SEARCH · Engineering Papers

Results for “Cross-validation”

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 NTRS2021

Weekly Mapping of Sea Ice Freeboard in the Ross Sea from ICESat-2

NASA’s ICESat-2 has been providing sea ice freeboard measurements across the polar regions since October 2018. In spite of the outstanding spatial resolution and precision of ICESat-2, the spatial sparsity of the data can be a critical issue for sea ice monitoring. This study employs a geostatistical approach (i.e., ordinary kriging) to characterize the spatial autocorrelation of the ICESat-2 freeboard measurements (ATL10) to estimate weekly freeboard variations in 2019 for the entire Ross Sea area, including where ICESat-2 tracks are not directly available. Three variogram models (exponential, Gaussian, and spherical) are compared in this study. According to the cross-validation results, the kriging-estimated freeboards show correlation coefficients of 0.56–0.57, root mean square error (RMSE) of ~0.12 m, and mean absolute error (MAE) of ~0.07 m with the actual ATL10 freeboard measurements. In addition, the estimated errors of the kriging interpolation are low in autumn and high in winter to spring, and low in southern regions and high in northern regions of the Ross Sea. The effective ranges of the variograms are 5–10 km and the results from the three variogram models do not show significant differences with each other. The southwest (SW) sector of the Ross Sea shows low and consistent freeboard over the entire year because of the frequent opening of wide polynya areas generating new ice in this sector. However, the southeast (SE) sector shows large variations in freeboard, which demonstrates the advection of thick multiyear ice from the Amundsen Sea into the Ross Sea. Thus, this kriging-based interpolation of ICESat-2 freeboard can be used in the future to estimate accurate sea ice production over the Ross Sea by incorporating other remote sensing data.

Satellite altimeter↗

NASA NTRSDate not supplied

Variance Decomposition of MEDLI2 Reconstructed Heating Using Neural Networks

The Mars Entry, Descent, and Landing Instrumentation (MEDLI2) sensor suite collected data during entry of the Mars 2020 Perseverance rover into Mars’ atmosphere. This suite included a network of MEDLI2 Instrumented Sensor Plugs (MISPs). Each MISP was comprised of a cylinder made of Thermal Protection System (TPS) material with 1-3 embedded thermocouples (TCs), and it was flush mounted into the heatshield or backshell. Data from these in-depth TCs were used to reconstruct the aeroheating environment of the vehicle throughout entry. Surface heating was posed as an inverse problem, with the goal of estimating the surface heating by minimizing an objective function of the difference between MISP temperature measurements during flight and the temperature predictions derived from the Fully Implicit Ablation and Thermal response (FIAT) program. Given an aerothermal environment, FIAT calculates the material response and provides in-depth temperatures throughout the TPS material. To achieve the reverse, an internal tool called FIAT_Opt runs through multiple different environments until the output temperature at the TC depth closely matches the flight data. 95% confidence intervals on the reconstructed surface heating were obtained using Monte Carlo analysis, in which uncertainties in the thermocouple depth and the TPS material properties (e.g., density, thermal conductivity, heat capacity, emissivity) based on flight-lot material testing were included. A variance decomposition method using Sobol indices was employed to assess the sensitivity of the reconstructed peak heating to the TC placement and material property uncertainties. Variance decomposition was found to require tens of thousands of FIAT_Opt runs in order for the Sobol indices to converge. With a single FIAT_Opt run taking on the order of 40 minutes, the required number of computations would take months to complete, even if using multiple CPUs. To mitigate this problem, three machine learning models (ridge regression with cross-validation, random forest regression, and a deep neural network) were trained and tested using the 2000 Monte Carlo runs that were already completed. A subset of 1600 runs were used to train the model (i.e., training set), while the remaining 400 runs were used as the test set. The predictions from the deep neural network (DNN) on the test set showed nearly perfect agreement to the actual values computed with FIAT_Opt (R2 > 0.99). Using the DNN as a surrogate model, the variance decomposition using 50,000 runs was completed within minutes. The resulting Sobol indices showed that the reconstructed peak surface heating was most sensitive to the uncertainties in the thermal conductivity (ST = 0.37) and heat capacity (ST = 0.26). This method can be leveraged to provide requirements for material property measurements needed to improve the accuracy of surface heating prediction and ultimately lead to the reduction of design margins in the future. This presentation will include background on the MEDLI2 suite; the method used for inverse heating estimation; the way that material property uncertainties were accounted for using Monte Carlo analysis; a brief background on variance decomposition; the motivation for using machine learning in this context; how a neural network was trained on the data to enable variance decomposition in a fraction of the time; and the variance decomposition results for one of the MISPs.

