Search NASA⌕ Search

SEARCH · Search NASA

Results for “Data Reasoning”

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 253 records · Page 14
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Model-Based Approaches to Generate Knowledge from Data in a Plant Reliability Context

One challenge that nuclear power plant system engineers are facing is that the amount of equipment reliability (ER) data being continuously generated are extremely large. These data elements come in different forms: textual (e.g., condition reports) and numeric (e.g., generated by monitoring systems) and they provide system engineers with valuable insights and information regarding the discovery of anomalous behaviors or degradation trends, the identification of the possible causes behind such behaviors and trends, and the prediction of their direct consequences. This paper directly targets the generation of knowledge from ER data by putting “data into context”. Here, we employ model-based system engineering (MBSE) models of systems and assets to represent and capture their architecture and functional (i.e., cause-effect) relations. ER data elements are processed by identifying first which elements of the developed MBSE elements they are referring to. This task is much harder for textual data since the information contained in issue or maintenance reports needs to “be understood” by a computational tool. Here we called this process “knowledge extraction” where our methods to extract knowledge from textual data. Lastly, once numeric and textual ER data elements have been processed and “understood”, we discover possible cause-effect relations among them. This is performed by observing if a logical connection through the MBSE models exists, and if there is a temporal relation among them. The logic and temporal are the two main ingredients to perform “machine reasoning” from ER data.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Model-Based Approaches to Generate Knowledge from Data in a Plant Reliability Context

One challenge that nuclear power plant system engineers are facing is continuous generation of an extremely large amount of equipment reliability (ER) data. These data elements come in textual (e.g., condition reports) and numeric (e.g., generated by monitoring systems) forms. They provide system engineers with valuable insights and information by discovering anomalous behaviors or degradation trends, identifying possible causes behind such behaviors and trends, and predicting their direct consequences. This paper directly targets the knowledge generation from ER data by putting “data into context.” We employ model-based system engineering (MBSE) of systems and assets to represent and capture their architecture and functional (i.e., cause-effect) relations. ER data elements are processed by first identifying which of the developed MBSE elements they are referring to. This task is harder for textual data since the information contained in issue or maintenance reports needs to be “understood” by a computational tool. We called this process “knowledge extraction” since our methods extract knowledge from textual data. Last, once numeric and textual ER data elements have been processed and “understood,” we discover possible cause-effect relations among them. This is performed by observing whether a logical connection through the MBSE models exists, and if there is a temporal relationship among them. The logic and temporal are the two main ingredients to perform “machine reasoning” from ER data.

97 - MATHEMATICS AND COMPUTING↗
NASA NTRS2003

Total Ozone from the Ozone Monitoring System (OMI) using TOMS and DOAS Methods

The Ozone Monitoring Instrument (OMI) is the Dutch-Finnish contribution to NASA's EOS-Aura satellite scheduled for launch in January 2004. OMI is an imaging spectrometer that will measure the back-scattered Solar radiance in the wavelength range of 270 to 500 nm. The instrument provides near global coverage in one day with a spatial resolution of 13x24 square kilometers. OMI is a new instrument, with a heritage from TOMS, SBW, GOME, GOMOS and SCIAMACHY. OMI'S unique capabilities for measuring important trace gases and aerosols with a small footprint and daily global coverage, in conjunction with the other Aura instruments, will make a major contribution to our understanding of stratospheric and tropospheric chemistry and climate change. OMI will provide data continuity with the 23-year ozone record of TOMS. There are three ozone products planned for OMI: total column ozone, ozone profile and tropospheric column ozone. We are developing two different algorithms for total column ozone: one similar to the algorithm currently being used to process the TOMS data, and the other an improved version of the differential optical absorption spectroscopy (DOAS) method, which has been applied to GOME and SCIAMACHY data. The main reasons for starting with two algorithms for total ozone have to do with heritage and past experience; our long-term goal is to combine the two to develop a more accurate and reliable total ozone product for OMI. We will compare the performance of these two algorithms by applying both of them to the GOME data. We will examine where and how the results differ, and use the extensive TOMS-Dobson comparison studies to assess the performance of the DOAS algorithm.

