SEARCH · Search NASA

Results for “Logistic Regression”

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.

SourceResearch connectionFrom yearThrough year

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

At least 91 records · Page 5

All sources NASA NTRS DOE OSTI

NASA NTRS2020

Mitigating fatigue on the flight deck: how is controlled rest used in practice?

Controlled Rest (CR) refers to a short, voluntary nap opportunity taken by pilots on the flight deck as a countermeasure to unanticipated sleepiness in flight. This study explores the profile of CR use in a long-haul commercial airline. Forty-four pilots wore actiwatches and filled in an application-based sleep/work diary for approximately 2 weeks resulting in complete records from 239 flights. Timing of sleep periods and flight schedules were analyzed relative to home-base time. Pearson correlations were used to assess the influence of pilot demographics on CR use. A mixed-effects logistic regression was used to analyze the impact of schedule factors on CR. CR was taken on 46% (n=110) of flights, with 80% (n=106/133) of all CR attempts estimated by actigraphy to have successfully achieved sleep. Average sleep duration during successful rest periods was estimated as 31.7 ± 12.2 minutes. CR was more frequent on return (60%, n=71) vs. outbound flights (33%, n=39); 2-pilot (69%, n=83) vs. >2-pilot flights (23%, n=27); <10h (63%, n=80) vs. >10h duration flights (27%, n=30); and night (55%, n=76) vs. day flights (34%, n=34) (all p≤0.001). There was no significant difference for direction of travel (eastbound: 51%, n= 57; westbound: 40%, n= 44; p=0.059). Of note, 22% (n=26) of augmented flights contained both CR and bunk rest. Data from this airline show that CR is most commonly used as a countermeasure to sleepiness on flights <10h duration (2-pilot crews) and home-base nighttime flights. Future studies are required to determine the generalizability of these results to other airlines.

sleepiness↗

NASA NTRSDate not supplied

Exploring the Relationship Between Social Factors and Government Survey Nonresponse

In a previous study, we explored the relationship between economic and political factors and survey refusal, and noted the importance to collect or otherwise obtain measures that will help us understand more about the social aspect of the social-political-economic construct of survey nonresponse. Recently, we had the opportunity to collect such measures as part of the Census Tracking Survey. The Tracking Survey was launched in September 2019 and concluded in June 2020. It was a national survey conducted by the U.S. Census Bureau that tracked public awareness of the 2020 Census. Participants were asked about a variety of questions, including questions about social engagement and empathy, both possible measures of one’s social environment and hence one’s attitude towards participating in a government survey. To our knowledge, empathy has not been considered as factor of survey nonresponse. We propose that social factors such as these play an important role in the decision to participate in a survey. Using the Tracking Survey data, we built a logistic regression model, with plan to participate/participated in the 2020 Census as the dependent variable, and known and suspected factors of survey participation as independent variables. We found that social engagement and empathy were both important factors of participating in the Census.

Luke J. Larsen↗

NASA NTRS2019

Comparing Ice Jam Hindcasting Models with Tree Scar Data

Hindcasting models can use historic ice jam observations and hydroclimatic data to identify conditions that form ice jams.However, historic ice jam records are often sparse or incomplete. New sources of historic ice jam data could improve hindcasting models, leading to better ice jam forecasting and flood warning systems. Because ice jams damage riparian trees, marker rings associated with historic scars include information about ice jam frequency and severity. This study examined marker rings from 56 trees along the Muskegon River to supplement the historic ice jam data on this system. The study team compared tree ring data to results from hindcasting models, which were independently validated with newspaper reports on 1,500 separate days. Logistic regression converted the marker ring data into annual ice jam probabilities. Ice jam dates from the dendrochronology data were too noisy to train or validate a hindcasting model. However, the marker ring data did confirm that ice jams on the Muskegon are nonstationary. Ice jams are significantly more likely now than they were before 1966.The marker rings also helped to distinguish between false-negatives and nondetects in the hindcasting model.

