Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “active machine 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 1,009 records · Page 56
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Computational insights into hydrogen adsorption energies on medium-entropy oxides

High entropy oxides (HEOs) have emerged as promising catalysts for several important chemical transformations including alkane activation. Hydrogen adsorption energy (HAE) has been used as a key descriptor for many reactions including methane C–H activation and hydrogen evolution reactions. Hence, understanding the relationship between HAEs and the surface chemistry of HEO surfaces could lay the foundation for meaningful correlations among methane C–H activation, HAE, and the complex, local environment of HEO surfaces. Here, we used a medium-entropy oxide as a prototypical system – Mg 0.25 Ni 0.25 Cu 0.25 Zn 0.25 O with a rock-salt structure – to interrogate these relationships. We sampled 2000 different surfaces of its (100) plane and calculated the HAEs at randomly chosen surface O sites using density functional theory (DFT). Our analysis of the 2000 data points reveals that the HAEs at the surface O sites are significantly influenced by the local environment around the adsorption sites, particularly the nature of the metal atom directly below the surface O site where H adsorbs. After comparing several popular graph-neural-network-based machine learning models, we found that the DimeNet++ model performed best achieving satisfactory accuracy in predicting HAEs for both Mg 0.25 Ni 0.25 Cu 0.25 Zn 0.25 O and slightly varied compositions. Our work underscores the promise of such models and the need for further refinement to address the complexity of HEOs.

Song, Haohong [Vanderbilt Univ., Nashville, TN (Un↗
DOE OSTI2025

Scalable Bayesian Physics-Informed Kolmogorov-Arnold Networks

Uncertainty quantification (UQ) plays a pivotal role in scientific machine learning, especially when surrogate models are used to approximate complex systems. Although multilayer perceptions (MLPs) are commonly employed as surrogates, they often suffer from overfitting due to their large number of parameters. Kolmogorov-Arnold networks (KANs) offer an alternative solution with fewer parameters. However, gradient-based inference methods, such as Hamiltonian Monte Carlo (HMC), may result in computational inefficiency when applied to KANs, especially for large-scale datasets, due to the high cost of back-propagation. To address these challenges, we propose a novel approach, combining the dropout Tikhonov ensemble Kalman inversion (DTEKI) with Chebyshev KANs. This gradient-free method effectively mitigates overfitting and enhances numerical stability. In addition, we incorporate the active subspace method to reduce the parameter-space dimensionality, allowing us to improve the accuracy of predictions and obtain more reliable uncertainty estimates. Extensive experiments demonstrate the efficacy of our approach in various test cases, including scenarios with large datasets and high noise levels. Our results show that the new method achieves comparable or better accuracy, much higher efficiency as well as stability compared to HMC, in addition to scalability. Moreover, by leveraging the low-dimensional parameter subspace, our method preserves prediction accuracy while substantially reducing further the computational cost.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Indoor Occupant Counting by RF Backscattering

