SEARCH · Engineering Papers
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.
This document describes the Impeded (ITOM) and Unimpeded Taxi Out Time Prediction Model (UTOM) Machine Learning (ML) services developed under the ATD-2 subproject as a reference implementation and released by NASA as Open Source software on github.
Drought is one of the most ecologically and economically devastating natural phenomena affecting the United States, causing the U.S. economy billions of dollars in damage, and driving widespread degradation of ecosystem health. Many drought indices are implemented to monitor the current extent and status of drought so stakeholders such as farmers and local governments can appropriately respond. Methods toforecast drought conditions weeks to months in advance are less common but would provide a more effective early warning system to enhance drought response, mitigation, and adaptation planning. To resolve this issue, we introduce DroughtCast, a machine learning framework for forecasting the United States Drought Monitor (USDM). DroughtCast operates on the knowledge that recent anomalies in hydrology and meteorology drive future changes in drought conditions. We use simulated meteorology and satellite observed soil moisture as inputs into a recurrent neural network to accurately forecast the USDM between 1 and 12 weeks into the future. Our analysis shows that precipitation, soil moisture, and temperature are the most important input variables when forecasting future drought conditions. Additionally, a case study of the 2017 Northern Plains Flash Drought shows that DroughtCast was able to forecast a very extreme drought event up to 12 weeks before its onset. Given the favorable forecasting skill of the model, DroughtCast may provide a promising tool for land managers and local governments in preparing for and mitigating the effects of drought.
This document describes the Estimated ON Model (EON) Machine Learning (ML) services developed under the ATD-2 subproject as a reference implementation and released by NASA as Open Source software on github.
We summarize the first exploratory investigation into whether Machine Learning (ML) techniques can augment science strategic planning. We find that an approach based on Latent Dirichlet Allocation (LDA) using abstracts drawn from high-impact astronomy journals may provide a leading indicator of future interest in a research topic. We show two topic metrics that correlate well with the high-priority research areas identified by the 2010 National Academies’ Astronomy and Astrophysics Decadal Survey. One metric is based on a sum of the fractional contribution to each topic by all scientific papers (“counts”) while the other is the Compound Annual Growth Rate (CAGR) of counts. These same metrics also show the same degree of correlation with the whitepapers submitted to the same Decadal Survey. Our results suggest that the Decadal Survey may under-emphasize fast growing research. A preliminary version of our work was presented by Thronson et al. (2021).
INTRODUCTION We use artificial neural networks (ANNs) as an example machine learning (ML) tool to predict the cognitive performance impairment of rats induced by irradiation. The experimental data in the analyses is attentional set-shifting (ATSET) test scores from a rodent model exposed to ≤15 cGy of individual galactic cosmic radiation (GCR) ions: 4He, 28Si, or 56Fe, expected for a Lunar or Mars mission [1]. This work investigates rats at a subject-based level and uses applied dose and performance scores taken before irradiation to predict whether a rat will be impaired when irradiated. The results of this study are significant to crewed space missions as they support the potential of predicting an astronaut’s impairment in a specific task before spaceflight through the implementation of appropriately trained ML tools. METHODS Data used in this work are scores from the ATSET, a multi-stage constrained cognitive flexibility test [2]. Our computational model utilizes the number of attempts to reach the criterion to pass a stage as a behavioral performance measure for rats. We use the post-irradiation scores, generate thresholds from cumulative distribution plots of non-irradiated rats, and calculate the percent of irradiated rats whose scores fall below the threshold to infer how each radiation type/dose affects a population. Rats scoring above the threshold are labeled impaired while the others are non-impaired. We then employ ANNs as a typical ML technique, and use each subject’s individual scores taken before radiation along with the applied dose, to predict their personal susceptibility to cognitive impairment due to space radiation exposure. RESULTS AND CONCLUSION A significant finding is the exhibition of a dose-dependent increasing probability of impairment for 1 to 10 cGy of 28Si or 56Fe in the simple discrimination (SD) stage of the ATSET, and for 1 to 10 cGy of 56Fe in the compound discrimination (CD) stage. On a subject-based level, implementing ML classifiers such as ANNs identifies rats that have a higher tendency for impairment after GCR exposure [1]. The receiver operating characteristic (ROC) and the precision-recall (PR) curves of the ML models show a better prediction of impairment when 56Fe is the ion in question in both SD (Figure 1) and CD stages. They, however, do not depict impairment due to 4He in SD (Figure 1) and 28Si in CD, suggesting no dose-dependent impairment response in these cases. In this work, “good” prediction pertains to “better-than-random-chance”, due to the limited sample size and the high inter- and intra-individual variabilities in response to brain stimulation paradigms, as applicable to both animals and humans. More behavioral tests and biomarkers should be investigated on the same subjects, to be fed to the ML models to capture the agents responsible for performance alterations of some individuals versus others.
