Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Context algorithm”

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 721 records · Page 40
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

SWIPE: Spectral Water Inversion Processor and Emulator

Degradation of Earth’s inland water resources due to anthropogenic perturbations and climate anomalies at both local and global scales continues to place human health at substantial risk. There is now a growing necessity to develop pragmatic approaches that allow timely and effective extrapolation of local processes, to spatially resolved global products, and to promote operational and sustainable resource policy management. This presentation will be discussing the progress made developing SWIPE: Spectral Water Inversion Processor and Emulator. SWIPE is a platform for advanced modeling of coastal and inland aquatic habitats. The goal is create a comprehensive and cohesive system to leverage recent advancements in computation and machine learning to develop a synthetic training ground for sensitivity studies and algorithm development. The four principal facets of SWIPE include: 1. Advanced two-layer coated sphere bio-optical modeling and GPU radiative transfer modeling, 2. Big Data involving massive synthetic spectral libraries of optical properties of various global aquatic particles, surface reflectance, and top-of-atmosphere reflectance, all at hyperspectral resolution leveraging high-end computing systems at NASA Ames Research Center, 3. Deep Learning for algorithm development for water quality inversion of concentrations of common biogeophysical variables as well as optics, full uncertainty characterization by water type, and forward emulation, and lastly, 4. Image Processing for application of developed retrieval algorithms for both hyperspectral and multispectral sensors with experimental corrections for global adjacency, noise, sunglint, and benthic reflectance. This presentation will demonstrate the Equivalent Algal Populations (EAP) two-layer coated sphere scattering model which has been used develop spectral libraries of hyperspectral inherent optical properties of roughly 80 species of phytoplankton, covering 15 different classes and nine taxonomic functional types. The EAP model was also used to derive spectral properties of 10 different non-algal particle functional types. Examples of how the SMART-G (Speed-up Monte-carlo Advanced Radiative Transfer using GPU) radiative transfer code is used to model optically complex aquatic signals will be presented and discussed in the context of creating a massive synthetic database which can leverage the full power of next generation machine learning techniques and high end computing for water quality inversion. We will discuss our active investigation in things like appropriate model architectures, dimensionality reduction techniques such as PCA and autoencoders, uncertainty quantification and abstaining, and which variables actually benefit most from hyperspectral information versus multispectral resolution. We are also curious about questions relating to cost/benefit analysis in terms of computation resources, neural network complexity, and data volumes. Answers to these questions will hopefully elaborate on cost efficiency for potential future sensor design considerations.

SWIPE↗
DOE OSTI2021

Using Machine Learning to Track Objects Across Cameras

Video surveillance is one of the most important technologies used by the International Atomic Energy Agency in international safeguards. At large, complicated facilities, multiple surveillance cameras are deployed to monitor the transfer of safeguards-relevant objects across the site. During inspections, all surveillance videos are reviewed to ensure the objects are not manipulated or diverted during transfer, a laborious, time-consuming task. This work describes using deep machine learning algorithms to track objects automatically across multiple cameras, greatly improving the efficiency of the review process. The fundamental problem in this object tracking task across multiple cameras is how to associate the same object, which may show extreme intra-class variations, such as viewpoints, occlusions, and various scales, in different and even non-overlapped cameras. Object re-identification (Re-ID) in nuclear facility video surveillance is even more challenging than classic person or vehicle Re-ID problems because different instances in the same category may display an identical appearance. One observation from nuclear facility surveillance videos is that all objects must be carted (e.g., via forklift) to move. Therefore, the spatial context information of an object, which provides the feature from the carrier, is critical for the object Re-ID task. This work proposes a two-stream convolutional neural networks model that takes features of objects and their surrounding regions into account. Moreover, the custom videos usually are gleaned from different scenes from the training data, which may have extreme variations in illumination changes and/or cluttered backgrounds. Directly applying the trained model to custom videos will dramatically decrease the performance. To tackle this problem, an advanced domain adaptation technique is proposed to mitigate the gap between the data taken from different scenes. The proposed framework will track objects of interest across a nuclear complex. The resulting tracks can be used in further analyses, such as event/activity recognition, anomaly detection, etc.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗
DOE OSTI2022