Veefkind, J. P.↗
NASA NTRS1975

Noise and sleep - A literature review and a proposed criterion for assessing effect

Results of a number of studies on the effects of various types of noise on the sleep of subjects of both sexes and a wide range of age groups are reviewed to develop a tentative criterion for assessing these effects. Available data suggest that reasonably accurate predictions of sleep disruption may be made if the interfering noise is specified in units (EPNdB or EdBA) which account for its spectral characteristics and duration. When EPNdB units are used as the measure of noise intensity, the correlation coefficient between intensity and the probability of no sleep disturbance is -0.86. Because of the paucity of data on the long-term results of frequent behavioral wakings or arousals, it is suggested that disturbance of sleep be defined as an electroencephalographic change of one or more sleep stages.

Lukas, J. S.↗
NASA NTRS2003

Maneuver Classification for Aircraft Fault Detection

Automated fault detection is an increasingly important problem in aircraft maintenance and operation. Standard methods of fault detection assume the availability of either data produced during all possible faulty operation modes or a clearly-defined means to determine whether the data provide a reasonable match to known examples of proper operation. In the domain of fault detection in aircraft, identifying all possible faulty and proper operating modes is clearly impossible. We envision a system for online fault detection in aircraft, one part of which is a classifier that predicts the maneuver being performed by the aircraft as a function of vibration data and other available data. To develop such a system, we use flight data collected under a controlled test environment, subject to many sources of variability. We explain where our classifier fits into the envisioned fault detection system as well as experiments showing the promise of this classification subsystem.

Oza, Nikunj C.↗
NASA NTRS2002

Classification of Aircraft Maneuvers for Fault Detection

Automated fault detection is an increasingly important problem in aircraft maintenance and operation. Standard methods of fault detection assume the availability of either data produced during all possible faulty operation modes or a clearly-defined means to determine whether the data is a reasonable match to known examples of proper operation. In our domain of fault detection in aircraft, the first assumption is unreasonable and the second is difficult to determine. We envision a system for online fault detection in aircraft, one part of which is a classifier that predicts the maneuver being performed by the aircraft as a function of vibration data and other available data. We explain where this subsystem fits into our envisioned fault detection system as well its experiments showing the promise of this classification subsystem.

Oza, Nikunj C.↗
NASA NTRS2002

Classification of Aircraft Maneuvers for Fault Detection

Automated fault detection is an increasingly important problem in aircraft maintenance and operation. Standard methods of fault detection assume the availability of either data produced during all possible faulty operation modes or a clearly-defined means to determine whether the data provide a reasonable match to known examples of proper operation. In the domain of fault detection in aircraft, the first assumption is unreasonable and the second is difficult to determine. We envision a system for online fault detection in aircraft, one part of which is a classifier that predicts the maneuver being performed by the aircraft as a function of vibration data and other available data. To develop such a system, we use flight data collected under a controlled test environment, subject to many sources of variability. We explain where our classifier fits into the envisioned fault detection system as well as experiments showing the promise of this classification subsystem.