Stanford Gibson↗

NASA NTRSDate not supplied

Classifying Agnostic Biosignatures using Raman, VNIR, and Elemental Data

How can we use our current wealth of terrestrial data, encompassing biogenic and abiogenic systems, to determine the distinguishing properties of life? SCOBI (Statistical Classification of Biosignature Information) uses machine learning techniques to algorithmically identify combinations of measurements that are “indicative of life”. A set of ~1000 observations, comprising elemental abundance, isotopic fractionation, VNIR reflectance, and (in progress) Raman spectra, have been assembled from existing literature and databases. The observations cover systems classified as “indicative alive” (e.g., cells, vegetation), “indicative non-alive” (e.g., fossils, teeth), “mixed indicative” (e.g., soil, pond water), or “non-indicative” (e.g., rocks, meteorites). VNIR data was preprocessed by linear interpolation from 400-2100 nm and smoothed with a Savitzky-Golay filter. To limit the amount of Earth-biochemistry-specific (non-agnostic) information included, the first five spectral features extracted were number of peaks, number of troughs, mean reflectance, mean peak width, and broadest peak width. To help further emphasize agnostic biosignatures, Earth-specific features such as chlorophylls have been manually flagged so that feature importance with and without them can be compared. Classifiers including k-nearest neighbors (KNN), Gaussian Naïve Bayes (GNB), logistic regression (LR), random forest (RF), and support vector machine (SVM) were implemented, as was a combination voting classifier. Performance metrics included false positive rates, false negative rates, and AUC with 50-50 test/train splits (Monte Carlo simulations). Key takeaways from this stage, prior to the inclusion of Raman spectra, are (1) the overall success rate of 0.933 AUC was most heavily influenced by the elemental abundance data; and (2) VNIR reflectance had the lowest classification performance with 0.52 AUC (58% of objects correctly classified). The next steps are to complete integration of Raman spectral data and to improve the approach to pre-processing and feature extraction for both types of spectral data, such as automated baseline removal, whole spectrum matching, and dimensionality reduction.

Biosignatures↗

NASA NTRSDate not supplied

Algorithmic Classification of Raman Spectra Biosignatures: Improving Life Detection Confidence

“Agnostic” biosignatures – indicators of life (or the absence of life), independent of a particular biochemistry – are increasingly considered a high standard for life detection. The Ladder of Life Detection (2018) called for investigating how combinations of independent and different potential biosignatures affect confidence. To address this gap, statistical classification of elemental abundances, isotopic fractionation, and reflectance spectroscopy (VNIR) has been implemented. Raman spectroscopy, highly desirable due to its wide availability, has the potential to improve this predictive power. This work implemented biosignature classification algorithms on Raman data alone, in preparation for combination with the other data types. Raman spectroscopy data was collected from published databases and papers as part of a manually curated dataset of “indicative” and “non-indicative of life” samples. These currently include 61 non-indicative samples (meteorites, magnetite); 3 indicative living samples (bacteria); 20 indicative non-living samples (chalk, bone); and 12 indicative mixed (with non-indicative material) samples (soil, microbial mats). Laboratory work is ongoing to characterize additional samples, particularly a greater breadth of mixed systems. Spectra were interpolated, filtered with the Savitzsky-Golay filter, and de-noised. For a preliminary examination, agnostic features were manually extracted including mean intensity, number of peaks, and mean peak width. Different peak prominences and filtering polynomials were used to refine features. Classification algorithms were implemented: k-nearest neighbors (KNN), logistic regression (LR), linear support vector machines (SVM), random forest (RF), Gaussian naïve bayes (GNB). Lastly, Monte Carlo simulations on 1,000 50%-train-test-splits were used to validate classification performance and feature significance. The preliminary feature set achieved its highest AUC of 0.52 with LR, with no strongly discriminatory features. Work to improve feature extraction, such as through deep learning with back propagation, is planned. In future work, the Raman data will be combined with the other data types, and potentially new data types such as enantiomeric excess. This project was partially supported through the NASA Ames Project EXcellence (APEX) incubator program.