Evaluation of Portable Programming Models to Accelerate LArTPC Detector Simulations

The Liquid Argon Time Projection Chamber (LArTPC) technology is widely used in high energy physics experiments, including the upcoming Deep Underground Neutrino Experiment (DUNE). Accurately simulating LArTPC detector responses is essential for analysis algorithm development and physics model interpretations. Accurate LArTPC detector response simulations are computationally demanding, and can become a bottleneck in the analysis workflow. Compute devices such as General-Purpose Graphics Processing Units (GPGPUs) have the potential to substantially accelerate simulations compared to traditional CPU-only processing. The software development that requires often carries the cost of specialized code refactorization and porting to match the target hardware architecture. With the rapid evolution and increased diversity of the computer architecture landscape, it is highly desirable to have a portable solution that also maintains reasonable performance. We report our ongoing effort in evaluating Kokkos as a basis for this portable programming model using LArTPC simulations in the context of the Wire-Cell Toolkit, a C++ library for LArTPC simulations, data analysis, reconstruction and visualization.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2022

Quantum-inspired method for solving the Vlasov-Poisson equations

Kinetic simulations of collisionless (or weakly collisional) plasmas using the Vlasov equation are often infeasible due to high-resolution requirements and the exponential scaling of computational cost with respect to dimension. Recently, it has been proposed that matrix product state (MPS) methods, a quantum-inspired but classical algorithm, can be used to solve partial differential equations with exponential speed-up, provided that the solution can be compressed and efficiently represented as a MPS within some tolerable error threshold. Here, in this work, we explore the practicality of MPS methods for solving the Vlasov-Poisson equations for systems with one coordinate in space and one coordinate in velocity, and find that important features of linear and nonlinear dynamics, such as damping or growth rates and saturation amplitudes, can be captured while compressing the solution significantly. Furthermore, by comparing the performance of different mappings of the distribution functions onto the MPS, we develop an intuition of the MPS representation and its behavior in the context of solving the Vlasov-Poisson equations, which will be useful for extending these methods to higher-dimensional problems.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
NASA NTRS1988

Near UV atmospheric absorption measurements from the DC-8 aircraft during the 1987 airborne Antarctic ozone experiment

During the Airborne Antarctic Ozone Experiment from 28 August to 30 September 1987 near UV zenith scattered sky measurements were made over Antarctic from the NASA DC-8 aircraft using a one third m spectrograph equipped with a diode-array detector. Scattered sky light data in the wavelength range 348 nm to 388 nm was spectrally analyzed for O3, NO2, OClO, and BrO column abundances. Slant column abudances of O3, NO2, OClO and BrO were determined, using a computer algorithm of non-linear and linear least square correlation of Antarctic scattered sky spectra to laboratory absorption cross section data. Using measured vertical electrochemical sonde ozone profiles from Palmer, Halley Bay, and the South Pole Stations the slant columns of O3 were converted into vertical column abundances. The vertical column amounts of NO2, OClO, and BrO were derived using vertical profiles calculated by a chemical model appropriate for Antarctica. NO2 vertical column abundances show steep latitudinal decrease with increasing latitude for all 13 flights carried out during the mission. In the regions where NO2 abudances are low, OClO and BrO were observed. The spatial and temporal vertical column abundances of these species are discussed in the context of the chemistry and dynamics in the antarctic polar vortex during the austral spring.

