Search NASA⌕ Search

SEARCH · Search NASA

Results for “local binary patterns”

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.

47 records · Page 3

Liquid metal alloy ion sources—An alternative for focussed ion beam technology

Today, Focused Ion Beam (FIB) processing is nearly exclusively based on gallium Liquid Metal Ion Sources (LMIS). But, many applications in the μm- or nm range could benefit from ion species other than gallium: local ion implantation, ion beam mixing, ion beam synthesis, or Focused Ion Beam Lithography (IBL). Therefore, Liquid Metal Alloy Ion Sources (LMAIS) represent a promising alternative to expand the remarkable application fields for FIB. Especially, the IBL process shows potential advantages over, e.g., electron beam or other lithography techniques: direct, resistless, and three-dimensional patterning, enabling a simultaneous in-situ process control by cross-sectioning and inspection. Taking additionally into account that the used ion species influences significantly the physical and chemical nature of the resulting nanostructures—in particular, the electrical, optical, magnetic, and mechanic properties leading to a large potential application area which can be tuned by choosing a well suited LMAIS. Nearly half of the elements of the periodic table are recently available in the FIB technology as a result of continuous research in this area during the last forty years. Key features of a LMAIS are long life-time, high brightness, and stable ion current. Recent developments could make these sources feasible for nano patterning issues as an alternative technology more in research than in industry. The authors will review existing LMAIS, LMIS other than Ga, and binary and ternary alloys. These physical properties as well as the fabrication technology and prospective domains for modern FIB applications will similarly be reviewed. Other emerging ion sources will be also presented and their performances discussed.

36 MATERIALS SCIENCE↗

FREEZE-OUT YIELDS OF RADIOACTIVITIES IN CORE-COLLAPSE SUPERNOVAE

We explore the nucleosynthesis trends from two mechanisms during freeze-out expansions in core-collapse supernovae. The first mechanism is related to the convection and instabilities within homogeneous stellar progenitor matter that is accreted through the supernova shock. The second mechanism is related to the impact of the supersonic wind termination shock (reverse shock) within the tumultuous inner regions of the ejecta above the proto-neutron star. Our results suggest that isotopes in the mass range 12 {<=} A {<=} 122 that are produced during the freeze-out expansions may be classified in two families. The isotopes of the first family manifest a common mass fraction evolutionary profile, whose specific shape per isotope depends on the characteristic transition between two equilibrium states (equilibrium state transition) during each type of freeze-out expansion. The first family includes the majority of isotopes in this mass range. The second family is limited to magic nuclei and isotopes in their locality, which do not sustain any transition, become nuclear flow hubs, and dominate the final composition. We use exponential and power-law adiabatic profiles to identify dynamic large-scale and small-scale equilibrium patterns among nuclear reactions. A reaction rate sensitivity study identifies those reactions that are crucial to the synthesis of radioactivities in the mass range of interest. In addition, we introduce non-monotonic parameterized profiles to probe the impact of the reverse shock and multi-dimensional explosion asymmetries on nucleosynthesis. Cases are shown in which the non-monotonic profiles favor the production of radioactivities. Non-monotonic freeze-out profiles involve longer non-equilibrium nucleosynthesis intervals compared with the exponential and power-law profiles, resulting in mass fraction trends and yield distributions that may not be achieved by the monotonic freeze-out profiles.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

On visualizing material flow and precipitate evolution during probeless friction stir spot welding of an Al-Li alloy

Highlights: • Severe thermal cycle and deformation refined grains and intermetallic particles in SZ. • T{sub 1} phases fully dissolved in SZ followed by re-precipitation of GP zone and δ′ phases. • The predominant flow direction remained in spiral-like pattern during P-FSSW. • Local abrasion existed in the lap-weld interface due to flow difference, forming joining. - Abstract: The precipitate evolution and material flow visualization during probeless friction stir spot welding (P-FSSW) of an Al-Li alloy has been investigated experimentally and numerically in this work. Due to severe heat input during welding, the main strengthening phases of T{sub 1} fully dissolved in the stir zone followed by the re-precipitation of GP zone and δ′ phases, assisted with the refinement of the intermetallic particles and grains. The history of material flow was three-dimensionally visualized with a tracer, studied with X-ray tomography. The experiments and the simulation results provided a consistent interpretation of a circumferential material flow which moved inwards radially near the top surface. Upward flow in the bottom sheet improved with dwell time, causing the interface to bend. Local abrasion between the two sheets due to flow difference led to the disruption of oxide layer, and formed a connection at the interface.