Building HVAC (heating, ventilation and air conditioning) consumes approximately 13% of all energy consumption in USA. Motion detectors, cameras and user programmable thermostats have been shown to be ineffective for HVAC controls to save energy, mostly due to the user concerns of comfort, reliability and privacy. A new HVAC control system based on real-time occupant counting that is fully automated, highly accurate, economically sensible and preserving privacy and aesthetics can thus bring forth a disruptive impact to this large energy sector. Our indoor occupant monitoring technology is based on the radio-frequency identification system (RFID), deployed in the room, not on the occupants. One reader with four antennas can be deployed on the ceiling or behind the ceiling panels for every thousand square feet in home, office and assisted living, with or without room partitions. The sticker-like passive tag, 10 cents each and maintenance-free, are profusely hidden on the wall or inside the furniture at arbitrary position, preserving privacy and aesthetics. The large number of tags can realize diverse observation points to accommodate arbitrary room layouts, which is impractical by other active units of camera, infrared, radar or lidar. With 20 tags, the system can reliably detect the number of occupants. For 100 tags, occupant posture and location can be known. The technology has been verified in the research labs and test buildings with very high accuracy. When the real-time occupant number can be accurately known without assuming devices on occupants or occupant motion, the building HVAC system can be automated to achieve building energy saving without sacrificing occupant comfort. According to our limited testing in a few types of building models and the simplified cost calculation, the RFID system has low overall cost in production, deployment, operation and maintenance. The signal processing algorithm based on machine learning requires very small number of training cases as most learning is transferrable for various layouts, and very low computational needs during operation, according to our testing in four different room sizes and layouts. In our preliminary estimate from HVAC saving alone, the RFID system can potentially pay for itself within 1.5 years, in addition to the other enhancement in building automation systems (BAS). Our commercialization strategy and business pitch deck focus on venturing this Cornell occupant monitoring technology into BAS and energy management markets. We have identified three broad BAS market segments of senior living, residential buildings, and office buildings. We have put together the minimum viable product characteristics for these identified segments, including analyses on total cost and competing technologies, as well as the fit and technical gaps for these market segments. We intend to bring the technology to market by licensing or partnering with existing BAS vendors. A list of potential collaborators and licensing partner candidates was assembled for different aspects of integrating our technology into a potential product that can be used with BAS.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
NASA NTRS2018

Overview of Artificial Intelligence (AI) at NASA Goddard

Artificial Intelligence (AI) is a collection of advanced technologies that allows machines to think and act, both humanly and rationally, through sensing, comprehending, acting and learning. AI's foundations lie at the intersection of several traditional fields Philosophy, Mathematics, Economics, Neuroscience, Psychology and Computer Science. Although the inception of AI started in the 1950's, it has recently made a strong comeback in all aspects of society and all over the world; this is mainly due to the timely combination of increased data volumes, advanced and mature algorithms, and improvements in computing power and storage. Current AI applications include big data analytics, robotics, intelligent sensing, assisted decision making, and speech recognition just to name a few. During the Tour, we will show a few examples of the current AI activities at NASA Goddard.

Le Moigne, Jacqueline↗
NASA NTRS2021

Planetary Boundary Layer Height Estimates From ICESat-2 and CATS Backscatter Measurements

The lowest layer of the atmosphere in which all human activity occurs is called the Planetary Boundary Layer (PBL). All physical interactions with the surface, such as heat and moisture transport, pollution dispersion and transport happen in this relatively shallow layer. The ability to understand and model the complex interactions that occur in the PBL is very important to air quality, weather prediction and climate modeling. A fundamental and physically important property of the PBL is its thickness or height. This work presents two methods to obtain global PBL height using satellite lidar data from the Ice, Cloud and land Elevation Satellite-2 (ICESat-2) and the Cloud-Aerosol Transport System (CATS). The first method is a straightforward backscatter threshold technique and the second is a machine learning approach known as a Convolutional Neural Network. The PBL height retrievals from the two methods are compared with each other and with PBL height from the NASA GEOS MERRA-2 reanalysis. The lidar-retrieved PBL heights have a high degree of spatial correlation with the model heights but are generally higher over ocean (∼400 m) and over northern hemisphere high latitude regions (∼1,000 m). Over mid-latitude and tropical land areas, the satellite estimated PBL heights agree well with model mid-day estimates. This work demonstrates the feasibility of using satellite lidar backscatter measurements to obtain global PBL height estimates, as well as determining seasonal and regional variability of PBL height.