Oza, Nikunj↗
NASA NTRSDate not supplied

Using XR for Improving Scientific Discovery With Numerical Weather Models

Earth science (ES) digital twins will help us understand the complex interactions and interrelationships that make up our Earth system and the impacts of earth science phenomena on it. Our work addresses two underdeveloped areas in current ES digital twin work: improving the understanding and interaction with ES model outputs by using Virtual and Mixed Reality (XR) tools and improving the non-intuitive mapping of continuous ES natural phenomena to gridded reference frames in current numerical models. Traditionally, scientists working on ES view and analyze the results of calculated or measured observables with static 1-dimensional (1D), 2D or 3D plots displayed on flat computer screens or paper. Using such limited mediums, it can be very difficult to identify, track and understand the evolution of key features due to poor viewing angles and the nature of flat computer screens. In addition, numerical models, such as the NASA Goddard Earth Observing System (GEOS) ES model, are almost exclusively formulated, visualized and analyzed in an Eulerian reference frame with fixed grid points in space and time. However, ES phenomena such as convective clouds, hurricanes and wildfire smoke plumes are visualized and analyzed in a Lagrangian reference frame: therefore it is often difficult and unnatural to understand these phenomena in relation to each other, visualized either in an Eulerian or Lagrangian context. In 3D visualizations, data generally takes one of three forms: gridded (e.g., voxelized) data, where space is divided into regions; point clouds, where data is represented as a set of points; and meshes, where objects are rendered as surfaces composed of small polygons (usually triangles). A gridded, Eulerian reference frame has been the default representation for the 2D visual analysis of atmospheric data in part because the numerical methods used to generate atmospheric model data in the first place use a gridded approach, with equations defining the relationships between the physical variables in each of a grid's cells across successive timesteps. In our work, we are particularly interested in data from GEOS. Another reason why gridded representations tend to be used for visualizing data from such models is because trajectories are difficult to interpret from representations on 2D surfaces, due to line-of-sight ambiguity. Instead of a fixed grid from GEOS, we embed a trajectory model to simulate particles' movement throughout a GEOS run. We then ingest these particle trajectories as animated point clouds with a NASA open source XR toolkit, the Mixed Reality Exploration Toolkit (MRET), and merge GEOS data with ES phenomena data onto one combined visualization that the user can intuitively interact with. Efficient rendering of arbitrarily large point clouds is an ongoing challenge being addressed by the computer science community, with the GPU-based optimizations and efficient GPU memory utilization a common theme of recent advances, especially for XR, where sustained high frame rate is mandatory to save the user from suffering due to simulation sickness. In this work, we describe and evaluate our progress in choosing and implementing appropriate methods for rendering arbitrarily large point clouds within MRET for XR. While tracking the XR headset enables the immersion of a user within a 3D scene of a data visualization, tracking of XR handheld controllers or user’s hands enables us to implement intuitive user interactions with the visualized datasets. Conventional tools require a user working with an ES visualization to conduct many interactions to commit their intended selections or manipulations with a visualized dataset; for example to specify a set of points in 3D space. Doing so in a 2D flat screen interface has traditionally required specifying a set of points in three distinct 2D coordinate systems (XY, XZ, and YZ), which is cumbersome. In other scientific domains, it has been shown that specifying or selecting a location or volume in XR using handheld controllers or tracked hands allows for greater speed and accuracy. We anticipate the same will hold true for atmospheric data, and we will share initial results of measuring the utility of such an interface. Notably, as the data being visualized is generated by GEOS as a prediction based on initial conditions, an intended application of our tool is to serve as part of an iterative feedback loop. Through XR, a scientist will review and manipulate a GEOS model run, modifying the conditions as needed to do subsequent runs of GEOS. Thereby, XR-based improvements to speed and accuracy of 3D tagging of points minimizes the effort required by both the scientist and the computer cluster conducting the necessary calculations.

Thomas Grubb↗
DOE OSTI2025

Data imbalance in drug response prediction: multi-objective optimization approach in deep learning setting

Abstract Drug response prediction (DRP) methods tackle the complex task of associating the effectiveness of small molecules with the specific genetic makeup of the patient. Anti-cancer DRP is a particularly challenging task requiring costly experiments as underlying pathogenic mechanisms are broad and associated with multiple genomic pathways. The scientific community has exerted significant efforts to generate public drug screening datasets, giving a path to various machine learning models that attempt to reason over complex data space of small compounds and biological characteristics of tumors. However, the data depth is still lacking compared to application domains like computer vision or natural language processing domains, limiting current learning capabilities. To combat this issue and improves the generalizability of the DRP models, we are exploring strategies that explicitly address the imbalance in the DRP datasets. We reframe the problem as a multi-objective optimization across multiple drugs to maximize deep learning model performance. We implement this approach by constructing Multi-Objective Optimization Regularized by Loss Entropy loss function and plugging it into a Deep Learning model. We demonstrate the utility of proposed drug discovery methods and make suggestions for further potential application of the work to achieve desirable outcomes in the healthcare field.

Biochemistry & Molecular Biology↗
NASA NTRSDate not supplied

Analysis and Comparison of Surface Roughness Effects on Pressure Data from SLS Wind Tunnel Test