Wahner, A.↗
NASA NTRS2017

GC13I-0860: An Assessment of Surface Water Detection Methods for the Tahoua Region, Niger

The recent release of several global surface water datasets derived from remotely sensed data has allowed for unprecedented analysis of the earth's hydrologic processes at a global scale. However, some of these datasets fail to identify important sources of surface water, especially small ponds, in the Sahel, an arid region of Africa that forms a border zone between the Sahara Desert to the north, and the savannah to the south. These ponds may seem insignificant in the context of wider, global-scale hydrologic processes, but smaller sources of water are important for local and regional hydrologic assessments. Particularly, these smaller water bodies are significant sources of hydration and irrigation for nomadic pastoralists and smallholder farmers throughout the Sahel. For this study, several methods of identifying surface water from Landsat 8 OLI, Sentinel 1 SAR, Sentinel 2 MSI, and Planet Dove data were compared to determine the most effective means of delineating these features in the Tahoua Region of Niger. The Automated Water Extraction Index (AWEInsh) had the best performance when validated against very high resolution Digital Globe imagery, with an overall accuracy of 98.6%. This study reiterates the importance of region-specific algorithms and suggests that the AWEInsh method may be the best for delineating surface water in the Sahelian ecozone, likely due to the nature of the exposed geology and lack of dense green vegetation.

Herndon, Kelsey E.↗
DOE OSTI2023

Simulating Catalysis with Realistic Pellet Geometries Using Mesoflow: A Case Study of Catalytic Propane Dehydrogenation

We present a case study of catalytic propane dehydrogenation with our open-source multiphysics solver, Mesoflow. The solver was developed to simulate reactive flow coupled to heterogeneous catalytic reactions and deactivation in the context of complex, mesoscale geometry. The method leverages cartesian block-structured adaptive mesh refinement to capture realistic catalyst microstructural features acquired directly from X-ray computed tomography data. A kinetic model for propane dehydrogenation and catalyst deactivation was developed based on temporal analysis of products (TAP) reactor experiments. The TAP reactor experiments allow for precise characterization of intrinsic kinetic reaction steps which are implemented into Mesoflow simulations to model the spatial and temporal evolution of reactants, products, and catalyst active sites. The short-term and long-term deactivation behavior is studied by using XCT data collected from fresh and aged catalyst pellets, which exhibit different microstructural features. This study employs time-splitting algorithms to connect disparate reaction and flow timescales, enabling the simulations to achieve realistic deactivation timescales on the order of minutes while the flow time-scales for small particles (100 microns) are several milliseconds. We also introduce a flexible automated python script that writes the necessary files to construct a Mesoflow simulation from user-created chemical mechanisms. We will also introduce a few new features that are added to Mesoflow such as higher order schemes, implicit chemistry integrators and the ability to run on AMD and NVIDIA graphics-processing-units.

AMReX↗
DOE OSTI2022

Substructure in the stellar halo near the Sun: I. Data-driven clustering in integrals-of-motion space

Context. Merger debris is expected to populate the stellar haloes of galaxies. In the case of the Milky Way, this debris should be apparent as clumps in a space defined by the orbital integrals of motion of the stars. Aims. Our aim is to develop a data-driven and statistics-based method for finding these clumps in integrals-of-motion space for nearby halo stars and to evaluate their significance robustly. Methods. We used data from Gaia EDR3, extended with radial velocities from ground-based spectroscopic surveys, to construct a sample of halo stars within 2.5 kpc from the Sun. We applied a hierarchical clustering method that makes exhaustive use of the single linkage algorithm in three-dimensional space defined by the commonly used integrals of motion energy E, together with two components of the angular momentum, L z and L ⊥ . To evaluate the statistical significance of the clusters, we compared the density within an ellipsoidal region centred on the cluster to that of random sets with similar global dynamical properties. By selecting the signal at the location of their maximum statistical significance in the hierarchical tree, we extracted a set of significant unique clusters. By describing these clusters with ellipsoids, we estimated the proximity of a star to the cluster centre using the Mahalanobis distance. Additionally, we applied the HDBSCAN clustering algorithm in velocity space to each cluster to extract subgroups representing debris with different orbital phases. Results. Our procedure identifies 67 highly significant clusters (> 3σ), containing 12% of the sources in our halo set, and 232 subgroups or individual streams in velocity space. In total, 13.8% of the stars in our data set can be confidently associated with a significant cluster based on their Mahalanobis distance. Inspection of the hierarchical tree describing our data set reveals a complex web of relations between the significant clusters, suggesting that they can be tentatively grouped into at least six main large structures, many of which can be associated with previously identified halo substructures, and a number of independent substructures. This preliminary conclusion is further explored in a companion paper, in which we also characterise the substructures in terms of their stellar populations. Conclusions. Our method allows us to systematically detect kinematic substructures in the Galactic stellar halo with a data-driven and interpretable algorithm. The list of the clusters and the associated star catalogue are provided in two tables available at the CDS.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2023