Hannah Alpert↗

NASA NTRS2022

Combining Machine Learning and Numerical Simulation for High-Resolution PM2.5 Concentration Forecast

Forecasting ambient PM2.5 concentrations with spatiotemporal coverage is key to alerting decision-makers of pollution episodes and preventing detrimental public exposure, especially in regions with limited ground air monitoring stations. The existing methods either rely on chemical transport models (CTMs) to forecast spatial distribution of PM2.5 with nontrivial uncertainty or statistical algorithms to forecast PM2.5 concentration time-series at air monitoring locations without continuous spatial coverage. In this study, we developed a PM2.5 forecast framework by combining the robust Random Forest algorithm with a publicly accessible global CTM forecast product – NASA’s Goddard Earth Observing System “Composition Forecasting” (GEOS-CF), providing spatiotemporally continuous PM2.5 concentration forecasts for the next five days at a 1-km spatial resolution. Our forecast experiment was conducted for a region in Central China including the populous and polluted Fenwei Plain. The forecast for the next two days had overall validation R2 of 0.76 and 0.64, respectively; the R2 was around 0.5 for the following three forecast days. Spatial cross-validation showed similar validation metrics. Our forecast model, with validation normalized mean bias close to zero, substantially reduced the large biases in GEOS-CF. The proposed framework requires minimal computational resources compared to running CTMs at urban scales, enabling near-real-time PM2.5 forecast in resource-restricted environments.

PM2.5↗

NASA NTRS2022

Hybrid Model Based Approaches for Systems Health Management and Prognostics

This is a previously approved and published presentation. To accurately predict the future state of any system, it is required to possess knowledge of its current health state and future operational conditions. Present achievements of data-driven algorithms in regression of complex nonlinear functions and classification tasks have generated a growing interest in artificial intelligence for industrial applications. Complex multi-physics models as well as digital twins, once purely built on physics and corresponding simplified lumped parameter iterations, can now benefit from machine learning algorithms to mitigate the lack of understanding of some complex behavior. Given models of the current and future system behavior, a general approach of model-based prognostics can solve the prediction problem and further decision-making. In principle, data-driven approaches can replace expensive experimental test-setups as well as reduce the number of simulations needed to explore, e.g., the parametric space of a multi-parameter model. Nonetheless, the limitations of pure data-driven methods came to light rather quickly, at least for some industries. In many industrial applications, data acquisition is costly, and the volume of data that can be collected does not satisfy the requirements for effective model training and cross-validation. Therefore, some recent works in the area of machine learning is focusing on blending physics with data-driven algorithms, thus mitigating the drawbacks of the two approaches and emphasizing respective advantages. Partial physical knowledge of the problem can aid the learning process by “guiding” the algorithm towards efficient solutions that satisfy the physics driving the system behavior. The result is a hybrid modeling approach combining physical knowledge as well data-driven methods to develop a unified hybrid approach. A hybrid framework for fusing information from physics-based performance models along with deep learning algorithms for prognostics of complex safety-critical systems is presented. In this framework, physics-based performance models infer unobservable model parameters related to the system's components health solving a calibration problem in the deep learning approach.