Astrobiology↗

NASA NTRSDate not supplied

Controlled Rest: Investigating the Use of an In-Flight Sleepiness Countermeasure

INTRODUCTION: Sleepiness is commonly reported amongst commercial airline pilots and is recognized as a safety risk due to its impact on performance. Controlled Rest (CR) refers to a short, voluntary nap opportunity taken by pilots on the flight deck as a countermeasure to unanticipated sleepiness in flight. This study explores the profile of CR use in a long-haul commercial airline. METHODS: Forty-four pilots filled in an application-based sleep/work diary and wore actiwatches for approximately 2 weeks. Complete data sets from 239 flights including sleep diaries, actigraphy, and schedules were merged and analyzed. Sleep diary entries were used to set CR intervals in the actigraphy software, which was then used to predict sleep within these intervals. All time-stamps of sleep periods and flight schedules were adjusted for home-base time of the pilots. Pearson Correlations were used to assess the influence of pilot demographics on CR use. A mixed-effects logistic regression was used to analyze the impact of schedule factors on CR. RESULTS: Pilots reported taking CR on 46% (n=110) of observed flights. Average CR attempt duration was 43.1 ± 11.0 minutes. Eighty-percent (n=106/133) of all CR attempts were estimated by actigraphy to have successfully achieved sleep with an average sleep duration during successful rest periods of 31.7 ± 12.2 minutes. Captains reported taking CR on 38% of flights (n=39/102), compared to First Officers reporting 52% (n=71/137) of flights with CR (p=0.131). Age, experience, BMI, and sleep need were not associated with the percentage of flights with CR (all p>0.244). The following schedule factors were associated with a higher frequency of CR: night (55%, n=76) vs. day flights (34%, n=34); <10h (63%, n=80) vs. >10h duration flights (27%, n=30); return (60%, n=71) vs. outbound flights (33%, n=39); and 2-pilot (69%, n=83) vs. >2-pilot flights (23%, n=27) (all p≤0.001). There was a trend for more CR on eastbound flights, but this was not significant (eastbound: 51%, n= 57; westbound: 40%, n= 44; p=0.059). Of note, 22% (n=26) of augmented flights (>2-pilots) contained both CR and Bunk Rest (in a designated rest facility). DISCUSSION: Data from this airline show that pilots commonly use CR to mitigate sleepiness in-flight, especially on flights <10h duration and during home-base nighttime flights. Future studies are required to determine generalizability of these results to other airlines.

sleepiness↗

NASA NTRS2021

The Efficacy of Seasonal Terrestrial Water Storage Forecasts for Predicting Vegetation Activity Over Africa

Terrestrial water storage (TWS) provides important information on terrestrial hydroclimate and may have value for seasonal forecasting because of its strong persistence. We use the NASA Hydrological Forecast and Analysis System (NHyFAS) to investigate TWS forecast skill over Africa and assess its value for predicting vegetation activity from satellite estimates of leaf area index (LAI). Forecast skill is high over East and Southern Africa, extending up to 3–6 months in some cases, with more modest skill over West Africa. Highest skill generally occurs during the dry season or beginning of the wet season when TWS anomalies from the previous wet season are most likely to carry forward in time. In East Africa, this occurs prior to and during the transition into the spring “Long Rains” from January–March, while in Southern Africa this period of highest skill starts at the beginning of the dry season in April and extends through to the start of the wet season in October. TWS is highly and positively correlated with LAI, and a logistic regression model shows high cross-validation skill in predicting above or below normal LAI using TWS. Combining the LAI regression model with the NHyFAS forecasts, 1-month lead LAI predictions have high accuracy over East and Southern Africa, with reduced but significant skill at 3-month leads over smaller sub-regions. This highlights the potential value of TWS as an additional source of information for seasonal forecasts over Africa, with direct applications to some of the most vulnerable agricultural regions on the continent.