Evaluation of Portable Programming Models to Accelerate LArTPC Detector Simulations

The Liquid Argon Time Projection Chamber (LArTPC) technology is widely used in high energy physics experiments, including the upcoming Deep Underground Neutrino Experiment (DUNE). Accurately simulating LArTPC detector responses is essential for analysis algorithm development and physics model interpretations. Accurate LArTPC detector response simulations are computationally demanding, and can become a bottleneck in the analysis workflow. Compute devices such as General-Purpose Graphics Processing Units (GPGPUs) have the potential to substantially accelerate simulations compared to traditional CPU-only processing. The software development for these compute accelerators often carries the cost of specialized code refactorization and porting to match the target hardware architecture. With the rapid evolution and increased diversity of the computer architecture landscape, it is highly desirable to have a portable solution that also maintains reasonable performance. We report our ongoing effort in evaluating Kokkos as a basis for this portable programming model using LArTPC simulations in the context of the Wire-Cell Toolkit, a C++ library for LArTPC simulations, data analysis, reconstruction and visualization.

47 OTHER INSTRUMENTATION↗
DOE OSTI2022

Transactional Knowledge Graph Generation To Model Adversarial Activities

A Knowledge Graph (KG) is a formal and structured representation of facts, relationships, and semantic descriptions of a set of entities. Traditionally, KGs are used to describe metadata about entities and to provide additional context to target application results. Many real-world domains also involve temporal interactions between entities in addition to the metadata data. Modeling these attributed transactions is a critical requirement when using KGs in complex real-world applications. Modeling adversarial activities is one such application that develops methodology and tools to produce realistic large-scale background activity graphs that include embedded Weapons of Mass Destruction (WMD) activity patterns. We present a novel platform for constructing a transactional knowledge graph from a diverse set of sources. We present the core components and architecture of the framework, and a use case for generating a background knowledge graph and WMD activity template to evaluate network alignment and subgraph matching algorithms.

Purohit, Sumit↗
NASA NTRS2017

MapX An In Situ, Full-frame X-Ray Spectroscopic Imager for Planetary Science and Astrobiology

Microbial life exploits micron-scale disequilibria at boundaries where valence, chemical potential, pH, Eh, etc. vary on a length scale commensurate with the organisms - 10's to 100's of microns. The detection of accumulations of the biogenic elements C,N,O,P,S at appropriate concentrations on or in a mineral/ice substrate would constitute permissive evidence of extant life, but context is also required. Does the putative biosignature exist under habitable conditions? Under what conditions of P, T, and chemical potential was the host mineralogy formed? MapX is an in situ robotic spacecraft instrument that images the biogenic elements C, N, O, P, S, as well as the cations of the rock-forming minerals (Na, Mg, Al, Si, K, Ca, Ti, Cr, Mn, Fe) and important anions such as Cl, Fl. MapX provides element maps with less than or equal to100 microns resolution over a 2.5 cm X 2.5 cm area, as well as quantitative XRF spectra from ground- or instrument-selected Regions of Interest (ROI). XRF spectra are converted to mineralogies using ground- or instrument-based algorithms. Either X-ray tube or radioisotope sources such as 244Cm (Alpha-particle and gamma- ray fluorescence) can be used. Fluoresced sample Xrays are imaged onto an X-ray sensitive CCD through an X-ray MicroPore Optic (MPO). The MapX design as well as baseline performance requirements for a MapX instrument intended for life detection / identification of habitable environments will be presented.