Prognostics↗

NASA NTRS2022

Estimating groundwater use and demand in arid Kenya through assimilation of satellite data and in-situ sensors with machine learning toward drought early action

Groundwater is an important source of water for people, livestock, and agriculture during drought in the Horn of Africa. In this work, areas of high groundwater use and demand in drought-prone Kenya were identified and forecasted prior to the dry season. Estimates of groundwater use were extended from a sentinel network of 69 in-situ sensored mechanical boreholes to the region with satellite data and a machine learning model. The sensors contributed 756 site-month observations from June 2017 to September 2021 for model building and validation at a density of approximately one sensor per 3700 sq.km. An ensemble of 19 parameterized algorithms was informed by features including satellite-derived precipitation, surface water availability, vegetation indices, hydrologic land surface modeling, and site characteristics to dichotomize high groundwater pump utilization. Three operational definitions of high demand on groundwater infrastructure were considered: 1) mechanical runtime of pumps greater than a quarter of a day (6+ hr) and daily per capita volume extractions indicative of 2) domestic water needs (35+ L), and 3) intermediate needs including livestock (75+ L). Gridded interpolation of localized groundwater use and demand was provided from 2017 to 2020 and forecasted for the 2021 dry season, June–September 2021. Cross-validated skill for contemporary estimates of daily pump runtime and daily volume extraction to meet domestic and intermediate water needs was 68%, 69%, and 75%, respectively. Forecasts were externally validated with an accuracy of at least 56%, 70%, or 72% for each groundwater use definition. The groundwater maps are accessible to stakeholders including the Kenya National Drought Management Authority (NDMA) and the Famine Early Warning Systems Network (FEWS NET). These maps represent the first operational spatially-explicit sub-seasonal to seasonal (S2S) estimates of groundwater use and demand in the literature. Knowledge of historical and forecasted groundwater use is anticipated to improve decision-making and resource allocation for a range of early warning early action applications.

Katie Fankhauser↗

NASA NTRS2022

Spectrally Simplified Approach for Leveraging Legacy Geostationary Oceanic Observations

The use of multispectral geostationary satellites to study aquatic ecosystems improves the temporal frequency of observations and mitigates cloud obstruction, but no operational capability presently exists for the coastal and inland waters of the United States. The Advanced Baseline Imager (ABI) on the current iteration of the Geostationary Operational Environmental Satellites, termed the R Series (GOES-R), however, provides sub-hourly imagery and the opportunity to overcome this deficit and to leverage a large repository of existing GOES-R aquatic observations. The fulfillment of this opportunity is assessed herein using a spectrally simplified, two-channel aquatic algorithm consistent with ABI wave bands to estimate the diffuse attenuation coefficient for photosynthetically available radiation, K(d)(PAR). First, an in situ ABI dataset was synthesized using a globally representative dataset of above- and in-water radiometric data products. Values of K(d)(PAR) were estimated by fitting the ratio of the shortest and longest visible wave bands from the in situ ABI dataset to coincident, in situ K(d)(PAR) data products. The algorithm was evaluated based on an iterative cross-validation analysis in which 80% of the dataset was randomly partitioned for fitting and the remaining 20% was used for validation. The iteration producing the median coefficient of determination (R2) value (0.88) resulted in a root mean square difference of 0.319 m−1, or 8.5% of the range in the validation dataset. Second, coincident mid-day images of central and southern California from ABI and from the Moderate Resolution Imaging Spectroradiometer (MODIS) were compared using Google Earth Engine (GEE). GEE default ABI reflectance values were adjusted based on a near infrared signal. Matchups between the ABI and MODIS imagery indicated similar spatial variability (R2 = 0.60) between ABI adjusted blue-to-red reflectance ratio values and MODIS default diffuse attenuation coefficient for spectral downward irradiance at 490 nm, K(d)(490), values. This work demonstrates that if an operational capability to provide- ABI aquatic data products was realized, the spectral configuration of ABI would potentially support a sub-hourly, visible aquatic data product that is applicable to water-mass tracing and physical oceanography research.