Terrestrial water shortage↗

NASA NTRS2021

Capturing the Footprints of Ground Motion in the Spatial Distribution of Rainfall-Induced Landslides

The coupled effect of earthquakes and rainfall is rarely investigated in landslide susceptibility assessments although it could be crucial to predict landslide occurrences. This is even more critical in the context of early warning systems and especially in cases of extreme precipitation regimes in post-seismic conditions, where the rock masses are already damaged due to the ground shaking. Here, we investigate this concept by accounting for the legacy of seismic ground shaking in rainfall-induced landslide (RFIL) scenarios. We do this to identify whether ground shaking plays a role in the susceptibility to post-seismic rainfall-induced landslides and to identify whether this legacy effect persists through time. With this motivation, we use binary logistic regression and examine time series of landslides associated with four earthquakes occurred in Indonesia: 2012 Sulawesi (M(sub w) = 6.3), 2016 Reuleut (M(sub w) = 6.5), 2017 Kasiguncu (M(sub w) = 6.6) and 2018 Palu (M(sub w) = 7.5) earthquakes. The dataset includes one co-seismic and three post-seismic landslide inventories for each earthquake. We use the peak ground acceleration map of the last strongest earthquake in each case as a predisposing factor of landslides representing the effect of ground shaking. We observe that, at least for the study areas under consideration and in a probabilistic context, the earthquake legacy contributes to increase the post-seismic RFIL susceptibility. This positive contribution decays through time. Specifically, we observe that ground motion is a significant predisposing factor controlling the spatial distribution of RFIL in the post-seismic period 110 days after an earthquake. We also show that this effect dissipates within 3 years at most.

Landslides↗

NASA NTRS2022

Deriving Severe Hail Likelihood from Satellite Observations and Model Reanalysis Parameters using a Deep Neural Network

Geostationary satellite imagers, such as those of the Geostationary Operational Environmental Satellite (GOES) series, have been observing severe convection at 15–60-minute intervals for over 40 years. When properly assessed, such a data record can be valuable in efforts of estimating severe storm risk throughout the diurnal cycle based on automated detection of patterns consistently found atop severe storms. Furthermore, environmental conditions favorable for severe weather are well-known and are thought to be represented well by modern reanalysis products. Promoting resilience against such hazards on local and global scales is a chief goal the NASA Disasters program, which seeks to encourage use of satellite observations to mitigate risk. For instance, hail is the costliest severe weather hazard across the globe in terms of insured loss, but reporting inconsistencies for hail events globally make it difficult to develop models that can quantify the risk. Satellite observation and model reanalysis taken together have the potential to, with reasonable skill and specificity, characterize environmental conditions that are favorable for hazardous weather, and thereby enable creation of hazard climatologie. Such climatologies are particularly useful over regions without extensive radar networks or storm reporting. By mapping the multivariate combination of observed cloud features and reanalysis environmental parameters/indices to United States Next Generation Weather Radar (NEXRAD) radar-estimated Maximum Expected Size of Hail (MESH) by way of a deep neural network (DNN), estimates of likelihood for potentially severe hail can be produced. Such estimates are of greater complexity and efficiency than could be performed with previous multivariate or logistic regression analyses for observed points within convective systems. Statistical distributions of convective parameters from satellite and reanalysis are shown to highlight non-severe/severe class separation for well-known hailstorm predictors, e.g., overshooting cloud top characteristics, deep-layer wind shear, mid-level stability, helicity, and convective inhibition. These complex, multivariate predictor relationships are exploited within a DNN, which can efficiently produce a quantitative hail risk metric with better than 70% detection rate and under 30% false alarms. These hail classifications can then be aggregated across the satellite record to yield a hazard climatology for hail frequency and severity – knowledge of which is of particular interest to those who manage risk (e.g., insurers) and are seeking opportunities to identify hail-prone regions, particularly in developing nations. This NASA study uses satellite observations and model parameters in a DNN to perform climatological hailstorm analysis in support of catastrophe model development, with the hope of promoting risk resilience particularly in regions without adequate weather radar coverage.

Passive Remote Sensing↗

NASA NTRSDate not supplied

Modeling approaches to estimate community annoyance due to sonic booms using data from repeated surveys

In an on-going project for NASA, we are developing a modeling approach to analyze the relationship between the noise level of sonic booms from an experimental supersonic plane and the level of annoyance measured through community response surveys. The goal of the project is to obtain a quantitative relationship between noise level and annoyance that is representative for the affected population. Particular modeling challenges include multiple annoyance measurements per survey respondent and very few occurrences of annoyance overall. To address these challenges, we propose a two-stage model for the presence of high annoyance, with the first stage modeling the probability that a respondent is ever highly annoyed and the second stage a multilevel logistic regression model for high annoyance based on noise level and demographic characteristics. We use a variation of Multilevel Regression and Poststratification (Gelman and Little, 1997) to obtain an overall representative noise-annoyance curve for the population. The approach is applied to data from a NASA pilot study.