Stephen P Palm↗
DOE OSTI2021

Advances and perspectives in discovery and functional analysis of small secreted proteins in plants

Small secreted proteins (SSPs) are less than 250 amino acids in length and are actively transported out of cells through conventional protein secretion pathways or unconventional protein secretion pathways. In plants, SSPs have been found to play important roles in various processes, including plant growth and development, plant response to abiotic and biotic stresses, and beneficial plant–microbe interactions. Over the past 10 years, substantial progress has been made in the identification and functional characterization of SSPs in several plant species relevant to agriculture, bioenergy, and horticulture. Yet, there are potentially a lot of SSPs that have not been discovered in plant genomes, which is largely due to limitations of existing computational algorithms. Recent advances in genomics, transcriptomics, and proteomics research, as well as the development of new computational algorithms based on machine learning, provide unprecedented capabilities for genome-wide discovery of novel SSPs in plants. In this review, we summarize known SSPs and their functions in various plant species. Then we provide an update on the computational and experimental approaches that can be used to discover new SSPs. Finally, we discuss strategies for elucidating the biological functions of SSPs in plants.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Fundamentals of hydrogen storage in nanoporous materials

Abstract Physisorption of hydrogen in nanoporous materials offers an efficient and competitive alternative for hydrogen storage. At low temperatures (e.g. 77 K) and moderate pressures (below 100 bar) molecular H 2 adsorbs reversibly, with very fast kinetics, at high density on the inner surfaces of materials such as zeolites, activated carbons and metal–organic frameworks (MOFs). This review, by experts of Task 40 ‘Energy Storage and Conversion based on Hydrogen’ of the Hydrogen Technology Collaboration Programme of the International Energy Agency, covers the fundamentals of H 2 adsorption in nanoporous materials and assessment of their storage performance. The discussion includes recent work on H 2 adsorption at both low temperature and high pressure, new findings on the assessment of the hydrogen storage performance of materials, the correlation of volumetric and gravimetric H 2 storage capacities, usable capacity, and optimum operating temperature. The application of neutron scattering as an ideal tool for characterising H 2 adsorption is summarised and state-of-the-art computational methods, such as machine learning, are considered for the discovery of new MOFs for H 2 storage applications, as well as the modelling of flexible porous networks for optimised H 2 delivery. The discussion focuses moreover on additional important issues, such as sustainable materials synthesis and improved reproducibility of experimental H 2 adsorption isotherm data by interlaboratory exercises and reference materials.

08 HYDROGEN↗
DOE OSTI2024

Exploration of signal processing methods for superconducting magnet and quench data

Quenching is the phenomenon of a superconducting magnetic material carrying current transitioning into a regular conducting material. This may cause severe and irreparable damage to the superconductor due to Joule heating. The Magnet Department at Fermi National Accelerator Laboratory (FNAL) has acquired experimental data through quench antenna arrays that are recorded when the quench is detected. These data are in terms of voltage signals that are sampled at 100kHz for several minutes. There are multiple channels and each channel provides a data set of more than 20 million observations, while there is one channel, called the trigger channel which shows the time when quench is detected. Despite some advancements that were made including machine learning, data complexity still shadows the progress. In this work, we studied a multi-resolution analysis of the quench antenna data through the Haar wavelet transform. In particular, we applied the maximally overlapped discrete w avelet transform (MODWT) of a suitable level L to the given data and then projected it onto the wavelet basis. This decomposes a given signal (Original data) $x ϵ \mathbb{R}^N$ into $L + 1$ subspaces of $\mathbb{R}^N$. One of the subspaces called the approximation, captures the trend of the signal, and the others, called the details, capture the fluctuations at different frequency bands. This decomposition provides a clear trend of the data at a suitable level and also various activities (spikes) are seen in the details of the decomposition at every level. These spikes might reveal some information about the quench under investigation but in any case, give information about magnet behavior. Also, this decomposition is seen to be very useful in removing noise present in the data due to the source or mechanism of the experiment.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