36 MATERIALS SCIENCE↗

THE M81 GROUP DWARF IRREGULAR GALAXY DDO 165. II. CONNECTING RECENT STAR FORMATION WITH INTERSTELLAR MEDIUM STRUCTURES AND KINEMATICS

We compare the stellar populations and complex neutral gas dynamics of the M81 group dIrr galaxy DDO 165 using data from the Hubble Space Telescope and the Very Large Array. Cannon et al. in Paper I of this series identified two kinematically distinct H I components, multiple localized high velocity gas features, and eight H I holes and shells (the largest of which spans {approx}2.2 x 1.1 kpc). Using the spatial and temporal information from the stellar populations in DDO 165, we compare the patterns of star formation (SF) over the past 500 Myr with the H I dynamics. We extract localized star formation histories within 6 of the 8 H I holes identified in Paper I, as well as 23 other regions that sample a range of stellar densities and neutral gas properties. From population synthesis modeling, we derive the energy outputs (from stellar winds and supernovae) of the stellar populations within these regions over the last 100 Myr, and compare with refined estimates of the energies required to create the H I holes. In all cases, we find that 'feedback' is energetically capable of creating the observed structures in the interstellar medium (ISM). Numerous regions with significant energy inputs from feedback lack coherent H I structures but show prominent localized high velocity gas features; this feedback signature is a natural product of temporally and spatially distributed SF. In DDO 165, the extended period of heightened SF activity (lasting more than 1 Gyr) is energetically capable of creating the observed holes and high velocity gas features in the neutral ISM.

79 ASTRONOMY AND ASTROPHYSICS↗

Phase-field model of freeze casting

Directional solidification of water-based solutions has emerged as a versatile technique for templating hierarchical porous materials. However, the underlying mechanisms of pattern formation remain incompletely understood. In this work, we present a detailed derivation and analysis of a quantitative phase-field model for simulating this nonequilibrium process. The phase-field model extends the thin-interface formulation of dilute binary alloy solidification with antitrapping to incorporate the highly anisotropic energetic and kinetic properties of the partially faceted ice-water interface. This interface is faceted in the basal plane normal to the ⟨0001⟩ directions and atomically rough in other directions within the basal plane. On the basal plane, the model reproduces a linear or nonlinear relationship between the interface growth rate and the kinetic undercooling that can be linked to experimental measurements. In both cases, spontaneous parity breaking of the solidification front is observed when the preferred growth direction is aligned with the temperature gradient. This phenomenon leads to the formation of partially faceted ice lamellae that drift laterally in one of the ⟨0001⟩ directions. Here, we demonstrate that the drifting velocity of the ice lamellae is controlled by the kinetics on the basal plane and converges as the thickness of the diffuse solid-liquid interface decreases. Furthermore, we examine the effect of the form of the kinetic anisotropy, which is chosen here such that the inverse of the kinetic coefficient varies linearly from a finite value in the ⟨0001⟩ directions to zero in all other directions within the basal plane, consistent with the assumption that the interface grows in local thermodynamic equilibrium in this plane. Our results indicate that the drifting velocity of ice lamellae is not affected by the slope of this linear relation, and the radius and undercooling at the tip of an ice lamella converge at relatively small slope values. Consequently, the phase-field simulations remain quantitative with computationally tractable choices of both the interface thickness and the slope assumed in the form of the kinetic anisotropy.