Robyn Ferg↗

NASA NTRS2022

Sea Level Rise and City-Level Climate Action

Background: Climate change is the greatest threat to global health in the 21st century. Rising sea levels are one particularly concerning manifestation of this and many of the world’s largest cities are vulnerable to sea level rise (SLR). Thus, urban climate adaptation and mitigation policies are increasingly important to protect population health. Objectives: This study aimed to determine whether being at risk of SLR was associated with city-level climate action. It also aimed to assess the wider drivers of climate action in cities, in order to guide ongoing efforts to motivate climate action, assess public health preparedness and identify research gaps. Methods: This is an ecological cross-sectional study using secondary data from CDP, the Urban Climate Change Research Network (UCCRN), World Bank, United Nations Cities and EM-DAT (Emergency Events Database). The study population consisted of 517 cities who participated in CDP’s 2019 Cities Survey. Multivariable logistic regression was utilized to assess the relationship between risk of SLR and city-level climate action, and secondly, to assess the wider determinants of city-level climate action. Results: There was evidence of crude associations between risk of SLR and three outcome variables representing city-level climate action. However, after adjusting for confounding variables, these crude associations disappeared. World region, national income status and urban population were shown to be stronger predictors of city-level climate action. Conclusion: It is concerning for population health that there is no association demonstrated between risk of SLR and climate action. This could indicate a lack of awareness of the risks posed by SLR within urban governance. To fulfil their health protection responsibilities, it is essential that public health professionals take a leading role in advocating for climate action.

sea level rise↗

NASA NTRS2022

Simulation and Application of Bayesian Dose Uncertainty Modeling for Low-Boom Community Noise Surveys

In dose-response modeling, failing to account for dose uncertainty can cause artificial flattening of the estimated slope of the dose-response curve. Previous analyses of NASA sonic boom community noise survey data utilized a Bayesian multilevel logistic regression model, which did not account for dose uncertainty. The current work extends the model to account for either classical or Berkson dose uncertainty. The extended model is applied to two simulated dose-response datasets to illustrate conditions under which the dose uncertainty term does and does not correct for the artificial flattening introduced by dose uncertainty. Finally, the extended model is applied to two previous NASA sonic boom community noise surveys. The resulting dose-response curve slope for the average participant is 5 to 10% steeper, but the difference in the noise dose that elicits a 5% highly annoyed response is small (less than 1 dB). The difference remains insignificant when producing population summary dose-response curves. Commentary is included on applicability to future X-59 low-boom community noise survey data modeling and analysis.

X-59↗

NASA NTRS2022

Comparison of Likelihood Methods for Generalized Linear Mixed Models with Application to Quiet Supersonic Flights 2018 Data

Repeated measurement will be a feature of the survey data collected during the Quesst missionX-59 community response tests (CRT). Since each participant will report his or her categorical level of annoyance in response to multiple events, the responses from any single individual may be correlated with one another. Several models within the class of generalized linear mixed models (GLMM) are pertinent to the analysis of correlated categorical outcomes; the random intercept logistic regression model is one example. Both Bayesian and frequentist methods for fitting these models are available, with frequentist methods relying on some form of approximation (of either an integral or the integrand) that appears in the marginal likelihood function. Given several anticipated similarities of the X-59 CRT data to data collected during a past risk reduction, Quiet Supersonic Flights 2018 (QSF18), this short note is intended to create awareness. It documents an instance in which a reported population average dose-response relationship derived from QSF18 single event data was distorted by the integral approximation applied in likelihood-based methods. We review some of the available literature on the topic, compare the outputs of several different computational approaches implemented in available statistical software, and present simple corrective actions that may be useful during the Quesst mission.

dose-response model↗

NASA NTRSDate not supplied

Modeling Approaches to Estimate Community Annoyance Due to Sonic Booms Using Data from Repeated Surveys

