylene chloride (dichloromethane, DCM) and tetrahydrofuran (THF) are capable of dissolving the most PS and ABS, while methanol (MeOH) and ethylene glycol (EG) are capable of precipitating the most PS and ABS. These solvents were subsequently used to recover polymers and remove. flame retardants within the ESR feedstock. By optimizing the dissolution time and the solvents used, the highest polymer dissolution yield (99 wt.%%) was achieved using DCM for 48 hr. Both pre-screened anti-solvents (MeOH and EG) showed the highest polymer precipitation yield (71 wt.%). In terms of flame retardant removal rate, EG was found to have a high phosphorus-containing flame retardant removal rate (up to 98%). Characterization shows that the proposed solvent-based processing can preserve a high molecular weight fraction of the polymers and effectively remove flame retardants. Cost analysis indicates that the amount of the solvent/anti-solvent recovered after the reaction would play a critical role in reducing the operating costs. The energy analysis shows that the proposed solvent-based processes can save up to 60% of the embodied energy used to manufacture plastics used in electronics (PS and ABS were used for calculations). The results from this project prove the potential of solvent-based processing to produce secondary materials (plastics and metals) from e-waste for cross-industry reuse.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Heterosynaptic plasticity in biomembrane memristors controlled by pH

Abstract In biology, heterosynaptic plasticity maintains homeostasis in synaptic inputs during associative learning and memory, and initiates long-term changes in synaptic strengths that nonspecifically modulate different synapse types. In bioinspired neuromorphic circuits, heterosynaptic plasticity may be used to extend the functionality of two-terminal, biomimetic memristors. In this article, we explore how changes in the pH of droplet interface bilayer aqueous solutions modulate the memristive responses of a lipid bilayer membrane in the pH range 4.97–7.40. Surprisingly, we did not find conclusive evidence for pH-dependent shifts in the voltage thresholds ( V* ) needed for alamethicin ion channel formation in the membrane. However, we did observe a clear modulation in the dynamics of pore formation with pH in time-dependent, pulsed voltage experiments. Moreover, at the same voltage, lowering the pH resulted in higher steady-state currents because of increased numbers of conductive peptide ion channels in the membrane. This was due to increased partitioning of alamethicin monomers into the membrane at pH 4.97, which is below the pKa (~5.3–5.7) of carboxylate groups on the glutamate residues of the peptide, making the monomers more hydrophobic. Neutralization of the negative charges on these residues, under acidic conditions, increased the concentration of peptide monomers in the membrane, shifting the equilibrium concentrations of peptide aggregate assemblies in the membrane to favor greater numbers of larger, increasingly more conductive pores. It also increased the relaxation time constants for pore formation and decay, and enhanced short-term facilitation and depression of the switching characteristics of the device. Modulating these thresholds globally and independently of alamethicin concentration and applied voltage will enable the assembly of neuromorphic computational circuitry with enhanced functionality. Impact statement We describe how to use pH as a modulatory “interneuron” that changes the voltage-dependent memristance of alamethicin ion channels in lipid bilayers by changing the structure and dynamical properties of the bilayer. Having the ability to independently control the threshold levels for pore conduction from voltage or ion channel concentration enables additional levels of programmability in a neuromorphic system. In this article, we note that barriers to conduction from membrane-bound ion channels can be lowered by reducing solution pH, resulting in higher currents, and enhanced short-term learning behavior in the form of paired-pulse facilitation. Tuning threshold values with environmental variables, such as pH, provide additional training and learning algorithms that can be used to elicit complex functionality within spiking neural networks. Graphical abstract

36 MATERIALS SCIENCE↗
DOE OSTI2024

Multi-resolution partial differential equations preserved learning framework for spatiotemporal dynamics

Traditional data-driven deep learning models often struggle with high training costs, error accumulation, and poor generalizability in complex physical processes. Physics-informed deep learning (PiDL) addresses these challenges by incorporating physical principles into the model. Most PiDL approaches regularize training by embedding governing equations into the loss function, yet this depends heavily on extensive hyperparameter tuning to weigh each loss term. To this end, we propose to leverage physics prior knowledge by “baking” the discretized governing equations into the neural network architecture via the connection between the partial differential equations (PDE) operators and network structures, resulting in a PDE-preserved neural network (PPNN). This method, embedding discretized PDEs through convolutional residual networks in a multi-resolution setting, largely improves the generalizability and long-term prediction accuracy, outperforming conventional black-box models. The effectiveness and merit of the proposed methods have been demonstrated across various spatiotemporal dynamical systems governed by spatiotemporal PDEs, including reaction-diffusion, Burgers’, and Navier-Stokes equations.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Heat transport in liquid water from first-principles and deep neural network simulations

In this work, we compute the thermal conductivity of water within linear response theory from equilibrium molecular dynamics simulations, by adopting two different approaches. In one, the potential energy surface (PES) is derived on the fly from the electronic ground state of density functional theory (DFT) and the corresponding analytical expression is used for the energy flux. In the other, the PES is represented by a deep neural network (DNN) trained on DFT data, whereby the PES has an explicit local decomposition and the energy flux takes a particularly simple expression. By virtue of a gauge invariance principle, established by Marcolongo, Umari, and Baroni, the two approaches should be equivalent if the PES were reproduced accurately by the DNN model. We test this hypothesis by calculating the thermal conductivity, at the GGA (PBE) level of theory, using the direct formulation and its DNN proxy, finding that both approaches yield the same conductivity, in excess of the experimental value by approximately 60%. Besides being numerically much more efficient than its direct DFT counterpart, the DNN scheme has the advantage of being easily applicable to more sophisticated DFT approximations, such as meta-GGA and hybrid functionals, for which it would be hard to derive analytically the expression of the energy flux. We find in this way that a DNN model, trained on meta-GGA (SCAN) data, reduces the deviation from experiment of the predicted thermal conductivity by about 50%, leaving the question open as to whether the residual error is due to deficiencies of the functional, to a neglect of nuclear quantum effects in the atomic dynamics, or, likely, to a combination of the two.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