Cyanobacterial harmful algal blooms are an increasing threat to coastal and inland waters. These blooms can be detected using optical radiometers due to the presence of phycocyanin (PC) pigments. The spectral resolution of best-available multispectral sensors limits their ability to diagnostically detect PC in the presence of other photosynthetic pigments. To assess the role of spectral resolution in the determination of PC, a large ( N=905 ) database of colocated in situ radiometric spectra and PC are employed. We first examine the performance of selected widely used machine-learning (ML) models against that of benchmark algorithms for hyperspectral remote sensing reflectance ( R_(rs) ) spectra resampled to the spectral configuration of the Hyperspectral Imager for the Coastal Ocean (HICO) with a full-width at half-maximum (FWHM) of < 6 nm. Results show that the multilayer perceptron (MLP) neural network applied to HICO spectral configurations (median errors < 65%) outperforms other ML models. This model is subsequently applied to R_(rs) spectra resampled to the band configuration of existing satellite instruments and of the one proposed for the next Landsat sensor. These results confirm that employing MLP models to estimate PC from hyperspectral data delivers tangible improvements compared with retrievals from multispectral data and benchmark algorithms (with median errors between ∼73 % and 126%) and shows promise for developing a globally applicable cyanobacteria measurement approach.
Qualification and certification of safety critical parts is a hurdle to the adoption of metallic additively manufactured components for aerospace vehicle applications. Challenges include variability in part properties due to inconsistent defect distribution and microstructure. Understanding of the process through finite element modeling (FEM), and process control through in-situ monitoring, may result in significant improvements; however, solutions useful to manufacturers will require large volumes of data and automated data utilization. Toward this end, a generalizable automated FEM calibration paradigm is developed. This paradigm leverages existing and novel tools from machine learning and uncertainty quantification to enable the automatic calibration of FEMs without requiring prior knowledge of the model performance across input parameter space, including meshing and solver settings, which can require time consuming manual model probing or cause noisy and inconsistent predictions. The result is a probabilistic distribution of calibrated and validated FEM input parameters targeting measured data.
Limited sample sizes, high data dimensionality, and sensitivity to technical and biological variability of next generation sequencing (NGS), has typically limited machine learning (ML) in space studies and further study of radiation effects. However, pooling smaller studies while addressing intra- and inter-study variabilities allows for ML predictive modeling. Here, integration methods were applied to whole transcriptome shotgun sequencing (RNAseq) data from 6 mouse liver GeneLab datasets (GLDS) with a total of 113 spaceflight and ground-control samples to determine top features relevant to spaceflight including the effect of radiation exposure. Data was normalized within each study, then merged and scaled across all datasets. Data dimensionality was reduced using a minimum redundancy maximum relevance (MRMR) methodology. The top MRMR features were used to predict spaceflight vs. ground-control samples using a Random Forest (RF) classifier with 5-fold cross validation (CV). The ML-based gene sets were further compared against differential gene expression results from individual GLDS. CV training using the top 100 MRMR genes show averages of 86% accuracy and 0.95 AUC value on the validation set over 5 folds (Figure 1A). Baseline set analysis on differentially expressed genes (DEGs) identified using padj ≤ 0.05 show 811 or 68 DEGs overlapping between at least 2 or 3 studies, respectively (Figure 1B). Over-representation analysis showed overlapping biological processes related to fatty acid and lipid metabolism. Set analysis between the MRMR features and the DEGs showed 60 or 8 genes overlapping with at least 1 or 2 studies, respectively. MRMR feature selection and ensemble ML methods (e.g. RF) improve performance relative to a Naïve Bayes classifier when NGS data sets are analyzed. A challenge of applying ML methods across heterogeneous NGS data is accounting for signal:noise ratio. Here, signal validation across studies was shown by intersecting sets between top MRMR genes and DEGs from RNASeq analysis. Non-intersecting sets introduce opportunity to explore spaceflight relevant genes and implementing ML methods across existing NGS datasets may overcome sample size limitations. ML coupled with existing analytical methods enhances understanding of disease by revealing common underlying pathways across datasets.
