Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “ML T&E”

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 289 records · Page 16
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

DeCOIL: Optimization of Degenerate Codon Libraries for Machine Learning-Assisted Protein Engineering

With advances in machine learning (ML)-assisted protein engineering, models based on data, biophysics, and natural evolution are being used to propose informed libraries of protein variants to explore. Synthesizing these libraries for experimental screens is a major bottleneck, as the cost of obtaining large numbers of exact gene sequences is often prohibitive. Degenerate codon (DC) libraries are a cost-effective alternative for generating combinatorial mutagenesis libraries where mutations are targeted to a handful of amino acid sites. However, existing computational methods to optimize DC libraries to include desired protein variants are not well suited to design libraries for ML-assisted protein engineering. To address these drawbacks, we present DEgenerate Codon Optimization for Informed Libraries (DeCOIL), a generalized method which directly optimizes DC libraries to be useful for protein engineering: to sample protein variants that are likely to have both high fitness and high diversity in the sequence search space. Using computational simulations and wet-lab experiments, we demonstrate that DeCOIL is effective across two specific case studies, with potential to be applied to many other use cases. DeCOIL offers several advantages over existing methods, as it is direct, easy-to-use, generalizable, and scalable. With accompanying software, DeCOIL can be readily implemented to generate desired informed libraries.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2022

Enabling practical nanoparticle electrodeposition from aqueous nanodroplets

The rapid rise of technology in the modern world has led to an increased demand for energy. Consequently, it is essential to increase the efficiency of current energy-producing systems due to the poor activity of their catalysts. Nanoparticles play a significant role in energy storage and conversion; however, electrodeposition of nanoparticles is difficult to achieve due to surface heterogeneities, nanoparticle diffusion layer overlap, and the inability to electrodeposit multi-metallic nanoparticles with stoichiometric control. These problems can be solved through nanodroplet-mediated electrodeposition, a technique where water nanodroplets are filled with metal salt precursors that form stable nanoparticles when they collide with a negatively-biased electrode. Further, this method has demonstrated control over nanoparticle size and morphology, displaying a wide variety of applications for the generation of materials with excellent catalytic properties. Historically, the cost of nanodroplet-mediated electrodeposition experimentation is prohibitive because practitioners use 0.1 M to 0.5 M tetrabutylammonium perchlorate (TBAP) dissolved in the oil phase (∼10 mL). Such high concentrations of electrolytes have been used to lower ohmic drop and provide ions to maintain charge balance during electrodeposition. Here, we show that supporting electrolyte is not necessary for the oil phase. In fact, one can use a suitable salt (such as lithium perchlorate) in the aqueous phase to achieve nanoparticle electrodeposition. This simple change, grounded in an understanding of ion transfer, drives down the cost per experiment by nearly three orders of magnitude, representing a necessary step forward in enabling practical nanoparticle electrodeposition from water nanodroplets. This approach is a promising procedure for future cost-effective energy conversion systems relying on electrocatalytic nanoparticles.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2026

Enabling integrated AI control on DIII-D: a control system design with state-of-the-art experiments

We present the design and application of a general algorithm for Prediction And Control using MAchiNe learning (PACMAN) in DIII-D. Machine learning (ML)-based predictors and controllers have shown great promise in achieving regimes in which traditional controllers fail, such as tearing mode (TM) free scenarios, ELM-free scenarios and stable advanced tokamak conditions. The architecture presented here was deployed on DIII-D to facilitate the end-to-end implementation of advanced control experiments, from diagnostic processing to final actuation commands. This paper describes the detailed design of the algorithm and explains the motivation behind each design point. We also describe several successful ML control experiments in DIII-D using this algorithm, including a reinforcement learning controller targeting advanced non-inductive plasmas, a wide-pedestal quiescent H-mode ELM predictor, an Alfvén Eigenmode controller, a Model Predictive Control plasma profile controller and a state-machine TM predictor-controller. There is also discussion on guiding principles for real-time ML controller design and implementation.

machine learning↗
DOE OSTI2024

Toward machine-learning-assisted PW-class high-repetition-rate experiments with solid targets