Advanced Baseline Imager↗

NASA NTRS2022

Introducing and Evaluating the Climate Hazards Center IMERG with Stations (CHIMES) Timely Station-Enhanced Integrated Multisatellite Retrievals for Global Precipitation Measurement

As human exposure to hydroclimatic extremes increase and the number of in situ precipitation observations declines, precipitation estimates, such as those provided by the Integrated Multisatellite Retrievals for Global Precipitation Measurement (GPM) (IMERG) mission, provide a critical source of information. Here, we present a new gauge-enhanced dataset [the Climate Hazards Center IMERG with Stations (CHIMES)] designed to support global crop and hydrologic modeling and monitoring. CHIMES enhances the IMERG Late Run product using an updated Climate Hazards Center (CHC) high-resolution climatology (CHPclim) and low-latency rain gauge observations. CHPclim differs from other products because it incorporates long-term averages of satellite precipitation, which increases CHPclim ’s fidelity in data-sparse areas with complex terrain. This fidelity translates into performance increases in unbiased IMERGlate data, which we refer to as CHIME. This is augmented with gauge observations to produce CHIMES. The CHC’s curated rain gauge archive contains valuable contributions from many countries. There are two versions of CHIMES: preliminary and final. The final product has more copious and better-curated station data. Every pentad and month, bias-adjusted IMERGlate fields are combined with gauge observations to create pentadal and monthly CHIMESprelim and CHIMESfinal. Comparisons with pentadal, high-quality gridded station data show that IMERG late performs well (r = 0.75), but has some systematic biases which can be reduced. Monthly cross-validation results indicate that unbiasing increases the variance explained from 50% to 63% and decreases the mean absolute error from 48 to 39 mm month −1. Gauge enhancement then increases the variance explained to 75%, reducing the mean absolute error to 27 mm month −1.

Chris C funk↗

NASA NTRSDate not supplied

The Global Water Monitor: Wetland surface height dynamics for Ecology, Conservation, and Resource Management

The Global Water Monitor (GWM) offers surface water-related products for lakes, river reaches and wetland zones. The surface elevation change products are derived from satellite radar altimeters, such as the Jason/Sentinel series, and can span multiple decades. While the current instruments are profiling, they offer surface water height at specific locations, thus contributing to parallel observation of wetland surface water extent. GWM wetland products are “operational” with routine updates within 1-2days of satellite overpass. There is also assurance of product continuity to at least the end of 2030. Currently, the GWM holds products for a small selection (~40) of diverse wetlands for objectives that focus on conservation and water/fisheries resource monitoring. These sites have been requested by various organizations also looking to the effects of climate change and anthropogenic influences. Many of the current GWM wetland regions are in National Parks such as the Everglades (USA), the Wasur (Rep. Indonesia), and the Kakadu marshes (Australia). They also include coastal river deltas of the Danube, Mekong, Amazon, Orinoco and Ganges Rivers, and the internal Okavango Delta in Botswana. The preliminary set also ensures a diverse range of wetlands e.g., the shallow pot-hole lake region of the Sand Hills and the coastal Black Swamp of the USA, the peat fields of Malaysia and rice growing fields of Yilinzhen in China. Extensive wetlands in Brazil (the Pantanal), South Sudan (the Sudd Marshes) and Belarus (the Pinsk) are also featured, as are the mangrove regions of the Sundarbans (India) and the Laguna Terminos (Mexico). The Usangu wetland (Tanzania) is also included, a focus region where wetland ecology strongly competes with demands from irrigation, livestock, and the needs of downstream hydro-electric power. The nadir-pointing altimeter instruments record height variations regardless of vegetation or canopy cover, and height dynamics at 10-day or monthly resolution reveal seasonal and inter-annual variations as well as longer-term declining or re-charging trends. These products provide a unique, multi-decadal data set that can stand-alone or serve with cross-validation or image-fusion efforts.