Unsteady flows are becoming a more characterized field of study as advancements in technology is allowing for more high-speed, time-resolved data acquisition. It is important to understand these flows as the shock-wave boundary-layer interactions and separation they are involved with can generate extreme loads caused by high pressure and temperature on the body of a flight vehicle. It is vital to characterize these loads, as they can impede upon the structural integrity of a high-speed system. A common instrument utilized today to characterize pressure distributions caused by unsteady flows are unsteady pressure transducers. Set flush with the surface of a flight vehicle or wind tunnel model, these transducers can provide a pressure distribution, capturing the frequency of unsteady loads that could impinge upon the test article. A couple negative aspects of this instrumentation is that they are expensive, have long lead times, and a pressure distribution can only be determined in one discrete location where the transducer is installed. An optical diagnostic known as unsteady pressure-sensitive paint (uPSP) can help to satisfy these deficiencies. This is a spray paint that can be applied to a surface of a model to provide a global pressure distribution across the whole painted region.2 A complete picture of the fluid dynamic pressures occurring on the surface of a test article can be analyzed, especially in locations where it may have been impossible to install a transducer. Pressure-sensitive paint is also less expensive than traditional pressure transducers, which are, on average, about $2,000 each including the cost of installation.3 Unsteady PSP will not replace unsteady pressure transducers, but the transducers can be used to validate the PSP response to the flow and measure frequencies higher than the frequency response of the paint. One issue that can arise using these tools simultaneously, is that the surface roughness of the uPSP can affect the pressure readings of the transducers. Applying the uPSP to the surface of the model is going to affect the flow in some way as the topography of the model is now different than if it was not painted. One study with steady PSP conducted by Amer, Obara, and Liu at NASA Langley concluded that the PSP surface roughness was minimally intrusive at different test conditions with various lift, drag, etc., however, it was noted that data from some pressure transducers had decreased, likely due to the uneven application of the PSP in the localized region of the transducers.9 Sugioka et. al. tested various formulations of uPSP to study surface roughness effects on a Common Research Model (CRM) in transonic flow. The influence of uPSP on the surface of the model, depending on how it was formulated, was noted to have the possibility of relocating the shock wave present in the flow. This study was conducted to examine and compare transducer data acquired in December 2017 of a 4% scale model of the Space Launch System (SLS) performed at NASA Ames Research Center (ARC) Unitary Plan Wind Tunnel (UPWT). One goal of the test was to demonstrate to the customer the potential of the uPSP system developed at NASA ARC. The effect of uPSP on transducer signals also became an interest in this experiment and is the reason for this data analysis. The results of this study were discussed with the SLS team to help them make decisions regarding the next test on an SLS model with the PSP and Unitary Plan Wind Tunnel teams.

pressure-sensitive paint↗
DOE OSTI2025

A Note to Reviewers Suggesting Post-reaction Catalyst Characterization: Know What You’re Asking For

Here, we highlight examples of post-reaction characterization in thermo- and electrocatalysis to present the challenges in obtaining reliable data to answer specific questions about the true identity of the active site and/or catalyst deactivation/degradation. We use this editorial to suggest to reviewers that, when formulating comments to authors that involve materials characterization after reaction testing, they should consider what specific, meaningful information can be attained or what targeted question can be answered that adds value to the individual paper and to the field in general, and how to reasonably obtain that data. In contrast, reviewers should avoid vague, open-ended comments that suggest unguided post-reaction characterization that would not add significant value to the report and, similarly, avoid comments that are substantial enough that they could form the basis of an entirely separate report.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Hot Droughts and Forest Tree Dynamics in the Amazon - Statistical Models, Scripts, Data, and Outputs

This package contains data, outputs, equations, and R scripts for analyses for manuscript entitled "Hot droughts in the Amazon: A window to a future hypertropical climate" by J. Chambers et al., in particular it contains statistical models and analyses for the INPA BIONTE tree mortality study. The Models folder contains details for all statistical models in PDF files. The Scripts folder contains the R scripts for Bayesian Hierarchical Models (two text files) and SEMs (one text file) are separate and reasonably annotated. All data associated with these scripts are in the data folder. The Data folder contains two of the three CSV files used for the analyses and are called by the R scripts. Two of them are part of published datasets (`BIONTE_mortality-rates.csv` from Lima et al. 2024, DOI:10.15486/ngt/1898910 and `SPEI.csv` from Pastorello et al. 2023 DOI:10.15486/ngt/1958257) and also provided in this package for convenience (please see the corresponding datasets for usage and citation terms). The third dataset (`BIONTE_gapfilled_wd.csv`) contains sensitive information and can be obtained by contacting the manuscript lead author. The Outputs folder contains the two output files that provide extra information about the analyses. The file `figuresFeb2025d.pdf` contains all the figures from the manuscript - captions are in the manuscript. The file `ChambersMS.pdf` contains primary results from Bayesian statistical models, regression analyses, and validation steps applied to the tree mortality data from the INPA experiments. The document includes visual summaries, model diagnostics, and leave-one-out (LOO) validation results. A breakdown of file contents can be found in the README file that is part of this package.