We present progress in utilizing a machine learning (ML) assisted optimization framework to study the trends in a parameter space defined by spectrally shaped, high-intensity, petawatt-class (8 J, 45 fs) laser pulses interacting with solid targets and give the first simulation-based overview of predicted trends. A neural network (NN) incorporating uncertainty quantification is trained to predict the number of hot electrons generated by the laser–target interaction as a function of pulse shaping parameters. The predictions of this NN serve as the basis function for a Bayesian optimization framework to navigate this space. For post-experimental evaluation, we compare two separate neural network (NN) models. One is based solely on data from experiments, and the other is trained only on ensemble particle-in-cell simulations. Reviewing the predicted and observed trends across the experiment-capable laser parameter search space, we find that both ML models predict a maximal increase in hot electron generation at a level of approximately 12%–18%; however, no statistically significant enhancement was observed in experiments. On direct comparison of the NN models, the average discrepancy is 8.5%, with a maximum of 30%. Since shot-to-shot fluctuations in experiments affect the observations, we evaluate the behavior of our optimization framework by performing virtual experiments that vary the number of repeated observations and the noise levels. Here, we discuss the implications of such a framework for future autonomous exploration platforms in high-repetition-rate experiments.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRS1976

Effect of hypovolemia, infusion, and oral rehydration on gradual onset +Gz acceleration tolerance

The purpose of this study was to determine the effect of blood withdrawal, blood infusion, and oral fluid intake on +Gz tolerance at an acceleration rate of 0.5 G/min. Six healthy men aged 21-27 yr were centrifuged after the withdrawal of 400 ml of blood (hypovolemia) from each man; they were centrifuged again following blood infusion (Phase I). Three weeks later the men were accelerated after similar hypovolemia and again after consuming 800 ml of an isotonic NaCl drink (Phase II). Phase I hypovolemia resulted in a reduction in tolerance in all subjects from a mean control level of 6.42 + or - 0.35 min to 5.45 + or - 0.17 min (-15.1%, p less than 0.05). Both infusion and drinking returned tolerances to control levels. During acceleration there were significant (p less than 0.05) increases in plasma vasopressin levels to 35 pg/ml; these were not influenced appreciably by infusion or drinking. In all acceleration runs there was an obligatory shift (loss) of plasma volume and electrolytes, especially potassium, regardless of the experimental treatments. Oral rehydration is shown to be as effective as blood replacement in restoring +Gz acceleration tolerance decrements due to hypovolemia.

Greenleaf, J. E.↗
DOE OSTI2025

Machine-Learning Analysis of Radiative Decays to Dark Matter at the LHC

The search for weakly interacting matter particles (WIMPs) is one of the main objectives of the High Luminosity Large Hadron Collider (HL-LHC). In this work we use Machine-Learning (ML) techniques to explore WIMP radiative decays into a Dark Matter (DM) candidate in a supersymmetric framework. The minimal supersymmetric WIMP sector includes the lightest neutralino that can provide the observed DM relic density through its co-annihilation with the second lightest neutralino and lightest chargino. Moreover, the direct DM detection cross section rates fulfill current experimental bounds and provide discovery targets for the same region of model parameters in which the radiative decay of the second lightest neutralino into a photon and the lightest neutralino is enhanced. This strongly motivates the search for radiatively decaying neutralinos which, however, suffers from strong backgrounds. We investigate the LHC reach in the search for these radiatively decaying particles by means of cut-based and ML methods and estimate its discovery potential in this well-motivated, new physics scenario. We demonstrate that using ML techniques would enable access to most of the parameter space unexplored by other searches.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2023

Development of a hybrid neural network and transfer learning model for optimized ICP-MS/MS operation

