Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “SCORE”

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 793 records · Page 44
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Evaluation of Planetary Extravehicular Activity Prebreathe Protocols using a 56.5 kPa, 34% O2, 66% N2 Saturation Cabin Atmosphere in an 11-day Hypobaric Hypoxia Study

INTRODUCTION: Apollo missions used 100% O2 cabin atmospheres which effectively eliminated the risk of decompression sickness (DCS) during Lunar extravehicular activities (EVAs, ‘spacewalks’); however, this atmosphere presented a flammability risk that is no longer acceptable to NASA. Denitrogenation prebreathe protocols used to mitigate DCS risk for Space Shuttle and International Space Station EVAs are validated for the microgravity environment, but the significantly increased risk of DCS during equivalent ambulatory surface EVAs make these protocols inapplicable to planetary/Lunar missions. A cabin/vehicle “Exploration Atmosphere” of 56.5 kPa (8.2 psia), 34% O2, 66% N2 has been recommended by NASA for future Moon and Mars missions as a compromise that balances subsequent pre-EVA prebreathe duration, hypoxia, and flammability risk, assuming a 29.6 kPa (4.3 psi) spacesuit. Prebreathe validation studies were initiated utilizing a three-story 6m diameter hypobaric chamber at NASA’s Johnson Space Center. Here, we report the results of a 11-day human-in-the-loop system checkout. METHODS: Six volunteers lived in a hyboparic chamber for 11 days with an ‘exploration atmosphere’ of 56.6kPa/34% O2 66% N2. Subjects acclimated to the exploration atmosphere for 48hrs and thereafter participated in five 6-hour simulated EVAs at 34kPa/85% O2 / 15% N2 over the course of 11 days. Prior to each simulated EVA, subjects underwent a 20-minute prebreathe at 85% O2. The EVA simulation was designed to include tasks that are physically and ergonomically representative of future planetary EVAs, proportionate to the subject’s VO2max. Decompression stress was evaluated during the simulated EVA by serial doppler and echocardiographs alternating every 15min, as well as clinical monitoring for DCS signs/symptoms. RESULTS AND DISCUSSION: Venous gas emboli (VGE) were present in 3 of 6 subjects during EVAs, with peak Grade II VGE as evaluated by Doppler and a peak Eftedal-Brubakk score of 5 by cardiac ultrasonography. Two cases of DCS were diagnosed during the 11-day test chamber. No acute hypoxic symptoms were noted. Musculoskeletal and gastrointestinal complaints were noted, likely associated with the exercise load and the food system. Two cases of DCS (8%) does not cross either accept or reject pre-test criterion, so an additional study is planned for 2023 to meet our pre-test thresholds.

Alejandro Garbino↗
NASA NTRSDate not supplied

Benchmark Models for Classification of Radiation Type Induced in Immune Cells

NASA Biological and Physical Sciences and the Science Mission Directorate have published a benchmark dataset of mouse immune cells subjected to radiation-induced DNA damage. The dataset comprises ML-ready microscopic imagery of said cells, including labels indicating radiation type and dose. The machine learning team at NASA Interagency Implementation and Advanced Concept Team (IMPACT) created multiple benchmark models. Initially, we conducted a preliminary analysis using thresholding. The algorithm used thresholds on average brightness of the available images to classify them into their respective radiation type. We also tested machine learning approaches. Convolutional Neural Networks (CNN) emerged as the best-performing model. This poster presents the benchmark scores obtained by the models.