Charon Birkett↗

NASA NTRSDate not supplied

Analysis of CO Transport from Australia Fires and Its Impact to Ozone, Water Vapor and Clouds Using CrIS Single-Field-of-View Sounder Products and Other Remote Sensing and MERRA-2 Reanalysis Data

Australia’s unprecedented fire disasters at the end of 2019 to early 2020 emitted huge amounts of carbon monoxide (CO) and fire aerosol particles, and the long-range transport of the smoke plumes poses great impact to climate change, such as altering the Antarctic ozone (O3) hole. Spaceborne observations from satellites have been proven successful in monitoring CO from wildfires in the past decade and can be used to examine the associated CO transport. The primary remote sensing data used in this study is the Single Field of View (SFOV) Sounder Atmospheric Product (SiFSAP) derived from the Cross-track Infrared Sounder (CrIS) on SNPP, a new product that will be generated at NASA and released to the public in a few months. SiFSAP has a high spatial resolution of ~14 km and includes atmospheric profiles of temperature, water vapor, CO, O3, as well as cloud products, and as the SiFSAP algorithm performs both day- and night-time retrievals, it provides an additional observation for night-time in comparison to the day-time-only solar polar satellite instruments such as MOPPIT, OMPS, and TROPOMI. Most recent significant improvements in the quality of this product plus its good spatial resolution (better than most global weather and climate models) enable us to conduct process-oriented analysis of CO transport, and the variation of water vapor, O3 and clouds (optical depth, effective radius and cloud height) within and around the fire plumes. The wind fields from MERRA-2 reanalysis will be used to help characterize the transport. Other remote sensing data, such as CO from AIRS, MOPPIT and TROPOMI, O3 from OMPS and TROPOMI, as well as the UV aerosol index from OMI and OMPS, will be used and compared with SiFSAP sounder products. Cross-validation of CO and O3 from these different sensors with the corresponding MERRA-2 products will also be carried out. Along the plume transport path, some enhancement of O3 and correlation between fire aerosol, cloud optical depth and water vapor have been found but need further investigation. Using the transport of fire plumes over the Southern Pacific Ocean as a unique testbed, this study will demonstrate the trace species monitoring capability of current satellite observations, in particular, for CO and O3, and hopefully, it will provide some insight on the impacts on fire emissions on air quality and climate.

Xiaozhen (Shawn) Xiong↗

NASA NTRS2016

EVEREST: Pixel Level Decorrelation of K2 Light Curves

We present EPIC Variability Extraction and Removal for Exoplanet Science Targets (EVEREST), an open-source pipeline for removing instrumental noise from K2 light curves. EVEREST employs a variant of pixel level decorrelation to remove systematics introduced by the spacecraft’s pointing error and a Gaussian process to capture astrophysical variability. We apply EVEREST to all K2 targets in campaigns 0–7, yielding light curves with precision comparable to that of the original Kepler mission for stars brighter than K(sub p) ≈ 13, and within a factor of two of the Kepler precision for fainter targets. We perform cross-validation and transit injection and recovery tests to validate the pipeline and compare our light curves to the other de-trended light curves available for download at the MAST High Level Science Products archive. We find that EVEREST achieves the highest average precision of any of these pipelines for unsaturated K2 stars. The improved precision of these light curves will aid in exoplanet detection and characterization, investigations of stellar variability, asteroseismology, and other photometric studies. The EVEREST pipeline can also easily be applied to future surveys, such as the TESS mission, to correct for instrumental systematics and enable the detection of low signal-to-noise transiting exoplanets. The EVEREST light curves and the source code used to generate them are freely available online.