Correct function and calibration of instrumentation is a crucial assumption for any scientific experiment. One such instrument, tandem inductively coupled plasma mass spectrometer (ICP-MS/MS), has in-depth calibration settings that range across 30+ different parameters, making it difficult to determine optimal conditions without expertise and some degree of trial and error. Often, these settings are hand-tuned, a time-intensive process prone to local maxima and human error. While some automation is available, the automation also may favor local optimizations over a global optimum. In addition to these difficulties, day to day instrument variability can further complicate the calibration process. We propose a solution to this problem as a machine learning (ML) algorithm that learns how each parameter helps determine the calibration sensitivity across several elements, and re-weights parameters over time as instrument variability changes (e.g., a global neural network (NN) with a time-dependent transfer learning (TL) component). This model would be able to generate a surface of predicted calibration sensitivities and their respective parameters, and a simple multivariate algorithm would be able to pull out the optimum results with the settings associated with them. Here-in, we describe our initial findings in working towards this goal, including data extraction from historical files, exploratory data analysis, and some initial model building to better describe the data and the feasibility of our goal.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
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 NTRS1994

Hypervolemia in men from drinking hyperhydration fluids at rest and during exercise

To test the hypothesis that drink composition is more important than drink osmolality (Osm) for maintaining and increasing plasma volume (PV) at rest and during exercise, six men (22-39 yr, 76.84 +/- 16.19 kg, 2.99 +/- 0.45 L/min VO2 peak) each underwent six treatments while sitting for 90 min (VO2 = 0.39 L/min) and then performed upright ergometer exercise for 70 min (VO2 = 2.08 +/- 0.33 1/min, 70% +/- 7% VO2 peak). Drink formulations (10 ml/kg body weight, X = 768 ml) for the sitting period were: P1 (55 mEq Na(+), 365 mOsm/kg H2O), P2 (97.1 mEq Na(+), 791 mOsm/kg), P2G (113 mEqNa(+), 80 ml glycerol, 1,382 mOsm/kg, HyperAde (HA) (164 mEq Na(+), 253 mOsm/kg), and 01 and 02 (no drinking). The exercise drink (10 ml/kg, 768 ml) was P1 for all treatments except 02. Plasma volume at rest increased (p less than 0.05) by 4.7% with P1 and by 7.9% with HA. Percent change in PV during exercise was +1% to +3%0(NS) with HA; -6% to 0% (NS) with P1, P2, P2G, and 01; and -8% to -5% (p less than 0.05) with 02. HyperAde, with the lowest osmolality (253 mOsm/kg), maintained PV at rest and during exercise, whereas the other drinks with lower Na(+) and higher osmolality (365 to 1,382 mOsm/kg) did not. But Performance 1 also increased PV at rest. Thus, drink composition may be more important than drink osmolality for increasing plasma volume at rest and for maintaining it during exercise.

Greenleaf, J. E.↗
DOE OSTI2025

Machine learning model inputs, outputs, and scripts associated with “Artificial intelligence-guided iterations between observations and modeling significantly improve environmental predictions”