54 ENVIRONMENTAL SCIENCES↗
NASA NTRSDate not supplied

Impact of Thermoplastic Composites: Testing and Modeling

Thermoplastic Composites (TPCs) are being increasingly considered for aerospace applications given their faster manufacturing cycles and lower cost. The NASA High-Rate Composite Aircraft Manufacturing (HiCAM) project aims to evaluate and mature thermoplastic manufacturing technologies to achieve a 4X – 6X increase in the production rate of Next Generation Single Aisle (NGSA) commercial aircraft. Within the purview of the NASA HiCAM project, this work investigates the response of thermoplastic composites under High Energy Dynamic Impact (HEDI) conditions. HEDI tests were conducted on panels fabricated with a carbon fiber reinforced low melt semi-crystalline resin TC1225 LMPAEK T700G (T700/LMPAEK) material system. A blunt metal projectile was chosen as the impactor which impacted the T700/LMPAEK panels over a range of impact velocities imparted by a gas gun test setup. As expected, lower velocity impacts caused the projectile to rebound, whereas higher velocity impacts resulted in the projectile penetrating the test panels. For the test cases in which the projectile rebounded, the predominant damage modes recorded with Ultrasonic (UT) scans included interlaminar delaminations which exhibited a “rotating fan” like structure when viewed in the through-thickness direction. Additionally, the dynamic deflection of the center point of the back face of the test panels and the velocity of the projectile was also measured during the test. Finite element models were developed to model a test case in which the projectile rebounded. These models were developed using LS-DYNA® wherein the primary objective was to evaluate the ability of the material model MAT299 to capture the dynamic response and damage modes in the T700/LMPAEK test panels. MAT299 is a Deformation Gradient Decomposition (DGD) based Continuum Damage Mechanics (CDM) material model. The interlaminar delaminations were modeled using the cohesive contact formulation available within LS-DYNA, wherein the mixed-mode fracture is captured via the Benzegaggh-Kenane (B-K) mode-dependent fracture energy interpolation law. The above-mentioned modeling methods have mostly been applied to thermoset composites and adapting them to TPCs involves addressing challenges associated with appropriately representing material behavior. Therefore, the proposed paper would discuss the systematic approach taken to adapt thermoset composites modeling practices for applications to TPCs, while appropriately addressing material behavior. The proposed paper would show that the predicted back face center point deflection correlated reasonably well with experimental data and the peak deflection was predicted to be within 5% of the experimental measurements. The projectile rebound velocity, while predicted to be higher than the experimental measurement, was within reasonable bounds. Additionally, it will be shown that the predicted delamination shapes were in reasonable agreement with experimental data.

Composite Materials↗
NASA NTRS1972

Rotor windage losses for Lundell alternators

The Lundell alternator is being investigated for power system applications. At the high speeds required, power loss due to windage can become high and result in significant heating of the alternator. This loss must be incorporated in the cooling design. The velocity profiles expected in these alternators are highly turbulent, and the Reynolds numbers are well above the levels previously reported; the available data could only be extrapolated. For this reason, a range of experimental data was generated to permit accurate calculation of the windage power loss for Lundell alternator design. Windage tests were conducted on two concentric rotor-stator configurations in ambient air, producing Reynolds numbers as high as 100,000. Using the data obtained, a method was developed to calculate the windage loss for any Lundell alternator given the geometry and cavity conditions.

Gorland, S. H.↗
NASA NTRS1990

Wall interference assessment/correction (WIAC) for transonic airfoil data from porous and shaped wall test sections

An existing computational wall interference assessment/correction (WIAC) procedure is applied to two sets of transonic airfoil data obtained from the same model tested in both a porous, planar-wall and a solid, shaped-wall test section. The published airfoil data from the porous test section agrees reasonably well with the published data from the shaped wall test section, although some differences exist. The WIAC procedure is applied to the data to assess and correct any wall interference effects; WIAC corrections generally improve the correlation between the two data sets. As an independent verification, both the published and WIAC corrected airfoil data are compared to Navier-Stokes calculations. Correlations are generally better between the WIAC corrected data and the Navier-Stokes calculations than between similar correlations with the published data.