Vishal Perekadan↗
NASA NTRS2022

Orbital Debris Quarterly News

- DebriSat Analysis and Shape Categorization - The Influence of Fragmentations and Mission-related Objects on the Space Environment - Abstracts from the NASA ODPO - Abstracts from the HVIT Group - Conference and Workshop Reports - Upcoming Meetings - Space Missions and Satellite Box Score

Heather Cowardin↗
NASA NTRSDate not supplied

Employing NASA Earth Observations and Socioeconomic Data to Conduct Site Suitability Analyses on Residential Tree Planting Initiatives in Phoenix, Arizona

Phoenix, Arizona is the hottest large city in the United States with an average summer daytime temperature of 106°F. Temperatures in Phoenix continue to climb due to increasing global greenhouse gas concentrations and regional urbanization. The impacts of high temperatures, including heat-related illnesses and deaths, are disproportionately concentrated in low-income neighborhoods often characterized by little tree canopy, lack of green space, and insufficient access to shade. The City of Phoenix’s Office of Heat Response and Mitigation and Arizona State University’s Urban Climate Research Center, partnered with NASA DEVELOP to identify residential neighborhoods and parcels within qualified census tracts (QCTs) to be prioritized for tree planting initiatives using funding from the American Rescue Plan Act (ARPA). This project conducted analyses using NASA Earth observations, socioeconomic data from the 2019 American Community Survey, and local tree canopy and mobility data. For Earth observations, daytime land surface temperature, vegetation, and land cover were obtained from the Landsat 8 Thermal Infrared Sensor (TIRS) and Operational Land Imager (OLI). The project team incorporated these data into a heat vulnerability index (HVI) with an emphasis on tree canopy and social vulnerability to rank block groups within QCTs and focused on the resulting top 25 block group HVI scores. These top 25 most vulnerable block groups were then processed through a parcel analysis to determine the feasibility of residential tree planting based on building footprints on each parcel. Within the top 25 block groups, 2,411 parcels were analyzed, and 3,133 existing trees were identified averaging 1.3 trees per parcel with 90% of parcels having 3 trees or less. Homes with 2 trees or fewer were considered high priority for future planting efforts. Based on the City’s goals for increased tree canopy the project team determined that <10,000 additional trees would need to be planted within the most vulnerable 25 block groups. The project findings have helped initiate community engagement efforts and have contributed to the approval of tree planting funds in Phoenix.

Ryan Hammock↗
NASA NTRSDate not supplied

Increasing Cognitive Ability/Reserve Using Software – Pilot (ICARUS-Pilot)

Background: This research study was competitively awarded under the 2022 JSC Innovation Charge Account (ICA) program administered by NASA Johnson Space Center’s Joint Technology Working Group. Study period of performance was May through September 2022, with a maximum allowed procurement budget of $10K. The study sought to quantify and assess the potential benefit of using commercial-off-the-shelf (COTS) cognitive training software to improve cognitive performance in an astronaut-like terrestrial population. Methods: Five volunteer research participants were recruited from the JSC employee population to mimic certain demographic characteristics of the NASA astronaut population (age, education/discipline). Participant cognitive performance was assessed before and after executing eighteen sessions of remote cognitive training executed nominally three times per week using six exercises within an adaptive app-based COTS software package (BrainHQ, Posit Science) on study-provided tablets. Pre- and post-training cognitive performance was measured using internal assessments in BrainHQ as well as Cognition Test Battery (CTB) version ISS B01 v3 (3.0.9-201710021500), an independent software test developed specifically for NASA and used currently in research studies on astronauts. BrainHQ exercises were posited to map well or partially to several CTB sub-tests. Participants provided feedback on their study experience formally via semi-structured interview at the conclusion of testing and informally throughout the study if they encountered issues. Results: The enrolled ICARUS-Pilot study participants generally matched Artemis crew demographic characteristics. Four of five participants have completed study training and assessment activities as of the writing of this abstract. These test participants complied well with desired training session frequency and duration yielding an average cumulative active training duration of 15 hours over an average of 45 days; participants showed 78% average improvement in metric performance for the six trained exercises, with an associated overall 33%ile ranking increase against performance of the entire BrainHQ subscribing population for internal pre/post assessment, agreeing with post-study survey self-reported performance increases. CTB overall feedback scoring, not corrected for learning effects, showed an average of 19% performance improvement across its 10 performance measures over the training period for the completed participants. Detailed analyses will be conducted once participant data collection for the study is complete and the resulting dataset is fully populated. Discussion: These preliminary results provide a positive trend for the effectiveness of the training approach, but further analysis will be needed to establish significance, investigate far transfer, and suggest the needed participant pool size for subsequent efforts to achieve statistically significant outcomes given similar results. The pilot study has already been helpful by allowing the study team to learn a great deal about the capabilities and limitations of the COTS software package that will be reflected in future proposals along with revised timelines for study execution and test participant management. From participant feedback, one common thread regarding the COTS training was that it felt overly repetitive – future proposals should reassess overall training duration, available levels for each trained exercise, and the behavior of the BrainHQ internal scheduler in determining which exercises should be trained and for how long. If the final analysis of this feasibility study ultimately supports it, the study team will recommend further investigation to fully evaluate this potential countermeasure and optimize its implementation. Future proposals would cite this feasibility study’s outcome and would seek to refine the training protocol and obtain statistically significant results for cognitive performance increases as well as retention data.