Arc jet Computer Vision (ArcjetCV) is a software application built to automate analysis of arc jet ground test video footage. This includes tracking material recession, sting arm motion, and the shock-material standoff distance. This provides a new capability to resolve and validate new physics associated with non-linear processes. This is an essential step to reduce testing, modeling, and validation uncertainties for heatshield material performance. ArcjetCV uses several types of machine learning (convolutional neural net: CNN, decision tree: DT, k-means unsupervised clustering: KM) to automate the video processing pipeline. These include inferring the start/stop of time segments of interest (1D CNN), measuring the time-dependent 2D recession of the material samples (2D CNN, DT), measuring the time-dependent shock standoff distance (2D CNN, DT), and post-processing cleaning of the recession data (KM). The software also provides a graphical user interface for ease of use. The results of using this tool on arc jet videos show non-linear time-dependent effects can be important for certain materials.
The imprecise nature of three-dimensional (3D) printing limits the technology’s use beyond prototyping. For production of end-use parts, such as those for aerospace applications, improvements are needed to enhance quality and repeatability. Much of the difficulty in obtaining high quality printed parts lies in finding optimum printing parameters. Currently, this requires trial and error performed by an expert. Finding the optimum printing parameters is also obfuscated by the variation in optimum parameters throughout the part due to part geometry and printer effects. To allow for locally optimized printing parameters, one can envision a machine learning algorithm that could take in an object, predict the best printing parameters, and communicate these parameters to a printer. With this scenario in mind, we developed a tool that can predict and implement locally optimized printing parameters in 3D printing. This tool consists of elements designed to detect errors in a printed part, predict the probability of local flaws occurring at each point in the part, and select the optimal local parameters for the highest quality part given hardware limitations. The results of this work were highlighted in Advanced Materials Technologies. In this paper, we will discuss in greater depth the workflow and algorithms involved with this tool that were not detailed in the journal publication.
- NASA SPoRT introduced the "Dust RGB" via NASA satellites to demonstrate GOES-R ABI capabilities and then evaluated the impact in operations (Fuell et al. 2016) - The Dust RGB allows for continued dust detection at night, but the cooling ground surface limits the effectiveness as night progresses. - SPoRT has developed a 'Machine Learning' (ML) model using a physically-based approach which can correctly label 85% of dust pixels and 99% of no-dust pixels
This research proposes a natural language processing enabled risk analysis framework, named Hazard Extraction andAnalysis of Trends (HEAT), and applies the framework to the ICS-209-PLUS data set of wildfire incident responseforms. The HEAT framework produces safety- and risk- relevant analyses, consisting of: (1) a set of hazards extractedfrom text data, (2) a primary analysis using hazard-relevant metrics, such as rate and severity, to form an FMEA-styletable and risk matrix, (3) a time series analysis of metric trends, and (4) a secondary analysis examining potentialpredictors for hazards. Results from HEAT provide quantitative risk-relevant information for high-level hazards doc-umented in existing-state operations. Because of the generalizability of the steps and limited data requirements, HEATcan be applied to any dataset containing narrative text, thus providing a framework for data-driven machine learning-enabled quantitative risk analysis across a variety of domains. To demonstrate HEAT in a case study, we apply theframework to the ICS-209-PLUS dataset of wildland fire incident response forms. Hazards identified in wildfire re-sponse arise from environmental conditions, the mission, and the wildland urban interface. The resulting risk matrixidentifies evacuations as high-risk hazards, while all other identified hazards are medium or serious risk.