Materials science↗

Geometric control of magnetic domain morphology in electrodeposited Ni rich NiPt mesoscopic wires

In this paper, we study the electrodeposited Ni—Pt magnetic wires, exploring the mechanisms by which changes in geometry and composition influence the local magnetic structure. The samples were prepared by electrodeposition, their elemental composition was analyzed by energy dispersive X-ray spectroscopy, and phase analysis was carried out by an X-ray diffraction measurement. Magnetic force microscopy measurements, and magnetic force microscopy measurements in magnetic field were carried out to study the domain morphology of the prepared samples. Magnetization characteristics were measured via vibrating sample magnetometry mode of a superconducting quantum interference device. Here, the results were analyzed and compared with micromagnetic simulations. It is shown that a strong perpendicular magnetic anisotropy is responsible for the characteristic checkerboard-like surface magnetization patterns, which can be tuned by geometrical constriction and Ni content. Understanding these relationships provides insights into the design of magnetic materials with tailored properties for advanced applications, like magnetic sensors.

Binary alloy↗

IMAGING ANALYSIS OF THE HARD X-RAY TELESCOPE ProtoEXIST2 AND NEW TECHNIQUES FOR HIGH-RESOLUTION CODED-APERTURE TELESCOPES

Wide-field (≳100 deg{sup 2}) hard X-ray coded-aperture telescopes with high angular resolution (≲2′) will enable a wide range of time domain astrophysics. For instance, transient sources such as gamma-ray bursts can be precisely localized without the assistance of secondary focusing X-ray telescopes to enable rapid followup studies. On the other hand, high angular resolution in coded-aperture imaging introduces a new challenge in handling the systematic uncertainty: the average photon count per pixel is often too small to establish a proper background pattern or model the systematic uncertainty in a timescale where the model remains invariant. We introduce two new techniques to improve detection sensitivity, which are designed for, but not limited to, a high-resolution coded-aperture system: a self-background modeling scheme which utilizes continuous scan or dithering operations, and a Poisson-statistics based probabilistic approach to evaluate the significance of source detection without subtraction in handling the background. We illustrate these new imaging analysis techniques in high resolution coded-aperture telescope using the data acquired by the wide-field hard X-ray telescope ProtoEXIST2 during a high-altitude balloon flight in fall 2012. We review the imaging sensitivity of ProtoEXIST2 during the flight, and demonstrate the performance of the new techniques using our balloon flight data in comparison with a simulated ideal Poisson background.

79 ASTRONOMY AND ASTROPHYSICS↗

FleCSPH notes

FleCSI is a compile-time con gurable framework designed to support multi-physics application development. As such, FleCSI provides a very general set of infrastructure design patterns that can be specialized and extended to suit the needs of a broad variety of solver and data requirements. FleCSI currently supports multi-dimensional mesh topology, geometry, and adjacency information, as well as n-dimensional hashed-tree data structures, graph partitioning interfaces, and dependency closures. FleCSI introduces a functional programming model with control, execution, and data abstractions that are consistent both with MPI and with state-of-the-art, task-based runtimes such as Legion and Charm++. The abstraction layer insulates developers from the underlying runtime, while allowing support for multiple runtime systems including conventional models like asynchronous MPI. The intent is to provide developers with a concrete set of user-friendly programming tools that can be used now, while allowing exibility in choosing runtime implementations and optimization that can be applied to future architectures and runtimes. FleCSI's control and execution models provide formal nomenclature for describing poorly understood concepts such as kernels and tasks. FleCSI's data model provides a low-buy-in approach that makes it an attractive option for many application projects, as developers are not locked into particular layouts or data structure representations. FleCSI currently provides a parallel but not distributed implementation of Binary, Quad and Oct-tree topology. This implementation is base on space lling curves domain decomposition, the Morton order. The current FleCSI version requires the implementation of a driver and a specialization driver. The role of the specialization driver is to provide the data distribution. This feature is not complete in FleCSI code and we provide it. The next step will be to incorporate it directly from FleCSPH to FleCSI as we reach a good level of performance. Then the driver represent the general execution of the resolution without worrying of the data locality and communications. As FleCSI is an On-Development code the structure may change in the future and we keep track of these changes in FleCSPH.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

Unveiling the chemical fingerprint of phosphorus-rich stars: I. In the infrared region of APOGEE-2