cognitive training↗
NASA NTRS2022

Evolution and folding of repeat proteins

Repeat proteins are made with tandem copies of similar amino acid stretches that fold into elongated architectures. These proteins constitute excellent model systems to investigate how evolution relates to structure, folding, and function. Here, we propose a scheme to map evolutionary information at the sequence level to a coarse-grained model for repeat-protein folding and use it to investigate the folding of thousands of repeat proteins. We model the energetics by a combination of an inverse Potts-model scheme with an explicit mechanistic model of duplications and deletions of repeats to calculate the evolutionary parameters of the system at the single-residue level. These parameters are used to inform an Ising-like model that allows for the generation of folding curves, apparent domain emergence, and occupation of intermediate states that are highly compatible with experimental data in specific case studies. We analyzed the folding of thousands of natural Ankyrin repeat proteins and found that a multiplicity of folding mechanisms are possible. Fully cooperative all-or-none transitions are obtained for arrays with enough sequence-similar elements and strong interactions between them, while noncooperative element-by-element intermittent folding arose if the elements are dissimilar and the interactions between them are energetically weak. Additionally, we characterized nucleation-propagation and multidomain folding mechanisms. We show that the global stability and cooperativity of the repeating arrays can be predicted from simple sequence scores.

Ezequiel A. Galpern↗
NASA NTRSDate not supplied

Light as a Reactive Countermeasure to Sleep Inertia: Translating Laboratory Findings to the Field

Sleep inertia describes the brief period of impaired alertness, mood, and cognitive performance experienced after waking. Under laboratory settings, light exposure upon waking during a habitual sleep period has been shown to improve sleep inertia symptoms. We investigated whether a field-deployable light-emitting device would help to mitigate sleep inertia in a real-world setting. Thirty-six participants (18 female; 26.6 years ± 6.1) completed an at-home, within-subject, randomized crossover study. Participants followed their habitual sleep-wake schedule for five nights before an adaptation and experimental night. Forty-five minutes after bedtime on the experimental night, participants received a phone call and were instructed to wear light-emitting glasses with the light either on (light condition) or off (control). A 5-minute psychomotor vigilance task (PVT), the Karolinska Sleepiness Scale (KSS), visual analog scales of mood (VASmood), and a 3-minute descending subtraction task (DST) were performed starting at +2, +12, +22, and +32 minutes after the call. Participants then went back to sleep and were called 45 minutes after lights out for the opposite condition. A series of mixed-effects models were performed with fixed effects of test bout, condition, test bout × condition, and a random effect of participant. Covariates included pre-sleep baseline scores, randomization order, sex, and sleep history. Participants rated themselves as more alert and energetic in the light condition compared to the control condition (VASalert-sleepy p = .01; VASlethargic-energetic p = .001). There was no effect of condition for DST outcomes, but there was a significant improvement in DST total responses in the light condition in a subset of participants waking from N3 (p = .03). There was a significant effect of condition for PVT outcomes, with faster responses (p < .001) and fewer lapses (p < .001) in the control condition. Our results under naturalistic at-home settings suggest that, similar to the in-laboratory study findings, the light intervention improved subjective alertness and mood, while working memory improved after waking from N3. Future studies of light interventions should include measures of visual acuity and comfort to assess the full feasibility and efficacy of interventions in real-world environments.