Aerosol-cloud interactions have a potentially large impact on climate, but are poorly quantified and thus contribute a significant and long-standing uncertainty in climate projections. The impacts derived from climate models are poorly constrained by observations, because retrieving robust large-scale signals of aerosol-cloud interactions are frequently hampered by the considerable noise associated with meteorological co-variability. The Iceland-Holuhraun effusive eruption in 2014 resulted in a massive aerosol plume in an otherwise near-pristine environment and thus provided an ideal natural experiment to quantify cloud responses to aerosol perturbations. Here we disentangle significant signals from the noise of meteorological co-variability using a satellite-based machine-learning approach. Our analysis shows that aerosols from the eruption increased cloud cover by approximately 10%, and this appears to be the leading cause of climate forcing, rather than cloud brightening as previously thought. We find that volcanic aerosols do brighten clouds by reducing droplet size, but this has a significantly smaller radiative impact than changes in cloud fraction. These results add substantial observational constraints on the cooling impact of aerosols. Such constraints are critical for improving climate models, which still inadequately represent the complex macro-physical and micro-physical impacts of aerosol-cloud interactions.
Developed a data pipeline utilizing a commercial Machine Learning platform to potentially improve the speed in which recommendations are made for continued use of EMU gloves on ISS; demonstrating the use of ISS as a testbed for further, deep space applications.
The emergence of Advance Air Mobility (AAM) will increase the number and types of aerial vehicles operating in shared airspaces, which will subsequently affect the amount of actionable data that ground control station operators (GCSOs) will be expected to manage. In this environment, GCSOs are particularly susceptible to the visual perceptual phenomenon known as change blindness, in which a stimulus undergoes a change without the change being noticed by its observer. A machine agent designed to detect change blindness and mitigate the effects could improve human agent performance in a data-saturated remote operations environment. The objective of this paper is to describe a proof-of-concept system architecture that integrates real-time eye tracking and vehicle telemetry data to prevent human-agent errors resulting from change blindness while operating aircraft from a remote ground control station (GCS).
When developing the aerodynamic databases for use in trajectory simulations, it is important to develop a system of metrics to qualify which aerodynamic models are best to use. Since aerodynamics are just one input into trajectory simulations, the results of these simulations do not reflect on the quality of the aerodynamic database used. This means that aerodynamic database comparisons must be done offline. While traditional metrics that focus on mean/nominal predictions are a good first step, more robust estimates of the prediction interval become important as more focused uncertainty models are developed. We explore the limitations of evaluating aerodynamic models based purely on nominal-centered response surfaces. Before elaborating and evaluating metrics based on distributed models, the value of evaluating prediction interval and confidence interval are discussed to conclude that prediction intervals are more relevant to the use of trajectory analysis. Several metrics to evaluate the prediction interval are introduced with a focus on the standard calibration metric. Finally, we compare candidate models using both mean and distributed metrics. A finalized candidate model developed using state of the art machine learning methods is compared to a baseline model developed using traditional aerodynamic database modeling techniques.
The emergence of Advance Air Mobility (AAM) will increase the number and types of aerial vehicles operating in shared airspaces, which will subsequently affect the amount of actionable data that ground control station operators (GCSOs) will be expected to manage. In this environment, GCSOs are particularly susceptible to the visual perceptual phenomenon known as change blindness, in which a stimulus undergoes a change without the change being noticed by its observer. A machine agent designed to detect change blindness and mitigate the effects could improve human agent performance in a data-saturated remote operations environment. The objective of this paper is to describe a proof-of-concept system architecture that integrates real-time eye tracking and vehicle telemetry data to prevent human-agent errors resulting from change blindness while operating aircraft from a remote ground control station (GCS).
Anthropogenic climate change is expected to alter drought risk in the future. However, droughts are not uncommon or unprecedented, as documented in tree-ring-based reconstructions of the summer average Palmer drought severity index (PDSI). Using an unsupervised machine-learning method trained on these reconstructions of pre-industrial climate, we identify outliers: years in which the spatial pattern of PDSI is unusual relative to ‘normal' variability. We show that in many regions, outliers are more frequently identified in the twentieth and twenty-first centuries. This trend is more pronounced when the regional drought atlases are combined into a single global dataset. By definition, outlier patterns at the 10% level are expected to occur once per decade, but from 1950 to 2000 more than 6 years per decade are identified as outliers in the global drought atlas (GDA). Extending the GDA through 2020 using an observational dataset suggests that anomalous global drought conditions are present in 80% of years in the twenty-first century. Our results indicate, without recourse to climate models, that the world is more frequently experiencing drought conditions that are highly unusual in the context of past natural climate variability.