NOTE: The manuscript associated with this data package is currently in review. The data may be revised based on reviewer feedback. Upon manuscript acceptance, this data package will be updated with the final dataset and additional metadata. This data package is associated with the manuscript “Artificial intelligence-guided iterations between observations and modeling significantly improve environmental predictions” (Malhotra et al., in prep). This effort was designed following ICON (integrated, coordinated, open, and networked) principles to facilitate a model-experiment (ModEx) iteration approach, leveraging crowdsourced sampling across the contiguous United States (CONUS). New machine learning models were created every month to guide sampling locations. Data from the resulting samples were used to test and rebuild the machine learning models for the next round of sampling guidance. Associated sediment and water geochemistry and in situ sensor data can be found at https://data.ess-dive.lbl.gov/datasets/doi:10.15485/1923689, https://data.ess-dive.lbl.gov/datasets/doi:10.15485/1729719, and https://data.ess-dive.lbl.gov/datasets/doi:10.15485/1603775. This data package is associated with two GitHub repositories found at https://github.com/parallelworks/dynamic-learning-rivers and https://github.com/WHONDRS-Hub/ICON-ModEx_Open_Manuscript. In addition to this readme, this data package also includes two file-level metadata (FLMD) files that describes each file and two data dictionaries (DD) that describe all column/row headers and variable definitions. This data package consists of two main folders (1) dynamic-learning-rivers and (2) ICON-ModEx_Open_Manuscript which contain snapshots of the associated GitHub repositories. The input data, output data, and machine learning models used to guide sampling locations are within dynamic-learning-rivers. The folder is organized into five top-level directories: (1) “input_data” holds the training data for the ML models; (2) “ml_models” holds machine learning (ML) models trained on the data in “input_data”; (3) “examples” contains files for direct experimentation with the machine learning model, including scripts for setting up “hindcast” run; (4) “scripts” contains data preprocessing and postprocessing scripts and intermediate results specific to this data set that bookend the ML workflow; and (5) “output_data” holds the overall results of the ML model on that branch. Each trained ML model resides on its own branch in the repository; this means that inputs and outputs can be different branch-to-branch. There is also one hidden directory “.github/workflows”. This hidden directory contains information for how to run the ML workflow as an end-to-end automated GitHub Action but it is not needed for reusing the ML models archived here. Please see the top-level README.md in the GitHub repository for more details on the automation. The scripts and data used to create figures in the manuscript are within ICON-ModEx_Open_Manuscript. The folder is organized into four folders which contain the scripts, data, and pdf for each figure. Within the “fig-model-score-evolution” folder, there is a folder called “intermediate_branch_data” which contains some intermediate files pulled from dynamic-learning-rivers and reorganized to easily integrate into the workflows. NOTE: THIS FOLDER INCLUDES THE FILES AT THE POINT OF PAPER SUBMISSION. IT WILL BE UPDATED ONCE THE PAPER IS ACCEPTED WITH ANY REVISIONS AND WILL INCLUDE A DD/FLMD AT THAT POINT. We thank the United States Forest Service, Washington Department of Fish and Wildlife, Washington Department of Natural Resources, Cowiche Canyon Conservatory, Washington State Parks and Recreation Commission (Scientific Research Permit #210901), and the Confederated Tribes and Bands of the Yakama Nation for access to field locations where the samples labeled “SSS” were collected. We also thank the Yakama Nation Tribal Council and Yakama Nation Fisheries for working with us to facilitate sample collection and optimization of data usage according to their values and worldview. WHONDRS consortium members were asked to provide any acknowledgments for the collection of samples labeled “CM” and the following is a list of acknowledgments that were submitted with their corresponding Site IDs: (MART) Research activities were conducted in part on the Wind River Experimental Forest within the Gifford Pinchot National Forest; (MP- 100379) Philadelphia is part of Lenapehoking, the ancestral homelands of the Lenape peoples; (MP-102398) Land surveyed is the ancestral homelands of the Nookhose'iinenno (Arapaho), Tsis tsis'tas (Cheyenne), and Nuuchu (Ute); (MP-100749 and MP- 100747) Georgia Coastal Ecosystem LTER, OCE-1832178; (SP-70 and SP-72) Eastern Shoshone, Shoshone-Bannock; (MP- 102944) Funded by Oregon Watershed Enhancement Board. On the traditional lands of the Confederated Tribes of the Siletz, Confederated Tribes of the Grand Rhonde, and the Clatsop-Nehalem Confederated Tribe; (MP- 100607) Holiday Creek is located on the traditional territory of the Monacan Indian Nation; (SP-45) Lafayette Blue Springs State Park; (MP-102420) NSF DEB-2016749; (MP-100019) New Hampshire Agriculture Experiment Station; (SP-35) Rayonier (land owner; https://www.rayonier.com/); (MP- 101276) US Department of Energy, Office of Science, Biological and Environmental Research, Subsurface Biogeochemical Research, Watershed Dynamics and Evolution SFA at ORNL; (MP- 103224) Watershed Dynamics and Evolution SFA at ORNL; (MP- 101584) Traditional lands of the Oceti Sakowin (Dakota, Lakota, Nakoda) and Anishinaabe Peoples.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2024

Comparison of Machine Learning Approaches for Prediction of the Equivalent Alkane Carbon Number for Microemulsions Based on Molecular Properties