sleep inertia↗
NASA NTRS2021

Decoding the effects of synonymous variants

Synonymous single nucleotide variants (sSNVs) are common in the human genome but are often overlooked. However, sSNVs can have significant biological impact and may lead to disease. Existing computational methods for evaluating the effect of sSNVs suffer from the lack of gold-standard training/evaluation data and exhibit over-reliance on sequence conservation signals. We developed synVep (synonymous Variant effect predictor), a machine learning-based method that overcomes both of these limitations. Our training data was a combination of variants reported by gnomAD (observed) and those unreported, but possible in the human genome (generated). We used positive-unlabeled learning to purify the generated variant set of any likely unobservable variants. We then trained two sequential extreme gradient boosting models to identify subsets of the remaining variants putatively enriched and depleted in effect. Our method attained 90% precision/recall on a previously unseen set of variants. Furthermore, although synVep does not explicitly use conservation, its scores correlated with evolutionary distances between orthologs in cross-species variation analysis. synVep was also able to differentiate pathogenic vs. benign variants, as well as splice-site disrupting variants (SDV) vs. non-SDVs. Thus, synVep provides an important improvement in annotation of sSNVs, allowing users to focus on variants that most likely harbor effects.

Zishuo Zeng↗
NASA NTRS2023

Orbital Debris Quarterly News, March 2023

- ISS Maneuver - NASA Releases HOOSF Update - Robert C. Reynolds Passes Away - Updates of the ES-MCAT for GEO Survey Operations - SpaceX Crew-4 Post-flight Inspection - Goldstone Measurements of the OD Environment: 2020-2021 - Meeting Reports - Upcoming Meetings - Plots - Space Missions and Satellite Box Score

Heather Mae Cowardin↗
NASA NTRS2018

On the Natural Structure of Amino Acid Patterns in Families of Protein Sequences

All known terrestrial proteins are coded as continuous strings of ≈20 amino acids. The patterns formed by the repetitions of elements in groups of finite sequences describes the natural architectures of protein families. We present a method to search for patterns and groupings of patterns in protein sequences using a mathematically precise definition for “repetition”, an efficient algorithmic implementation and a robust scoring system with no adjustable parameters. We show that the sequence patterns can be well-separated into disjoint classes according to their recurrence in nested structures. The statistics of the occurrences of patterns indicate that short repetitions are sufficient to account for the differences between natural families and randomized groups of sequences by more than 10 standard deviations, while contiguous sequence patterns shorter than 5 residues are effectively random in their occurrences. A small subset of patterns is sufficient to account for a robust ”familiarity” definition between arbitrary sets of sequences.

Pablo Turjanski↗
NASA NTRS2023

Leveraging Automated Fiber Placement Computer Aided Process Planning Framework for Defect Validation and Dynamic Layup Strategies

Process planning represents an essential stage of the Automated Fiber Placement (AFP) workflow. It develops useful and efficient machine processes based upon the working material, composite design, and manufacturing resources. The current state of process planning requires a high degree of interaction from the process planner and could greatly benefit from increased automation. Therefore, a list of key steps and functions are created to identify the more difficult and time-consuming phases of process planning. Additionally, a set of metrics must exist by which to evaluate the effectiveness of the manufactured laminate from the machine code created during the Process Planning stage. Layup strategies, in addition to dog ears, stagger shifts, steering constraints, and starting points, represented the group of functions labeled as process optimization and ranked the highest in terms of priority for automation. The laminates resulting from the selected parameters are evaluated through the occurrences of principal defect metrics such as fiber gaps, overlaps, angle deviation and steering violations. This document presents an automated software solution to the layup strategy and starting point selection phase of process planning. A series of ply scenarios are generated with variations of these ply parameters and evaluated according to a set of metrics entered by the Process Planner. These metrics are generated through use of the Analytical Hierarchy Process (AHP), where relative importance between each of the fiber features are defined. The ply scenarios are selected which reduce the overall fiber feature scores based on the defects the Process Planner wishes to minimize.