The origin of phosphorus, one of the essential elements for life on Earth, is currently unknown. Prevalent models of Galactic chemical evolution (GCE) systematically underestimate the amount of P compared to observations, especially at low metallicities. The recently discovered P-rich ([P/Fe] ≳ 1.2 dex) and metal-poor ([Fe/H] ≃ –1.0 dex) giants further challenge the GCE models, calling current theories on stellar nucleosynthesis into question. Since the observed low-mass giants are not expected to produce their high P contents themselves, our primary goal is to find clues on their progenitor or polluter. By increasing the number of known P-rich stars, we aim to narrow down a statistically reliable chemical abundance pattern that defines these peculiar stars. In this way, we place more robust constraints on the nucleosynthetic mechanism that causes the unusually high P abundances. In the long term, identifying the progenitor of the P-rich stars may contribute to the search for the source of P in our Galaxy. We performed a detailed chemical abundance analysis based on the high-resolution near-infrared (H band) spectra from the latest data release (DR17) of the APOGEE-2 survey. Employing the BACCHUS code, we measured the abundances of 13 elements in the inspected sample, which is mainly composed of a recent collection of Si-enhanced giants. We also analyzed the orbital motions and compared the abundance results to possible nucleosynthetic formation scenarios, and also to detailed GCE models. These models were produced with the OMEGA+ chemical evolution code, using four different massive star yield sets to investigate different scenarios for massive star evolution. We enlarged the sample of confirmed P-rich stars from 16 to a group of 78 giants, which represents the largest sample of P-rich stars to date. The sample includes the first detection of a P-rich star in a Galactic globular cluster. Significant enhancements in O, Al, Si, and Ce, as well as systematic correlations among the studied elements, unveil the unique chemical fingerprint of the P-rich stars. In contrast, the high [Mg/Fe] and [(C+N)/Fe] found in some of the P-rich stars with respect to P-normal stars is not confirmed over the full sample because of the current uncertainties. Strikingly, the strong overabundance in the α-element Si is accompanied by normal Ca and S abundances. This is at odds with current stellar nucleosynthesis models of massive stars. Our analysis of the orbital motion showed that the P-rich stars do not belong to a locally specific population in the Galaxy. In addition, we confirm that the majority of the sample stars are not part of binary systems.

79 ASTRONOMY AND ASTROPHYSICS↗

SIMULATIONS OF WINDS OF WEAK-LINED T TAURI STARS. II. THE EFFECTS OF A TILTED MAGNETOSPHERE AND PLANETARY INTERACTIONS

Based on our previous work, we investigate here the effects on the wind and magnetospheric structures of weak-lined T Tauri stars due to a misalignment between the axis of rotation of the star and its magnetic dipole moment vector. In such a configuration, the system loses the axisymmetry presented in the aligned case, requiring a fully three-dimensional (3D) approach. We perform 3D numerical magnetohydrodynamic simulations of stellar winds and study the effects caused by different model parameters, namely the misalignment angle {theta}{sub t}, the stellar period of rotation, the plasma-{beta}, and the heating index {gamma}. Our simulations take into account the interplay between the wind and the stellar magnetic field during the time evolution. The system reaches a periodic behavior with the same rotational period of the star. We show that the magnetic field lines present an oscillatory pattern. Furthermore, we obtain that by increasing {theta}{sub t}, the wind velocity increases, especially in the case of strong magnetic field and relatively rapid stellar rotation. Our 3D, time-dependent wind models allow us to study the interaction of a magnetized wind with a magnetized extrasolar planet. Such interaction gives rise to reconnection, generating electrons that propagate along the planet's magnetic field lines and produce electron cyclotron radiation at radio wavelengths. The power released in the interaction depends on the planet's magnetic field intensity, its orbital radius, and on the stellar wind local characteristics. We find that a close-in Jupiter-like planet orbiting at 0.05 AU presents a radio power that is {approx}5 orders of magnitude larger than the one observed in Jupiter, which suggests that the stellar wind from a young star has the potential to generate strong planetary radio emission that could be detected in the near future with LOFAR. This radio power varies according to the phase of rotation of the star. For three selected simulations, we find a variation of the radio power of a factor 1.3-3.7, depending on {theta} {sub t}. Moreover, we extend the investigation done in Vidotto et al. and analyze whether winds from misaligned stellar magnetospheres could cause a significant effect on planetary migration. Compared to the aligned case, we show that the timescale {tau}{sub w} for an appreciable radial motion of the planet is shorter for larger misalignment angles. While for the aligned case {tau}{sub w} {approx_equal} 100 Myr, for a stellar magnetosphere tilted by {theta}{sub t} = 30{sup 0}, {tau} {sub w} ranges from {approx}40 to 70 Myr for a planet located at a radius of 0.05 AU. Further reduction on {tau}{sub w} might occur for even larger misalignment angles and/or different wind parameters.