Astrobiology↗
NASA NTRS2022

A Census of Young Stellar Objects in Two Line-of-Sight Star-Forming Regions Toward IRAS 22147+5948 in the Outer Galaxy

Context. Star formation in the outer Galaxy, namely, outside of the Solar circle, has not been extensively studied in part due to the low CO brightness of the molecular clouds linked with the negative metallicity gradient. Recent infrared surveys provide an overview of dust emission in large sections of the Galaxy, but they suffer from cloud confusion and poor spatial resolution at far-infrared wavelengths. Aims. We aim to develop a methodology to identify and classify young stellar objects (YSOs) in star-forming regions in the outer Galaxy and use it to resolve a long-standing disparity in terms of the distance and evolutionary status of IRAS 22147+5948. Methods. We used a support vector machine learning algorithm to complement standard color–color and color–magnitude diagrams in our search for YSOs in the IRAS 22147 region, based on publicly available data from the Spitzer Mapping of the Outer Galaxy survey. The agglomerative hierarchical clustering algorithm was used to identify clusters. Then the physical properties of individual YSOs were calculated. The distances were determined using CO 1–0 from the Five College Radio Astronomy Observatory survey. Results. We identified 13 Class I and 13 Class II YSO candidates using the color–color diagrams, along with an additional 2 and 21 sources, respectively, using the applied machine learning techniques. The spectral energy distributions of 23 sources were modeled with a star and a passive disk, corresponding to Class II objects. The models of three sources include envelopes that are typical for Class I objects. The objects were grouped into two clusters located at a distance of 2:2 kpc and 5 clusters at 5:6 kpc. The spatial extent of CO, radio continuum, and dust emission confirms the origin of YSOs in two distinct star-forming regions along a similar line of sight. Conclusions. The outer Galaxy may serve as a unique laboratory for exploring star formation across environments, on the condition that complementary methods and ancillary data are used to properly account for cloud confusion and distance uncertainties.

Agata Karska↗
DOE OSTI2023

Computationally Efficient Control Co-Design Optimization Framework with Mixed-Fidelity Fluid and Structure Analysis: OpenTurbineCoDe (OTCD) - ARPA-E ATLANTIS Phase I Project (Final Technical Report)

The goal of the Department of Energy (DOE) Advanced Research Projects Agency-Energy (ARPA-E) Aerodynamic Turbines Lighter and Afloat with Nautical Technologies and Integrated Servo-control (ATLANTIS) Program is to develop new technologies for floating offshore wind turbines, or wind farms, using the discipline of control co-design (CCD.) In this context, our goal is to develop a computationally efficient optimization framework for design of floating offshore wind turbines. Our specific aim is to utilize high-fidelity structural, aerodynamic, aero-structural tools, and to derive control-oriented reduced- or low-order models directly from the high-fidelity tools. We proposed a mixed-fidelity modeling approach which means that we are also using low- and mid-fidelity tools when necessary. This research is conducted by a multidisciplinary team consisting of Rutgers University, University of Michigan, Brigham Young University, and the National Renewable Energy Laboratory (NREL). The computational framework, called OpenTurbineCoDe, is designed to integrate, where possible, traditional structural, aerodynamic, aeroelastic models (e.g., OpenFAST) and advanced control algorithms with higher fidelity simulation tools including Reynolds-averaged Navier–Stokes (RANS) solvers, and three-dimensional structural finite element solvers. All the high-fidelity tools used in this research provide numerically exact gradients to facilitate both efficient optimization and local linearization for control implementation.

17 WIND ENERGY↗
DOE OSTI2023

Role of reinforcement learning for risk-based robust control of cyber-physical energy systems

Critical infrastructures such as cyber-physical energy systems (CPS-E) integrate information flow and physical operations that are vulnerable to natural and targeted failures. Safe, secure, and reliable operation and control of CPS-E is critical to ensure societal well-being and economic prosperity. Automated control is key for real-time operations and may be mathematically cast as a sequential decision-making problem under uncertainty. Emergence of data-driven techniques for decision making under uncertainty, such as reinforcement learning (RL), have led to promising advances for addressing sequential decision-making problems for risk-based robust CPS-E control. However, existing research challenges include understanding the applicability of RL methods across diverse CPS-E applications, addressing the effect of risk preferences across multiple RL methods, and development of open-source domain-aware simulation environments for RL experimentation within a CPS-E context. This article systematically analyzes the applicability of four types of RL methods (model-free, model-based, hybrid model-free and model-based, and hierarchical) for risk-based robust CPS-E control. Problem features and solution stability for the RL methods are also discussed. We demonstrate and compare the performance of multiple RL methods under different risk specifications (risk-averse, risk-neutral, and risk-seeking) through the development and application of an open-source simulation environment. Motivating numerical simulation examples include representative single-zone and multizone building control use cases. Finally, six key insights for future research and broader adoption of RL methods are identified, with specific emphasis on problem features, algorithmic explainability, and solution stability.