HiCAM↗
NASA NTRS2022

Precipitation Phase Determination by Brightness Temperatures From ATMS

Previous studies used the temperature-related variables from model outputs (e.g., 2-m temperature) for precipitation phase determination (i.e., rain–snow separation). This study presents a new idea for precipitation phase determination using brightness temperatures (TBs) from Advanced Technology Microwave Sounder (ATMS). It is found that TB-based phase discrimination shows comparable determination performance to that from model outputs over land. In contrast, TB-based phase discrimination over the ocean performs noticeably worse than that from model outputs. Further analyses reveal that the phase determination performance over land from TBs slightly depends on the satellite’s local zenith angle. However, the determination performance over the ocean strongly depends on the satellite’s local zenith angle, with the skill score decreasing sharply from 0.74 near the nadir to 0.55 near the edge. These results imply that over land, TBs may be used directly for phase determination, which can be extended to other operational and future microwave sounders with similar channels available.

Yalei You↗
NASA NTRS2023

The Earth in Living Color - NASA’s Surface Biology and Geology Designated Observable

The Surface Biology and Geology (SBG) Designated Observable will transform our understanding of the global land surface, inland and coastal aquatic ecosystems through visible-to-shortwave infra-red imaging (VSWIR) spectroscopy and thermal infra-red (TIR) imaging. SBG is one of four high-priority observables recommended in the 2017 NASA Earth Science Decadal Survey t o address science questions on vegetation and aquatic ecosystem health, snow-cover dynamics, volcanic activity, and minerology. With a planned launch readiness date of 2028, SBG is currently in Pre-Phase A, with Level 1 requirements being developed for a two-spacecraft architecture, including an additional constellation pathfinder. The recommended architecture emerged from an extensive study (2018-2021) that engaged the research and applications community to consider the science questions and measurement objectives of the Decadal Survey. A Science and Applications Traceability Matrix was used as a basis for scoring candidate architectures, with inputs from four working groups that covered algorithms, applications, calibration and validation, and modeling. Two pathfinder studies, Modeling End-to-End Traceability in support of SBG (MEET-SBG) and Space-based Imaging Spectroscopy and Thermal pathfindER (SISTER) are providing pre-launch modeling tools and data for algorithm development to support science value trades. The architecture consists of one spacecraft hosting a wide-swath VSWIR imaging spectrometer providing 30-m ground-sample distance (GSD), a spectral range of 380-2500 nm (at 10 nm resolution), 16-day revisit with 400 signal-to-noise for VNIR and 250 for SWIR (at 25% reflectance). A separate spacecraft will host a wide swath thermal imager, with five to seven bands placed between 4-12 μm), with 60-m (GSD), 3- day revisit, and 0.2K noise-equivalent differential temperature (NeDT). A VNIR compact camera will be hosted on the TIR spacecraft to enable coincident TIR and VNIR observations. A constellation pathfinder will evaluate options for enabling VSWIR mission continuity using Small Sats or data buys. Partnerships with international space agencies contribute technology as well as improvements to temporal revisit. SBG, when launched, will be the first dedicated mission collecting the full spectra of the Earth’s ‘living color’ and will play a critical role in NASA’s Earth System Observatory.