Catalogs↗

NASA NTRSDate not supplied

Using Machine Learning to Infer Material Properties of Debris Fragments from X-ray Images in the DebriSat Project

The DebriSat project is a collaboration effort with the NASA Orbital Debris Program Office, the U.S. Space Force Space Systems Command Center, The Aerospace Corporation, and the University of Florida. To date, over 200,000 fragments from this ground-based, hypervelocity impact experiment have been collected, and processing is underway to determine their physical characteristics, such as material, shape, color, characteristic length, and average cross-sectional area. The x-ray process is primarily used to identify the location of the fragments and estimated size for extraction, so that these physical characteristics can be assessed. This paper proposes a machine learning-based approach to characterize materials from x-ray images of debris fragments embedded in soft-catch foam used in the DebriSat project. The novel methodology discussed in this paper will highlight the use of x-ray imagery data to characterize these fragments without extraction or a human-in-the-loop. Both supervised and unsupervised machine learning techniques are utilized with this approach to infer the physical parameters of the fragments embedded in the soft-catch foam panels used in the impact experiment based on x-ray images of the foam panels. Additionally, 3D reconstructions of the extracted fragments are created with images taken from two different angles using the structure from motion (SfM) method. The characteristic lengths and shape from the 3D reconstruction, alongside the physical characteristics of the debris, are used in the inference of the material type. To develop and test the approach, a dataset of x-ray images of debris fragments of varying sizes and materials is collected. Supervised learning methods such as convolutional neural networks (CNNs), support vector machines (SVM), decision trees, and random forest classifiers are used due to the high-dimensional feature spaces of the debris and nonlinear decision boundaries for material categorization. Given the limited pre-labeled data of embedded debris materials smaller than 10 mm, unsupervised machine learning techniques such as clustering algorithms and autoencoders are used, in addition to supervised learning methods. The clustering algorithms group similar fragments together based on their physical properties, and autoencoders reduce the dimensionality of the x ray images and extract relevant features. The performance of the proposed approach's is analyzed using a range of statistical methods, including confusion matrices, receiver operating characteristic curves, and precision-recall curves. The results are compared with those obtained using a baseline approach that relies on manual identification and classification of debris fragments. To evaluate the effectiveness of different machine learning methods, statistical tests such as t-tests, ANOVA, and cross-validation are performed, comparing the performance of CNNs, SVMs, clustering algorithms, and autoencoders. Additional analysis needs to be conducted to identify any sources of bias or variability that may affect the results, such as variations in imaging conditions or fragmentation patterns. Other topics explored are limitations, refinements, and the potential use of semi-supervised learning techniques, such as self-training to label unlabeled datasets and co-training using x-ray images taken from two different angles as two different models.

Saik Anam Siam↗

NASA NTRSDate not supplied

Aero-Engines AI - A Machine-Learning App for Aircraft Engine Concepts Assessment

Effective deployment of machine-learning (ML) models could drive a high level of efficiency in aircraft engine conceptual design. Aero-Engines AI is a user-friendly app that has been created to deploy trained machine-learning (ML) models to assess aircraft engine concepts. It was created using tkinter, a GUI (graphical user interface) module that is built into the standard Python library. Employing tkinter greatly facilitates the sharing of ML application as an executable file which can be run on Windows machines (without the need to have Python or any library installed). The app gets user input for a turbofan design, preprocesses the input data, and deploys trained ML models to predict turbofan thrust specific fuel consumption (TSFC), engine weight, core size, and turbomachinery stage-counts. The ML predictive models were built by employing supervised deep-learning and K-nearest neighbor regression algorithms to study patterns in an existing open-source database of production and research turbofan engines. They were trained, cross-validated, and tested in Keras, an open-source neural networks API (application programming interface) written in Python, with TensorFlow (Google open-source artificial intelligence library) serving as the backend engine. The smooth deployment of these ML models using the app shows that Aero-Engines AI is an easy-touse and a time-saving tool for aircraft engine design-space exploration during the conceptual design stage. Current version of the app focuses on the performance prediction of conventional turbofans. However, the scope of the app can easily be expanded to include other engine types (such as turboshaft and hybrid-electric systems) after their ML models are developed. Overall, the use of a machine-learning app for aircraft engine concept assessment represents a promising area of development in aircraft engine conceptual design.