A reactive molecular dynamics model for uranium/hydrogen containing systems

Uranium-based materials are valuable assets in the energy, medical, and military industries. However, understanding their sensitivity to hydrogen embrittlement is particularly challenging due to the toxicity of uranium and the computationally expensive nature of quantum-based methods generally required to study such processes. In this regard, we have developed a Chebyshev Interaction Model for Efficient Simulation (ChIMES) that can be employed to compute energies and forces of U and UH3 bulk structures with vacancies and hydrogen interstitials with accuracy similar to that of Density Functional Theory (DFT) while yielding linear scaling and orders of magnitude improvement in computational efficiency. Here, we show that the bulk structural parameters, uranium and hydrogen vacancy formation energies, and diffusion barriers predicted by the ChIMES potential are in strong agreement with the reference DFT data. We then use ChIMES to conduct molecular dynamics simulations of the temperature-dependent diffusion of a hydrogen interstitial and determine the corresponding diffusion activation energy. Our model has particular significance in studies of actinides and other high-Z materials, where there is a strong need for computationally efficient methods to bridge length and time scales between experiments and quantum theory.

36 MATERIALS SCIENCE↗
DOE OSTI2020

Correlation-based network analysis combined with machine learning techniques highlight the role of the GABA shunt in Brachypodium sylvaticum freezing tolerance

Perennial grasses will account for approximately 16 billion gallons of renewable fuels by the year 2022, contributing significantly to carbon and nitrogen sequestration. However, perennial grasses productivity can be limited by severe freezing conditions in some geographical areas, although these risks could decrease with the advance of climate warming, the possibility of unpredictable early cold events cannot be discarded. We conducted a study on the model perennial grass Brachypodium sylvaticum to investigate the molecular mechanisms that contribute to cold and freezing adaption. The study was performed on two different B. sylvaticum accessions, Ain1 and Osl1, typical to warm and cold climates, respectively. Both accessions were grown under controlled conditions with subsequent cold acclimation followed by freezing stress. For each treatment a set of morphological parameters, transcription, metabolite, and lipid profiles were measured. State-of-the-art algorithms were employed to analyze cross-component relationships. Phenotypic analysis revealed higher adaption of Osl1 to freezing stress. Our analysis highlighted the differential regulation of the TCA cycle and the GABA shunt between Ain1 and Osl1. Osl1 adapted to freezing stress by repressing the GABA shunt activity, avoiding the detrimental reduction in fatty acid biosynthesis and the concomitant detrimental effects on membrane integrity.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Automated identification of deformation twin systems in Mg WE43 from SEM DIC

In this study, the application of machine learning and computer vision approaches to microscale deformation data for the automated identification of deformation twinning systems, and their associated twin area, is introduced. Deformation data was obtained during in-situ SEM compression testing of a WE43 Mg alloy using digital image correlation (DIC) modified for use with electron microscopy. A 5.7 mm × 3.4 mm area of interest was analyzed, generating ~100 million data points of deformation. Experimental twin trace directions were determined by applying k-means clustering, morphological thinning, and Hough transforms to the deformation data. The identification of deformation twinning was achieved by consideration of the twin trace direction, its strain value, and its evolution. The deformation map was divided into areas corresponding to individual active twin systems, enabling the analysis of microstructure dependence of deformation behavior and twinning activity. The performance of the proposed twinning identification approach was evaluated by accuracy, precision, and sensitivity metrics. The effect of the tuning parameters used in the algorithm on the performance is also discussed.

36 MATERIALS SCIENCE↗
NASA NTRS2020

NeMO-Net – The Neural Multi-Modal Observation & Training Network for Global Coral Reef Assessment