The chemical properties of oils are vital in the design of microemulsion systems. The hydrophilic–lipophilic difference equation used to predict microemulsions’ phase behavior expresses the oils’ physiochemical properties as the equivalent alkane carbon number (EACN). The experimental determination of EACN requires knowledge of the temperature dependence of the microemulsion system and the effects of different surfactant concentrations. Thus, the experimental determination is time-intensive and tedious, requiring days to months for proper separations. Furthermore, the experiments require high purity of chemicals because microemulsions are sensitive to impurities. Our work focuses on the quick and reliable predictions of the EACN with machine learning (ML) models. Due to the immaturity of ML chemical predictions, we compare three graph neural networks (GNNs) and a gradient-boosted tree algorithm, known as XGBoost. The GNNs use the molecular structures represented as simplified molecular-input line-entry system (SMILES) codes for the initial input, which allows us to assess whether geometry optimization is necessary for reliable results. The XGBoost model also begins with the SMILES representations of the molecules but uses molecular descriptors instead of geometry optimizations. As a result, the best model tested (crystal graph convolutional neural network with Merck molecular force field-94) has an error of 1.15 EACN units of the true EACN for unknown data with the errors skewed toward zero and an R² score of 0.9

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS2003

Body water handling in response to hypertonic-saline induced diuresis in fasting northern elephant seal pups (Mirounga angustirostris)

During natural fasting conditions in postweaned northern elephant seal (NES) (Mirounga angustirostris) pups, urinary water loss is minimized and percent total body water (TBW) is maintained constant. However, following infusion of hypertonic saline, glomerular filtration rate (GFR) and urine output increased in fasting pups. Therefore, we quantified the magnitude of the hypernatremia-induced diuresis relative to the animal's total body water (TBW) pool and the percentage of filtered water reabsorbed. Following a 24 h control period, naturally fasting NES pups (n=7) were infused (4 ml min(-1)) with hypertonic saline (16.7%) at a dose of 3 mmol NaCl kg(-1) body mass. Total body water was estimated prior to infusion by tritium dilution, GFR was estimated by standard creatinine clearance, and urine output (V) was measured for 24 h during the control and post infusion periods. Percentage of filtered water reabsorbed was calculated as (1-(V/GFR))x100. Twenty-four hours following the infusion, GFR (control: 69+/-12 ml min(-1) and post-infusion: 118+/-19 ml min(-1); mean+/-S.E.) increased 77+/-28% above control and the percentage of filtered water reabsorbed was decreased 0.4+/-0.1%. The increase in urine output (control: 218+/-47 ml d(-1) and post-infusion: 883+/-92 ml d(-1)) accounted for 1.7+/-0.2% of the pups' TBW. The hypernatremia-induced diuresis was accompanied by the loss of body water indicating the lack of water retention. Although the 77% increase in GFR was only associated with a 0.4% decrease in the percentage of filtered water reabsorbed, this decrease was significant enough to result in a 4-fold increase in urine output. Despite the observed diuresis, fasting NES pups appear to possess an efficient water recycling mechanism requiring only a small percentage of body water to excrete an excess salt load. This water recycling mechanism may allow pups to avoid negative perturbations in body water as they initiate feeding in a marine environment following the fast.

Non-NASA Center↗
NASA NTRSDate not supplied

Supercritical Water Oxidation: Testing of Ersatz Wastewater

Supercritical Water Oxidation (SCWO) technology is under consideration by NASA for treatment of wastewater and other wet waste streams. The dramatic changes in water's thermophysical properties near its critical point (374◦C and 22 MPa) result in nearly complete solubility of organics and gases. The absence of inter–phase transport processes and phase separation results in dramatically reduced reaction timescales and the elimination of complications of two–phase transport and processing in reduced gravity. Other advantages are that the product streams are microbially inert,benign, amenable to resource recovery and organic waste. This paper first described the design and construction of tubular SCWO reactor built at NASA Glenn. It consists of separate wastewater and oxidizer inlets, which are independently heated and pressurized to conditions approaching the critical point of water. These flows enter a reactor chamber having a volume of 62 ml. The reactor section is heated to the desired temperature in the range of 450 ◦C – 650 ◦C. A pressure regulator maintains the operating pressure nominally between 27.6 MPa and 28.3 MPa. The reacted fluid is captured downstream of the pressure regulator during an experiment run. A separate vent line may also be used for collection of the effluent. Next, the results of SCWO experiments using both a representative organic (ethanol) as well as a wastewater simulant provided by NASA Ames are presented. Raman analysis of the pre–reacted and post–reacted solutions are presented. Finally, initial efforts on supplementary chemical kinetics modeling of ethanol oxidation with and without inclusion of a nitrogenous compounds (ammonia) are presented.