Mineck, Raymond E.↗
NASA NTRS1992

Magellan ephemeris improvement using synthetic aperture radar landmark measurements

A technique is described for measuring the positions of landmarks in multiple SAR images of the surface of Venus taken aboard the Magellan spacecraft. These measurements are then used to improve the spacecraft orbit estimate. The Venus-fixed coordinates of the landmarks are also estimated, as are the low-order coefficients of the gravitational field. Sample results are shown for five-orbit and 13-orbit data arcs using hundreds of landmark measurements. Reasonably good fits to the data are obtained for the short-arc solutions, while the data fits over long arcs are poorer, possibly due to higher-order uncertainties in the gravitational field. A comparison of post-fit orbit uncertainties shows that the SAR data significantly improves the orbit estimate.

Chodas, Paul W.↗
NASA NTRS2008

Metrology - Beyond the Calibration Lab

We rely on data from measurements every day; a gas-pump, a speedometer, and a supermarket weight scale are just three examples of measurements we use to make decisions. We generally accept the data from these measurements as "valid." One reason we can accept the data is the "legal metrology" requirements established and regulated by the government in matters of commerce. The measurement data used by NASA, other government agencies, and industry can be critical to decisions which affect everything from economic viability, to mission success, to the security of the nation. Measurement data can even affect life and death decisions. Metrology requirements must adequately provide for risks associated with these decisions. To do this, metrology must be integrated into all aspects of an industry including research, design, testing, and product acceptance. Metrology, the science of measurement, has traditionally focused on the calibration of instruments, and although instrument calibration is vital, it is only a part of the process that assures quality in measurement data. For example, measurements made in research can influence the fundamental premises that establish the design parameters, which then flow down to the manufacturing processes, and eventually impact the final product. Because a breakdown can occur anywhere within this cycle, measurement quality assurance has to be integrated into every part of the life-cycle process starting with the basic research and ending with the final product inspection process. The purpose of this paper is to discuss the role of metrology in the various phases of a product's life-cycle. For simplicity, the cycle will be divided in four broad phases, with discussions centering on metrology within NASA. .

Mimbs, Scott M.↗
NASA NTRSDate not supplied

Snow Depth from AMSR-2 Using Multispectral Satellite Data in an Artificial Neural Network

By using diffusion theory and Monte Carlo lidar radiative transfer simulations, Hu et al. (2022b) has derived snow depth from the first-, second- and third-order moments of the lidar backscattering pathlength distribution. Lu et al. (2022) calculated the snow depth by applying the methods to the satellite ICESat-2 lidar measurements over the Arctic sea ice, as well as land surfaces of Northern Hemisphere. In this paper, an artificial neural network (ANN) algorithm, employing several channels from Advanced Microwave Scanning Radiometer 2 (AMSR-2) and the humidity vertical profiles from Global Modeling and Assimilation Office (GMAO) Goddard Earth Observing System for Instrument Teams (GEOS-IT) product, is trained to determine snow depth identified by time and geolocation matched 2019 ICESat-2 snow-depth data during winter months over the Arctic sea ice. The trained ANN snow-depth was applied to 2018 AMSR-2 clear pixel data, although the algorithms perform reasonably well in thinner clouds. The validation data (different from the training set) of ANN snow depth from AMSR-2 showed a good agreement with time matched and co-located snow-depth values from ICESat-2. The bias was near zero, with mean absolute error (MAE) 0.05 cm and a root-mean-square-error (RMSE) 0.08 cm. Prior applying the trained ANN snow depth to AMSR-2 data, a cloud screening algorithm was developed with a similar approach. A separate ANN cloud mask was trained to determine an AMSR-2 pixel is clear or cloudy with time and geolocation matched 2015 CALIOP Vertical Feature Mask (VFM) over Arctic sea ice. The ANN cloud mask from AMSR-2 under-estimated cloud fraction by 3-6% compared to CALIOP . The additional research is needed to conclusively evaluate the ANN cloud mask accuracy. Finally, this paper will lay the foundation for a sustained long-term snowfall and snow-storm monitoring system. The future Cloud Aerosol LIdar for Global scale Observations of the ocean-Land Atmosphere system (CALIGOLA) mission will provide a means to calculate snow depth from the lidar backscattering pathlength distribution, benefiting from the UV, visible and infrared pulses. With the calculated snow depth as the truth one could develop a machine learning algorithm, as it was done in this paper, using a passive microwave instrument available at that time to generate a wide range of snow depth data, covering extensive spatial areas in the cross-orbit direction.

Neural Network↗