David S Schimel↗
NASA NTRS2023

UAM Instrument Flight Procedure Design and Evaluation in the Joby Flight Simulator

NASA’s Advanced Air Mobility (AAM) National Campaign (NC) partnered with Joby Aviation to test and evaluate different developmental candidate Urban Air Mobility (UAM) Instrument Flight Procedure (IFP) designs including new departure, enroute, approach and missed approach architectures using Joby’s high-fidelity engineering aircraft simulator. In conjunction with the simulator testing, this effort also evaluated related aspects such as charting, coding, and adherence to flight planning criteria. The test objectives were to assess the safety, efficiency, passenger comfort and noise of the different variations of the developmental IFPs. Safety-related measures include clearance from terrain and vertical obstructions, procedure flyability, and flight path conformance. Efficiency-related measures included time required, airspace volume required, and battery energy required. Passenger comfort and ride quality measures include roll/pitch angles, roll/pitch attitude change rates, and airspeeds prior to aggressive maneuvers, subjective pilot/passenger responses and acceleration forces. The noise impacts of the different IFPs will be interpolated/extrapolated using data from the simulator fed into a separate Joby acoustic software-based tool. Overall, several tradeoffs were identified and characterized between the different variations of the developmental IFP profiles. No single version of the developmental IFP structure scored highest across all measures listed above; rather, different IFP variations proved optimal for different measures, confirming that the best IFP depends on which specific measures are prioritized for a given aircraft, location and operation.

National Campaign↗
NASA NTRSDate not supplied

Digitizing Named Entities Found Within Letters of Agreement

Letters of Agreement (LOAs) are text-based air traffic control documents that contain procedures and actions agreed upon by the different parties, typically two or more FAA facilities, that are subject to an agreement. The documents contain among other things generic constraints, which are explicit and implicit combinations of procedures that limit a flight’s trajectory and affects pilot actions. For example, a controller may be required, to assign a specific altitude to an aircraft crossing the boundary between two airspaces. Although LOA generic constraints directly impact the trajectory of an aircraft, they are not currently available in a digital form that can be used for (or directly ingested into automated) flight planning. Instead, the constraints are manually input into an onboard or ground based system. LOA documents are primarily stored at a controlling facility and the generic constraints are implemented by experienced air traffic controllers and pilots primarily using voice instructions. This increases the workload of the controllers, likelihood of error (e.g., due to noisy communication) and makes it impractical for implementation with unmanned aircraft. Therefore, steps must be taken to make existing constraints machine interpretable to enable e.g., automated handoffs which in turn would reduce controller workload. With recent advances in natural language processing, especially the rise in digitization of text documents (e.g., medical documents) and automated extraction of information therein, it is now possible to extract flight specific constraints from LOAs. The goal of this work is to digitize named entities through a combination of natural language processing tasks: named entity disambiguation, toponym resolution, and numeric parsing to extract general constraint components contained within LOAs, herein referred to as Entity Enhancement (EE). Starting with a small list of named entities (e.g., ARTCC, Tower, Altitude and Speed), EE can extract the named entities while simultaneously converting the string-based output into a digital format using an ensemble of processes like rule-based gazetteers and syntactic-lexical patterns. The digital format contains a diverse set of information based on the entity label in question, ranging from standardized facility names to units of measure (e.g., feet) and other numeric information. Upon validating our approach using a truth dataset, we show an overall F1-Score of 0.71 for the extraction process. Looking beyond entity enhancement, we are also working towards the goal of completely digitizing the general constraints by performing EE and fitting them into a standardized exchange model (XM) such as the Aeronautical Information Exchange Model (AIXM). This will allow for easy distribution and dissemination of LOA constraints to air users, better searchability within documents, and enable ingestion into automated flight planning. Finally, we show a preliminary version of the proposed XM architecture and demonstrate how the model can be populated from the EE output.