24 POWER TRANSMISSION AND DISTRIBUTION↗
NASA NTRS1989

Zonal multigrid solution of compressible flow problems on unstructured and adaptive meshes

The simultaneous use of adaptive meshing techniques with a multigrid strategy for solving the 2-D Euler equations in the context of unstructured meshes is studied. To obtain optimal efficiency, methods capable of computing locally improved solutions without recourse to global recalculations are pursued. A method for locally refining an existing unstructured mesh, without regenerating a new global mesh is employed, and the domain is automatically partitioned into refined and unrefined regions. Two multigrid strategies are developed. In the first, time-stepping is performed on a global fine mesh covering the entire domain, and convergence acceleration is achieved through the use of zonal coarse grid accelerator meshes, which lie under the adaptively refined regions of the global fine mesh. Both schemes are shown to produce similar convergence rates to each other, and also with respect to a previously developed global multigrid algorithm, which performs time-stepping throughout the entire domain, on each mesh level. However, the present schemes exhibit higher computational efficiency due to the smaller number of operations on each level.

Mavriplis, Dimitri J.↗
DOE OSTI2025

An improved guess for the variational calculation of charge-transfer excitations in large systems

Ab initio quantum-chemical methods that perform well for computing the electronic ground state are not straightforwardly transferable to electronically excited states, particularly in large molecular systems. Wave function theory offers high accuracy, but is often prohibitively expensive. Methods based on time-dependent density functional theory (TD-DFT) are crucially sensitive to the chosen exchange-correlation functional (XCF) parameterization, and system-specific tuning protocols were therefore proposed to address the method's robustness. Methods based on the variational relaxation of the excited-state electron density showcased promising results for the calculation of charge-transfer excitations, but the complex shape of the electronic hypersurface makes convergence to a specific excited state much more difficult than for the ground state when standard variational techniques are applied. We address the latter aspect by providing suitable initial guesses, which we obtain by two separate constrained algorithms. Combined with the squared-gradient minimization algorithm for all-electrons relaxation in a freeze-and-release scheme (FRZ-SGM), we demonstrate that orbital-optimized density functional theory (OO-DFT) calculations can reliably converge to the charge-transfer states of interest even for large molecular systems. We test the FRZ-SGM method on a phenothiazine-anthraquinone CT excitation in a supramolecular Pd(II) coordination cage complex as a function of the cage conformation. This compound has been studied experimentally prior to our work. We compare this freeze-and-release scheme to two XCF reparameterizations, which were recently proposed as low-cost TD-DFT-based alternatives to variational methods. Two dye-semiconductor complexes, which were previously investigated in the context of photovoltaic applications, serve as a second example to investigate the convergence and stability of the FRZ-SGM approach. Our results demonstrate that FRZ-SGM provides reliable convergence for charge-transfer excited states and avoids variational collapse to lower-lying electronic states, whereas time-dependent DFT calculations with an adequate tuning procedure for the range-separation parameter provide a computationally efficient initial estimate of the corresponding energies, with a computational cost comparable to that of configuration-interaction singles (CIS) calculations.