Michael C Hicks↗
DOE OSTI2023

Estimating cross-field particle transport at the outer midplane of TCV by tracking filaments with machine learning

Abstract Cross-field transport of particles in the boundary region of magnetically confined fusion plasmas is dominated by turbulence. Blobs, intermittent turbulent structures with large amplitude and a filamentary shape appearing in the scrape-off layer (SOL), are known from theoretical and experimental studies to be the main contributor to the cross-field particle transport. The dynamics of blobs differs depending on various plasma conditions, including triangularity ( δ ). In this work, we analyze triangularity dependence of the cross-field particle transport at the outer midplane of plasmas with δ = + 0.38 , +0.15, −0.14, and −0.26 on the Tokamak à Configuration Variable, using our novel machine learning (ML) blob-tracking approach applied to gas puff imaging data. The cross-field particle flux determined in this way is of the same order as the overall transport inferred from KN1D, GBS, and SOLPS-ITER simulations, suggesting that the blobs identified by the ML blob-tracking account for most of the cross-field particle transport in the SOL. Also, the ML blob-tracking and KN1D show a decrease in the cross-field particle transport as δ becomes more negative. The blob-by-blob analysis of the result from the tracking reveals that the decrease of cross-field particle transport with decreasing δ is accompanied by a decrease in the number of blobs in a fixed time, which tend to have larger area and lower radial speed. Also, the blobs in these plasmas are in the connected sheath regime, and show a velocity scaling consistent with the two-region model.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2023

Physics-Informed Machine Learning for Modeling and Control of Dynamical Systems

Physics-informed machine learning (PIML) is a set of methods and tools that systematically integrate machine learning (ML) algorithms with physical constraints and abstract mathematical models developed in scientific and engineering domains. As opposed to purely data-driven methods, {PIML} models can be trained from additional information obtained by enforcing physical laws such as energy and mass conservation. More broadly, {PIML} models can include abstract properties and conditions such as stability, convexity, or invariance. The basic premise of {PIML} is that the integration of ML and physics can yield more effective, physically consistent, and data-efficient models. This paper aims to provide a tutorial-like overview of the recent advances in {PIML} for dynamical system modeling and control. Specifically, the paper covers an overview of the theory, fundamental concepts and methods, tools, and applications on topics of: 1) physics-informed learning for system identification; 2) physics-informed learning for control; 3) analysis and verification of {PIML} models; and 4) physics-informed digital twins. The paper is concluded with a perspective on open challenges and future research opportunities.

Nghiem, Truong↗
DOE OSTI2023

Reining in Radium for Nuclear Medicine: Extra-Large Chelator Development for an Extra-Large Ion