Stephen S. B. Clarke↗
NASA NTRSDate not supplied

Predicting Airport Runway Configurations for Decision-Support Using Supervised Learning

One of the most challenging tasks for air traffic controllers is runway configuration management (RCM). It deals with the optimal selection of runways to operate on (for arrivals and departures) based on traffic, surface wind speed, wind direction, other environmental variables, noise constraints, and several other airport-specific factors. It affects the efficiency of the National Airspace System (NAS) and both surface and airspace operations can benefit from better understanding future runway configurations. In this paper, we present a comprehensive implementation of predictive models for runway configuration estimation from large volumes of historical data. Specifically, operational data from two full years (2018 and 2019) is collected, analyzed, and fused together to build the data product used in this work. The data set differs from prior work in the field in terms of its scope, resolution, and variety of factors collected and considered. Meteorological data is collected from two different sources – current weather conditions from METAR (Meteorological Terminal Aviation Routine Weather Report) and forecast weather conditions from Localized Aviation MOS Program (LAMP). Operational data from the Federal Aviation Administration (FAA) Aviation System Performance Metrics (ASPM) related to scheduled and actual number of arrivals and departures, average taxi times, etc. are collected. NASA’s Sherlock Data Warehouse is used to identify critical information such as go-arounds, and other events that might impact RCM decision-making. All data is collected and aggregated over 15-minute intervals throughout the two years. This provides a resolution like the timescales that might be necessary for runway configuration management decision-making. A variety of supervised learning algorithms are tested including Support Vector Machine, Random Forest, Gradient Boosting, etc. including tuning of the model hyperparameters. The modeling process is applied and presented on two representative U.S. airports – Charlotte Douglas International Airport (KCLT) and Denver International Airport (KDEN). The two airports present different levels of complexity in terms of the total number of configurations used and provide a balanced perspective on the generalizability of the developed approach to other airports in the NAS. Initial results are promising (F1 score of 0.91 at KCLT and 0.83 at KDEN) for data in the test set. The final paper will contain a comprehensive comparison between different models and model building strategies as well as further refined results. Most important predictors for each airport will be identified along with a discussion and recommendations on adapting the framework to other scenarios.

Tejas G Puranik↗
NASA NTRS2023

An Ensemble Neural Network Model for Predicting Rare-Earth Oxide and Silicate Heat Capacities at High Temperature

In this work, a neural network model was developed to predict the constant pressure heat capacity for materials in the rare-earth oxide—silica material space. Several model architectures were trained and tested on heat capacity data generated from first-principles density functional theory calculations. Hyperparameter optimization was performed, and the optimal model was selected for heat capacity predictions. The optimal model architecture was found to have a root-mean-squared error of 5.12 ± 3.37 J/mol-K. The optimal model architecture was then used in a bagging ensemble model trained using the leave-one-group-out method to provide error estimates for model predictions. The out-of-bag score for the ensemble model was 0.997. The predicted heat capacities agree well with the DFT and experimental results and were computed orders of magnitude faster than DFT simulations. Machine learning shows the potential to provide a suitable surrogate model for thermochemical property predictions for candidate environmental barrier coating materials but refining of input material features and model architectures could further improve accuracy for these models.

environmental barrier coatings↗
NASA NTRS2022

MLtool Python Code

Machine Learning (ML) is a subfield of Artificial Intelligence that gives computers the ability to learn from past data without being explicitly programmed. The predictive capabilities of ML models have already been used to facilitate several scientific breakthroughs. However, the practical application of ML is often limited due to the gaps in technical knowledge of its users. The common issue faced by many scientific researchers is the inability to choose the appropriate ML pipelines that are needed to treat real-world data, which is often sparse and noisy. To solve this problem, we have developed an automated Machine Learning tool (MLtool) that includes a set of ML algorithms and approaches to aid scientific researchers. The current version of MLtool is implemented as an object-oriented Python code that is easily extensible. It includes 44 different regression algorithms used to model data. MLtool helps users select the best model for their data, based on the scoring metrics used. Besides regression algorithms, MLtool also includes a suite of pre- and post-processing techniques such as missing value imputation, categorical variable encoding, input feature normalization, uncertainty quantification, exploratory data analysis (EDA), etc. MLtool was tested on several publicly available multi-dimensional data sets and was found capable of making accurate predictions.

Machine Learning↗