Bogo, Nicola↗
NASA NTRS2024

Recommendations on Evidence and Process for Certification of Learning-enabled Components in Aerospace Systems

This report primarily identifies a collection of relevant and necessary evidence for assurance of machine learnt components (MLCs)—also known as learning-enabled components—integrated into aircraft systems, and gives preliminary suggestions on the elements of a certification process that invoke the identified evidence. The main focus is on feedforward neural networks that are static and trained offline through supervised learning. A brief background on the generic elements of the lifecycle of an MLC is given to contextualize the assurance considerations and, consequently, the evidence that is relevant and necessary to support certification. At the level of an MLC, those considerations relate to: (i) the consistency and correctness of MLC contributions to system functions in the context of a validated functional intent; and (ii) the absence of MLC contributions to aircraft-level failure conditions. At an ML model level, confidence in model and data properties contribute to assurance of the containing MLC, in particular: (a) generalizability and robustness of models, in the presence of inputs not previously seen during training, disturbances to inputs, and unexpected inputs; and (b) valid data, i.e., data that are at least representative, relevant, complete, and accurate. Evidence for the above span the elements of the ML lifecycle, and includes, at a minimum, lifecycle artifacts that pertain to: (1) properties of requirements capturing functional intent, safety constraints, and aspects of the intended use and operating environment; (2) model performance, model complexity and design, and algorithm choice; (3) achievement of required performance at the levels of a trained model during model development, a trained model after model development is complete, and a trained model that is transformed into an executable equivalent; (4) model implementation aspects necessary for transforming a trained model into the executable equivalent; (5) integration of the executable trained model into the containing MLC, and eventually the larger system; and, (6) lastly, the verification and validation (V&V) of each of the above. Such V&V lifecycle artifacts themselves include: aspects of coverage, e.g., of various levels of requirements by the input space of the model and the data; traceability (where applicable); application of formal methods for property specification, analysis, and checking. Examples of evidence generation methods and tools further ground the discussion on what constitutes evidence, and the contribution to assurance during certification. The identified assurance considerations and supporting evidence is not a comprehensive set. Additionally, neither what should be considered as sufficient evidence relative to the assigned criticality of an MLC, nor how criticality ought to be determined and adjusted, have been considered in this report. However, suggestions are made for potential activities of the ML lifecycle that are aimed at providing confidence that an MLC can be relied upon when integrated into its containing (aircraft) system. Those activities are proposed as candidate elements of a certification process for MLCs. The main purpose of this report to inform regulatory guidance and consensus standards that may be used to meet the safety intent of the applicable regulations.

Aviation safety↗
NASA NTRS2020

An AeroCom–AeroSat study: intercomparison of satellite AOD datasets for aerosol model evaluation

To better understand and characterize current uncertainties in the important observational constraint of climate models of aerosol optical depth (AOD), we evaluate and intercompare 14 satellite products, representing nine different retrieval algorithm families using observations from five different sensors on six different platforms. The satellite products (super-observations consisting of 1°×1° daily aggregated retrievals drawn from the years 2006, 2008 and 2010) are evaluated with AErosol RObotic NETwork (AERONET) and Maritime Aerosol Network (MAN) data. Results show that different products exhibit different regionally varying biases (both under- and overestimates) that may reach ±50 %, although a typical bias would be 15 %–25 % (depending on the product). In addition to these biases, the products exhibit random errors that can be 1.6 to 3 times as large. Most products show similar performance, although there are a few exceptions with either larger biases or larger random errors. The intercomparison of satellite products extends this analysis and provides spatial context to it. In particular, we show that aggregated satellite AOD agrees much better than the spatial coverage (often driven by cloud masks) within the 1°×1° grid cells. Up to ∼50 % of the difference between satellite AOD is attributed to cloud contamination. The diversity in AOD products shows clear spatial patterns and varies from 10 % (parts of the ocean) to 100 % (central Asia and Australia). More importantly, we show that the diversity may be used as an indication of AOD uncertainty, at least for the better performing products. This provides modellers with a global map of expected AOD uncertainty in satellite products, allows assessment of products away from AERONET sites, can provide guidance for future AERONET locations and offers suggestions for product improvements. We account for statistical and sampling noise in our analyses. Sampling noise, variations due to the evaluation of different subsets of the data, causes important changes in error metrics. The consequences of this noise term for product evaluation are discussed.

Aerosol↗