We present NeMO-Net, the Srst open-source deep convolutional neural network (CNN) and interactive learning and training software aimed at assessing the present and past dynamics of coral reef ecosystems through habitat mapping into 10 biological and physical classes. Shallow marine systems, particularly coral reefs, are under significant pressures due to climate change, ocean acidification, and other anthropogenic pressures, leading to rapid, often devastating changes, in these fragile and diverse ecosystems. Historically, remote sensing of shallow marine habitats has been limited to meter-scale imagery due to the optical effects of ocean wave distortion, refraction, and optical attenuation. NeMO-Net combines 3D cm-scale distortion-free imagery captured using NASA FluidCam and Fluid lensing remote sensing technology with low resolution airborne and spaceborne datasets of varying spatial resolutions, spectral spaces, calibrations, and temporal cadence in a supercomputer-based machine learning framework. NeMO-Net augments and improves the benthic habitat classification accuracy of low-resolution datasets across large geographic ad temporal scales using high-resolution training data from FluidCam.NeMO-Net uses fully convolutional networks based upon ResNet and ReSneNet to perform semantic segmentation of remote sensing imagery of shallow marine systems captured by drones, aircraft, and satellites, including WorldView and Sentinel. Deep Laplacian Pyramid Super-Resolution Networks (LapSRN) alongside Domain Adversarial Neural Networks (DANNs) are used to reconstruct high resolution information from low resolution imagery, and to recognize domain-invariant features across datasets from multiple platforms to achieve high classification accuracies, overcoming inter-sensor spatial, spectral and temporal variations.Finally, we share our online active learning and citizen science platform, which allows users to provide interactive training data for NeMO-Net in 2D and 3D, integrated within a deep learning framework. We present results from the PaciSc Islands including Fiji, Guam and Peros Banhos 1 1 2 1 3 1 where 24-class classification accuracy exceeds 91%.

Chirayath, Ved↗
DOE OSTI2023

Star formation rate and stellar mass calibrations based on infrared photometry and their dependence on stellar population age and extinction

The stellar mass (M $\star$ ) and the star formation rate (SFR) are among the most important features that characterize galaxies. Measuring these fundamental properties accurately is critical for understanding the present state of galaxies, their history, and future evolution. Infrared (IR) photometry is widely used to measure the M $\star$ and SFR of galaxies because the near-IR traces the continuum emission of the majority of their stellar populations (SPs), and the mid/far-IR traces the dust emission powered by star-forming activity. This work explores the dependence of the IR emission of galaxies on their extinction, and the age of their SPs. It aims to provide accurate and precise IR-photometry SFR and M $\star$ calibrations that account for SP age and extinction while providing quantification of their scatter. We used the CIGALE spectral energy distribution (SED) fitting code to create model SEDs of galaxies with a wide range of star formation histories, dust content, and interstellar medium properties. We fit the relations between M $\star$ and SFR with IR and optical photometry of the model-galaxy SEDs with the Markov chain Monte Carlo (MCMC) method. As an independent confirmation of the MCMC fitting method, we performed a machine-learning random forest (RF) analysis on the same data set. The RF model yields similar results to the MCMC fits, thus validating the latter. This work provides calibrations for the SFR using a combination of the WISE bands 1 and 3, or the JWST NIR-F200W and MIRI-F2100W. It also provides mass-to-light ratio calibrations based on the WISE band-1, the JWST NIR-F200W, and the optical u - r or g - r colors. These calibrations account for the biases attributed to the SP age, while they are given in the form of extinction-dependent and extinction-independent relations. The proposed calibrations show robust estimations while minimizing the scatter and biases throughout a wide range of SFRs and stellar masses. The SFR calibration offers better results, especially in dust-free or passive galaxies where the contributions of old SPs or biases from the lack of dust are significant. Similarly, the M $\star$ calibration yields significantly better results for dusty and high-SFR galaxies where dust emission can otherwise bias the estimations.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Field Laboratory for Emerging Stacked Unconventional Plays in Central Appalachia