79 ASTRONOMY AND ASTROPHYSICS↗

A Machine Learning Approach to Improve Air Traffic Management Initiatives

Collaborating closely with commercial air carriers and related organizations, the Federal Aviation Administration(FAA) regulates air traffic and ensures the safety and efficiency of air operations. Air traffic controllers make strategic decisions, such as delaying, rerouting, or canceling flights, partly based on guidance provided by the FAA’s Air TrafficControl System Command Center (ATCSCC). The guidance includes, among other things, control measures known asTraffic Management Initiatives (TMIs) designed to enhance safety and improve operational efficiency. TMIs play a crucial role in managing the demand and capacity within the U.S. National Airspace System (NAS). Two major TMIs that are routinely used (primarily to mitigate the adverse effects of bad weather) are Ground Delay Programs (GDPs) andGround Stops (GSs). In a GDP, flights destined for airports facing thunderstorm activity experience delays at their origin airports. This proactive approach minimizes the risk of routing aircraft through hazardous weather conditions and also replaces (fuel burning) airborne delays with ground delays. In a GS, a temporary restriction is imposed on the departure or arrival of aircraft at a specific airport or within a designated airspace. Although other TMIs (e.g., miles-in-trail) are also implemented as part of (air) traffic flow management in the NAS, the focus of this work is on GDPs and GSs. Since TMIs, by design, lead to flight delays or cancellations, it is crucial to put in place the right set of parameters(e.g., scope and duration of the GDP). For example, when the end time of a GDP extends beyond what is necessary, it imposes unnecessary delays on departing flights. This situation could occur as a result of inaccurate prediction of the(required) duration of the GDP based on the weather forecast. On the other hand, if a GDP ends prematurely before the underlying capacity constraints are resolved at the destination airport, it may result in airborne holding. The delicate balance lies in matching the termination of the GDP precisely with the resolution of capacity constraints, avoiding both the imposition of unnecessary ground delays and the need for airborne holding due to premature program termination.Failing to specify the right parameters for TMIs also leads to flight delays, creating a significant obstacle in managing the increasing traffic volumes causing increased work load for the controllers. To address this issue, we propose the integration of Machine Learning (ML) models in the traffic flow management(TFM) pipeline. In current operations, decisions are made by human experts based on extensive training, historical patterns, available traffic and weather data. Since we have an abundance of data from past events that tell us the likely impact of various TMIs, by ingesting historical data, properly trained ML models can offer valuable insights and aid human decision-making. With the FAA increasingly exploring advanced analytics, ML emerges as a focal point for enhancing TFM within the National Airspace System (NAS). As a first step, this study aims to provide traffic controllers with decision-making support for the issuance and adjustment of TMIs. Data analytics and machine learning have been previously employed to address some of the challenges associated with TMIs. Numerous studies have concentrated on various facets of TMI issuance, exploring factors influencing TMI parameters, including arrival rate, airport capacity, and delay prediction. For example, using weather forecasts, several statistical methods were used to produce probabilistic capacity profiles which in conjunction with deterministic models provided insights into the GDP planning process [1–4]. The downside of using deterministic models is that they rely on fixed inputs and predetermined rules, which lack the ability to account for the inherent uncertainty and variability present in real-world scenarios. In a separate series of studies, researchers aimed to predict the occurrences of GDPs and GSs. The majority of these studies utilized various supervised learning methods, including Decision Trees, Naive Bayes, Support VectorMachines, and Random Forests to analyze the influence of weather conditions and arrival demand on TMI incidents[5–8]. However, these studies primarily focused on predicting the incidence of TMIs without explicitly addressing the scope of TMIs, including their duration and their geographical coverage. Furthermore, the emphasis of these studies was largely on GDPs, given their higher frequency and longer duration when compared to GSs. A limited number of studies focused on predicting the parameters of TMIs, specifically addressing their duration and extent. In one such study focusing on optimizing the TMI parameters at San Francisco International Airport (SFO),the authors utilized a probabilistic forecast of fog [9]. They simulated various capacity scenarios based on the (fog)burn-off forecasts, selecting GDP parameters