machine learning↗

NASA NTRS2023

Regional Analysis of the 2015–16 Lower Mekong River Basin Drought Using NASA Satellite Observations

Study region Lower Mekong River Basin (LMRB) Study focus Satellite remote sensing products are widely used for monitoring droughts. Using NASA satellite sensors of precipitation (Global Measurement Mission, GPM), soil moisture (Soil Moisture Active and Passive, SMAP), and terrestrial water storage (Gravity Recovery and Climate Experiment, GRACE), this study evaluates the historical drought in the LMRB during 2015–16. SMAP soil moisture was validated against in-situ soil moisture, and GPM precipitation and SMAP soil moisture were cross-validated with streamflow observations. The spatiotemporal dynamics of soil moisture were also examined in different ranges of catchment areas. In performing the analysis, we used lagged correlations between hydrological variables and the indices of the Standardized Precipitation Index (SPI) and Standardized Streamflow Index (SSI). New hydrological insights for the regions Spatio-temporal patterns of drought in 2015–16 were examined from the entire basin to small watersheds. A mismatch occurs when using GRACE data to study droughts in small watersheds (many of the small watersheds would be a fraction of the few 100 km2 spatial resolutions of GRACE pixel). In smaller watersheds, hydrological drought (SSI) was closely defined with SMAP soil moisture downscaled to 1 km rather than the meteorological drought index (SPI). By leveraging satellite-based observations across a range of spatial scales, this study highlights the utility of Earth observations in informing water resources and land management decisions at the regional scale.

Mekong↗

NASA NTRSDate not supplied

Aero-Engines AI - A Machine-Learning App for Aircraft Engine Concepts Assessment

Effective deployment of trained machine-learning models could drive a high level of efficiency in aircraft engine conceptual design. Aero-Engines AI is a Windows app that has been created to deploy trained machine-learning models to assess aircraft engine concepts. It was created using tkinter, a GUI (graphical user interface) module that is built into the standard Python library. Employing tkinter greatly facilitates the sharing of machine-learning application as an executable file which can be run on Windows machines (without the need to have Python or any library installed). Current version of the app focuses on the performance prediction of conventional turbofans. The app gets user input for a turbofan design, preprocesses the input data, and deploys trained machine-learning models to predict turbofan thrust specific fuel consumption (TSFC), engine weight, core size, and turbomachinery stage-counts. The machine-learning predictive models were built by employing supervised deep-learning algorithm to study patterns in an existing open-source database of production and research turbofan engines. They were trained, cross-validated, and tested in Keras, an open-source neural networks API (application programming interface) written in Python, with TensorFlow (Google open-source artificial intelligence library) serving as the backend engine. The smooth deployment of these machine-learning models using the app shows that Aero-Engines AI is an easy-to-use and a time-saving tool for aircraft engine design-space exploration during the conceptual design stage.

machine learning↗

NASA NTRS2023

Reconstructing PM 2.5 Data Record for the Kathmandu Valley Using a Machine Learning Model

This paper presents a method for reconstructing the historical hourly concentrations of particulate matter 2.5 (PM2.5) over the Kathmandu Valley from 1980 to the present. The method uses a machine learning model that is trained using PM2.5 readings from US Embassy (Phora Durbar) as a ground truth, and the meteorological data from Modern-Era Retrospective Analysis for Research and Applications v2 (MERRA2) as input. The Extreme Gradient Boosting (XGBoost) model acquires a credible 10-fold cross-validation (CV) score of ~83.4%, an r2-score of ~84%, a Root Mean Square Error (RMSE) of ~15.82 µg/m3, and a Mean Absolute Error (MAE) of ~10.27 µg/m3. Further demonstrating the model's applicability to years other than those for which truth values are unavailable, the multiple cross-test with an unseen data set offered r2-scores for 2018, 2019, and 2020 ranging from 56% to 67%. The model-predicted data agrees with true values and indicates that MERRA2 underestimates PM2.5 over the region. It strongly agrees with ground-based evidence showing substantially higher mass concentrations in the dry pre- and post-monsoon seasons than in the monsoon months. It also shows a strong anti-correlation between PM2.5 concentration and humidity. The results also demonstrate that none of the years fulfilled the annual mean air quality index (AQI) standards set by the World Health Organization (WHO).