The goal of the Field Laboratory for Emerging Stacked Unconventional Plays (ESUP) in Central Appalachia project was to investigate and characterize the resource potential for multi-play production of emerging unconventional reservoirs in Central Appalachia. Project activities included drilling, logging and coring of a vertical characterization well drilled to basement to approximately 15,000 feet in depth. The data from drilling and well logs as well recovered core samples were used by the research team to support characterization of the geology and potential pay zones within the Nora Gas Field of southwestern Virginia and the greater Central Appalachian Basin. This project was led by Dr. Nino Ripepi of the Virginia Center for Coal and Energy Research (VCCER) in close collaboration with EnerVest Operating LLC (EnerVest). VCCER is housed in the Department of Mining and Minerals Engineering at Virginia Tech and was created by an Act of the Virginia General Assembly on March 30, 1977, as an interdisciplinary study, research, information, and resource facility for the Commonwealth of Virginia. EnerVest is a top tier, low-cost oil and natural gas company with a long history of traditional operating relationships with institutional investors as well as public and private companies. This report summarizes two major research activities: 1) Log and Core Analysis and 2) Numerical Modeling. Core analysis comprises the characterization efforts of the ESUP Field Laboratory and includes a discussion of the well logs run in the deep characterization wells, an initial analysis of those, the number, size and location of cores recovered, core testing and analysis done to date as well as plans for future analysis. Numerical modeling is comprised of seven major modeling efforts, including (1) Multiphysics shale transport modeling work, (2) the developed in-house compositional simulator studies, (3) reservoir modeling studies using GEM software, (4) fracture modeling work using EFRAC3D software and (5) numerical modeling efforts with ABAQUS software, (6) Numerical modeling efforts using FLAC3D and PFC3D, and (7) Automatic Machine Learning (AutoML) Studies.

02 PETROLEUM↗
DOE OSTI2023

Disruption event characterization and forecasting in tokamaks

Disruption prediction and avoidance is a critical need for next-step tokamaks, such as ITER. Disruption Event Characterization and Forecasting (DECAF) research fully automates analysis of tokamak data to determine chains of events that lead to disruptions and to forecast their evolution allowing sufficient time for mitigation or complete avoidance of the disruption. Disruption event chains related to local rotating or global magnetohydrodynamic (MHD) modes and vertical instability are examined with warnings issued for many off-normal physics events, including density limits, plasma dynamics, confinement transitions, and profile variations. Along with Greenwald density limit evaluation, a local radiative island power balance theory is evaluated and compared to the observation of island growth. Automated decomposition and analysis of rotating tearing modes produce physical event chains leading to disruptions. A total MHD state warning model comprised of 15 separate criteria produces a disruption forecast about 180 ms before a standard locked mode detector warning. Single DECAF event analyses have begun on KSTAR, MAST, and NSTX/-U databases with thousands of shot seconds of device operation using from 0.5 to 1 × 10 6 tested sample times per device. An initial multi-device database comparison illustrates a highly important result that plasma disruptivity does not need to increase as βN increases. Global MHD instabilities, such as resistive wall modes (RWMs), can give the briefest time period of warning before disruption compared to other physics events. In an NSTX database with unstable RWMs, the mode onset, loss of boundary and current control, and disruption event warnings are found in all cases and vertical displacement events are found in 91% of cases. An initial time-dependent reduced physics model of kinetic RWM stabilization created to forecast the disruption chain predicts instability 84% of the time for experimentally unstable cases with a relatively low false positive rate. Instances of the disruption event chain analysis illustrate dynamics including H–L back transitions for rotating MHD and global RWM triggering events. Furthermore, disruption warnings are issued with sufficient time before the disruption (on transport timescales) to potentially allow active profile control for disruption avoidance, active mode control, or mitigation.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2024