Robyn Ferg↗

NASA NTRSDate not supplied

Effects of Dose Error and Sample Size on Sonic Boom Dose-response Curves

NASA will soon be collecting noise-annoyance community survey data as the X-59 aircraft flies supersonically over several communities in the USA. Sparse measurements of the X-59 sonic thumps will be used together with physics-based simulations to estimate noise doses at survey participant locations. These dose estimates have associated error that affects the accuracy of modeled dose-response curves, which can result in misestimation of annoyance. The precision in dose-response curves is also a consideration in selecting the number of survey participants. To enable pretest studies of dose error and precision, simulated dose-response data were generated based on NASA’s Quiet Supersonic Flights 2018 test. The data included various degrees of dose error and sample size. Frequentist multilevel logistic regression models were fit to the true and perturbed dose-response data. Simple proportional relationships were identified between the model parameters and the perturbation standard deviation. The summary dose-response curves illustrate the impact on accuracy if dose error is not accounted for in the model. The precision in the dose-response curves is also shown as the number of participants and degree of participation is varied. Finally, sampling variability is illustrated by showing the dose-response curves for several replicates with random draws of participants and errors.

X-59↗

NASA NTRSDate not supplied

Effects of Dose Error and Sample Size on Sonic Boom Dose-Response Curves

X-59↗

NASA NTRSDate not supplied

Statistical Classification of Biosignature Information using Multiple Instrument Observations

The accurate identification of biosignatures (indications of life) from data taken from remote or in situ planetary exploration is one of the most important challenges in astrobiology, the interdisciplinary field examining habitability and the potential for extraterrestrial life. This study employs machine learning algorithms to optimize the identification of biosignatures, with an emphasis on those which are agnostic to a specific biochemical basis. We exploit the wealth of terrestrial data available from biogenic and abiogenic systems to enhance efficient feature prioritization. Our dataset, pulled from public databases and laboratory recorded measurements, includes elemental abundance, isotopic fractionation, and VNIR/Raman spectra The data curation process included standardization for detection limits and ranges. Subsequent feature extraction yielded detailed inputs for machine learning, including combinations of elemental content, isotopic ratios, and parameters of spectral peaks and troughs. Feature significance was evaluated across diverse machine learning methodologies, such as k-nearest neighbors, logistic regression, Random Forest, support vector machines, and Gaussian Naïve Bayes, along with a combined voting classifier. We utilized Receiver Operating Characteristic Area Under the Curve (ROC AUC) across 2,000 50% test-train splits as a robust metric of model performance. Results revealed a promising ROC AUC of 0.853 for the combined voting classifier. Removing elemental abundance data notably reduced model accuracy (13% decrease in AUC), highlighting its critical role in biosignature detection. Several other individual data features exhibited significance within their respective data types, offering additional granularity. This research fortifies the relevance of machine learning to astrobiology, potentially enhancing life detection missions by allowing algorithmic prioritization of high-interest samples for further investigation. Future work will refine data standardization, expand the dataset to include more terrestrial systems, and incorporate convolutional neural networks for spectral feature extraction. The potential for public data sharing is also under exploration, reinforcing our commitment to collective scientific advancement.

Statistical↗

NASA NTRSDate not supplied

Document Classification Techniques for Aviation Letters of Agreement

Often when working with technical documents, it is helpful to classify them into specific categories. In this paper, we conduct a thorough review of natural language processing techniques to perform this classification task on Letters of Agreement (LOAs), technical aviation documents outlining rules for utilizing US airspace. We evaluate multiple techniques, including Transfer Learning, for representing the text in the documents as embeddings: unigram and bigram Term Frequency Inverse Document Frequency (TFIDF), Word2Vec, Doc2Vec, GloVe and RoBERTa. We investigate a wide range of classification models: K-Nearest Neighbors, Random Forest, Support Vector Machines (SVM), Logistic Regression, Naive Bayes, Feed-Forward Neural Network, Convolutional Neural Networks (CNNs) and Long-Short Term Memory (LSTM). By comparing the different methods, we found the best overall approach for our task was to use unigram TFIDF representations with SVM while also gaining insight into how the other methodologies performed on a small technical datasets.

Aayushi Batra↗