machine learning↗

NASA NTRS2023

Aero-Engines AI - A Machine-Learning App for Aircraft Engine Concepts Assessment

Effective deployment of machine-learning (ML) models could drive a high level of efficiency in aircraft engine conceptual design. Aero-Engines AI is a user-friendly app that has been created to deploy trained machine-learning (ML) models to assess aircraft engine concepts. It was created using tkinter, a GUI (graphical user interface) module that is built into the standard Python library. Employing tkinter greatly facilitates the sharing of ML application as an executable file which can be run on Windows machines (without the need to have Python or any library installed). The app gets user input for a turbofan design, preprocesses the input data, and deploys trained ML models to predict turbofan thrust specific fuel consumption (TSFC), engine weight, core size, and turbomachinery stage-counts. The ML predictive models were built by employing supervised deep-learning and K-nearest neighbor regression algorithms to study patterns in an existing open-source database of production and research turbofan engines. They were trained, cross-validated, and tested in Keras, an open-source neural networks API (application programming interface) written in Python, with TensorFlow (Google open-source artificial intelligence library) serving as the backend engine. The smooth deployment of these ML models using the app shows that Aero-Engines AI is an easy-touse and a time-saving tool for aircraft engine design-space exploration during the conceptual design stage. Current version of the app focuses on the performance prediction of conventional turbofans. However, the scope of the app can easily be easily expanded to include other engine types (such as turboshaft and hybrid-electric systems) after their ML models are developed. Overall, the use of a machine-learning app for aircraft engine concept assessment represents a promising area of development in aircraft engine conceptual design.

machine learning↗

NASA NTRS2023

Using Machine Learning to Infer Material Properties of Debris Fragments from X-ray Images in the DebriSat Project

Saik Anam Siam↗

NASA NTRS2023

Using Regionalized Air Quality Model Performance and Bayesian Maximum Entropy Data Fusion to Map Global Surface Ozone Concentration and Associated Uncertainty

Estimates of ground-level ozone concentrations have been improved through data fusion of observations and atmospheric chemistry models. Our previous global ozone estimates for the Global Burden of Disease study corrected for bias uniformly across continents and then corrected near monitoring stations using the Bayesian Maximum Entropy (BME) framework for data fusion. Here, we use the Regionalized Air Quality Model Performance (RAMP) framework to correct model bias over a much larger spatial range than BME can, accounting for the spatial inhomogeneity of bias and nonlinearity as a function of modeled ozone. RAMP bias correction is applied to a composite of 9 global chemistry-climate models, based on the nearest set of monitors. These estimates are then fused with observations using BME, which matches observations at measurement stations, with the influence of observations declining with distance in space and time. We create global ozone maps for each year from 1990 to 2017 at fine spatial resolution. RAMP is shown to create unrealistic discontinuities due to the spatial clustering of ozone monitors, which we overcome by applying a weighting for RAMP based on the number of monitors nearby. Incorporating RAMP before BME has little effect on model performance near stations, but strongly increases R 2 by 0.15 at locations farther from stations, shown through a checkerboard cross-validation. Corrections to estimates differ based on location in space and time, confirming heterogeneity. We quantify the likelihood of exceeding selected ozone levels, finding that parts of the Middle East, India, and China are most likely to exceed 55 parts per billion (ppb) in 2017. About 96% of the global population was exposed to ozone levels above the World Health Organization guideline of 60 µg m −3 (30 ppb) in 2017. Our annual fine-resolution ozone estimates may be useful for several applications including epidemiology and assessments of impacts on health, agriculture, and ecosystems.

Ozone↗