LENS: Learning Enabled Network Synthesis

RTRC and UMD have developed novel machine learning based methods under the ARPA-E DIFFERENTIATE program for rapid acceleration of hypothesis generation in complex architecture design spaces involving both discrete choices of component inclusion and interconnection and continuous parametric decisions. The project named Learning Enabled Network Synthesis (LENS) further demonstrated the developed methods on challenging electrical power converter design problems by identifying the most suitable circuit topologies and simultaneously selecting the most appropriate components to achieve optimized design of power converter with improved performances. We demonstrated that LENS could enable exploration of very large design space of circuit topologies and components by addressing the limitations of conventional design process in non-linear, high switching speed, multi-dimensional power converter design and optimization. The key innovation developed in LENS is the seamless integration of statistical learning and logical reasoning techniques and building on the individual strengths of these techniques for rapid hypothesis discovery. The main component of LENS comprises of: 1) Graph Reasoning Engine (GRE) to enforce composition rules that rapidly reject all discrete architectures that are composed incorrectly and generates an adaptive database of feasible designs which can be used by ML modules, 2) Graph Generative Learning module which is a deep neural network based generative model for graph architectures which can enable design space exploration beyond the dataset generated by the GRE, 3) Graph Reduced Order Model (ROM) for graph domains for accelerating computation of output metrics, and 4) Active learning and Rule Discovery module for sample efficient learning and extracting logical rules from the learned ML models which will be integrated in the GRE to enhance the filtering effectiveness. LENS approach can be applied to any design domains where designs can be represented as multi-attribute graphs. The LENS team integrated the various technical innovations listed above into an optimization pipeline and exercised the optimization pipeline on the converter design problem. The LENS project demonstrated that the developed AI/ML technologies can be used to generate novel converter circuits >45x faster than experts on chosen use-cases. This can enable faster design space exploration and identification of new designs which are not considered by experts due to the increasing design space complexity. This has significant potential impact on the public and energy needs of the country. It is currently estimated that 30% of all electrical powers generated passes through power converters. The future estimate is that 80% of all power generated would be passing through converters. LENS fills a critical gap in this space since by accelerating the design process the designers would be able to generate more efficient converters which can lead to significant energy savings for the country.

42 ENGINEERING↗
NASA NTRS2019

Machine Learning for the Zwicky Transient Facility

The Zwicky Transient Facility is a large optical survey in multiple filters producing hundreds of thousands of transient alerts per night. We describe here various machine learning (ML) implementations and plans to make the maximal use of the large data set by taking advantage of the temporal nature of the data, and further combining it with other data sets. We start with the initial steps of separating bogus candidates from real ones, separating stars and galaxies, and go on to the classification of real objects into various classes. Besides the usual methods (e.g., based on features extracted from light curves) we also describe early plans for alternate methods including the use of domain adaptation, and deep learning. In a similar fashion we describe efforts to detect fast moving asteroids. We also describe the use of the Zooniverse platform for helping with classifications through the creation of training samples, and active learning. Finally we mention the synergistic aspects of ZTF and LSST from the ML perspective.

Ashish Mahabal↗
DOE OSTI2025

Expediting field-effect transistor chemical sensor design with neuromorphic spiking graph neural networks

Improving the sensitive and selective detection of analytes in a variety of applications requires accelerating the rational design of field-effect transistor (FET) chemical sensors. Achieving high-performance detection relies on identifying optimal probe materials that can effectively interact with target analytes, a process traditionally driven by chemical intuition and time-consuming trial-and-error methods. To address the difficulties in probe screening for FET sensor development, this work presents a methodology that combines neuromorphic machine learning (ML) architectures, specifically a hybrid spiking graph neural network (SGNN), with an enriched dataset of physicochemical properties through semi-automated data extraction using large language models. Achieving a classification accuracy of 0.89 in predicting sensor sensitivity categories, the SGNN model outperformed traditional ML techniques by leveraging its ability to capture both global physicochemical properties and sparse topological features through a hybrid modeling framework. Next-generation sensor design was informed by the actionable insights into the connections between material properties and sensing performance offered by the SGNN framework. Through virtual screening for the detection of per- and polyfluoroalkyl substances (PFAS) as a use case, the effectiveness of the SGNN model was further validated. Density functional theory simulations confirmed graphene as a promising active material for PFAS detection as suggested by the SGNN framework. By bridging gaps in predictive modeling and data availability, this integrated approach provides a strong foundation for accelerating advancements in FET sensor design and innovation.

Ferreira, Rodrigo Pires [Univ. of Chicago, IL (Uni↗