Targeted α therapy (TAT) of soft-tissue cancers using the α particle-emitting radionuclide 223 Ra holds great potential because of its favorable nuclear properties, adequate availability, and established clinical use for treating metastatic prostate cancer of the bone. Despite these advantages, the use of 223 Ra has been largely overshadowed by other α emitters due to its challenging chelation chemistry. A key criterion that needs to be met for a radionuclide to be used in TAT is its stable attachment to a targeting vector via a bifunctional chelator. The low charge density of Ra 2+ arising from its large ionic radius weakens its electrostatic binding interactions with chelators, leading to insufficient complex stability in vivo. In this study, we synthesized and evaluated macropa-XL as a novel chelator for 223 Ra. It bears a large 21-crown-7 macrocyclic core and two picolinate pendent groups, which we hypothesized would effectively saturate the large coordination sphere of the Ra 2+ ion. The structural chemistry of macropa-XL was first established with the nonradioactive Ba 2+ ion using X-ray diffraction and X-ray absorption spectroscopy, which revealed the formation of an 11-coordinate complex in a rare anti pendent-arm configuration. Subsequently, the stability constant of the [Ra(macropa-XL)] complex was determined via competitive cation exchange with 223 Ra and 224 Ra radiotracers and compared with that of macropa, the current state-of-the-art chelator for Ra 2+ . A moderate log K ML value of 8.12 was measured for [Ra(macropa-XL)], which is approximately 1.5 log K units lower than the stability constant of [Ra(macropa)]. This relative decrease in Ra 2+ complex stability for macropa-XL versus macropa was further probed using density functional theory calculations. Additionally, macropa-XL was radiolabeled with 223 Ra, and the kinetic stability of the resulting complex was evaluated in human serum. Furthermore, although macropa-XL could effectively bind 223 Ra under mild conditions, the complex appeared to be unstable to transchelation. Collectively, this study sheds additional light on the chelation chemistry of the exotic Ra 2+ ion and contributes to the small, but growing, number of chelator development efforts for 223 Ra-based TAT.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Silver Adsorption on Calcium Niobate(001) Nanosheets: Calorimetric Energies That Explain Sinter-Resistant Support

Metal nanoparticles deposited on oxide supports are essential to many technologies, including catalysts, fuel cells and electronics. Therefore, understanding the chemical bonding strength between metal nanoparticles and oxide surfaces is of great interest. The adsorption energetics, adhesion energy and adsorbate structure of Ag on dehydrated HCa 2 Nb 3 O 10 (001) nanosheets at 300 K have been studied using metal adsorption calorimetry and surface spectroscopies. These dehydrated (“dh”) calcium niobate nanosheets “(dh-HCa 2 Nb 3 O 10 (001))” have stoichiometry Ca 4 Nb 6 O 19 . They impart unusual stability to metal nanoparticles when used as catalyst supports and are easy-to-prepare by Langmuir-Blodgett (LB) techniques, highly ordered, and essentially single-crystal surfaces of mixed oxides with a huge ratio of terrace to edge sites. Below monolayer coverage, Ag grows on dh-HCa 2 Nb 3 O 10 (001) as 2D islands of thickness ~2 layers. The differential heat of Ag adsorption is initially ~303 kJ/mol, increasing slowly to ~338 kJ/mol by 0.8 ML. At higher coverages, Ag atoms mainly add on top of these 2D islands, growing 3D nanoparticles of increasing thickness, as the heat decreases asymptotically towards silver’s heat of sublimation (285 kJ/mol). The adhesion energy of Ag(s) to this Ca niobate surface is estimated to be 4.33 J/m 2 , larger than on any oxide surface previously measured. This explains the sinter resistance reported for metal nanoparticles on this support. Electron transfer from Ag into the calcium niobate is also measured. Furthermore, these results demonstrate an easy way to do singlecrystal-type surface science studies - and especially thermochemical measurements - on the complex surfaces of mixed oxides: using LB-deposited perovskite nanosheets and ultrahigh vacuum annealing in O 2 .

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
NASA NTRS1995

A conceptual design for the attitude control and determination system for the Magnetosphere Imager spacecraft

This paper presents a conceptual design for the attitude control and determination (ACAD) system for the Magnetosphere Imager (Ml) spacecraft. The MI is a small spin-stabilized spacecraft that has been proposed for launch on a Taurus-S expendable launch vehicle into a highly-ellipdcal polar Earth orbit. Presently, launch is projected for 1999. The paper describes the MI mission and ACAD requirements and then proposes an ACAD system for meeting these requirements. The proposed design is low-power, low-mass, very simple conceptually, highly passive, and consistent with the overall MI design philosophy, which is faster-better-cheaper. Still, the MI ACAD system is extremely robust and can handle a number of unexpected, adverse situations on orbit without impacting the mission as a whole. Simulation results are presented that support the soundness of the design approach.

Polites, M. E.↗