that minimized airborne and overall ground delays. However, this approach exclusively emphasizes stratus (fog) burn-off as the primary determinant of GDP and GS, neglecting other influential factors like severe weather events, runway closures, lower capacity than traffic demand, and other important variables. Given the complexity of predicting the TMI and determining its scope, we seek a more holistic approach. We aim to consider all significant factors that could impact TMIs and their parameters. What sets this research apart is the fusion of all data sources relevant to the issuance and adjustment of TMIs and it represents the first comprehensive attempt to optimize TMIs in this manner. Since this comprehensive solution involves various aspects, we break down the problem into smaller components and input all parameters into a unified model called the “TMI Adjuster”. Figure 1 shows the overall framework and the list of datasets used in each model. The objective of the TMI Adjuster module is to deliver reliable, consistent and expedited recommendations for the progression, adjustment, and termination of TMIs. The ML solution entails developing a pipeline capable of predicting the necessity of a TMI (e.g., GS or GDP) along with its various parameters. For example, in the case of a GS, this includes the scope of the GS either in terms of distance from the destination airport or based on pre-defined airspace sectors. Here, scope refers to those regions and departing airports that are subject to the GS. In this paper, we concentrate on the issuance of GSs in the three major airports in the New York area — LaGuardia(LGA), John F. Kennedy International (JFK), and Newark Liberty International (EWR). We fuse traffic, weather and other relevant aviation data from years 2017 to 2019 to train and validate the ML models. In particular, we use the following datasets: •Terminal Aerodrome Forecast (TAF): meteorological forecasts specific to each airport, issued four times a day, covering predefined time periods. •TMI data: includes all GSs and GDPs along with their respective parameters. •Aviation System Performance Metrics (ASPM): includes traffic related data such as aircraft delays, arrival, and departure rates. •Notices to Airmen (NOTAMs): utilized to extract runway closure data and manage interdependencies between terminals in close proximity. •Flight cancellation data •Airspace Flow Programs (AFP): includes information on flight airborne holdings caused by TMIs. The data preprocessing entails transforming ASPM, TMI, AFP, NOTAMs, and weather data into an hourly format and consolidating all datasets by merging them based on date and time as the primary key. The TMI Adjuster framework comprises two parallel models: one dedicated to GS and a second model focused on GDP. As previously mentioned, our specific focus is on the GS model as a multi-classification problem. In this framework, each data point of the GS model input summarizes ten hours of data. Specifically, the data loader for the GS model generates the input and output of the model as follows: at a given time step, the input includes the actual traffic, weather, and TMI data from the two-hour window before the time step, alongside the weather forecast and scheduled traffic for the next 8 hours starting from the time step. Based on this information, the output of the GS model for each time interval consists of three dimensions. The first dimension represents a binary decision on whether there should be a GS in place for the next hour or not. The second dimension is related to the scope of the GS in the United States, and the third dimension is related to the scope of the GS in Canada (i.e., to determine if the GS impacts airports in Canada).One of the challenges with TMI modeling is the sparsity of TMI events, particularly regarding its scope. To address this challenge in the scope of the GS model output, we implement grouping. The GS scope for the US region is defined based on a list of centers that should be included when the GS is in place. With 20 centers in the US, we utilized historical data to group them into 4 categories. In particular, we summarized our historical data in a graph format where nodes represent centers, and link weights are defined based on the co-occurrence of centers in the scope parameter ofTMIs. By identified strongly connected components in this graph, we were able to partition the centers into four groups. We consider two model structures for the GS Model. Firstly, a hierarchical classification model [10], where the human decision-making for a GS is of hierarchical nature. The decision-maker first decides whether there is a need fora GS, and if the answer is yes, determines the scope. A hierarchical classification model organizes the problem into a class hierarchy, typically a tree or a Directed Acyclic Graph (DAG) structure, and considers the dependency of the decision in the previous step to the next component [10]. Here, we employ the local classifier per level approach, which involves training one multi-class classifier for each level of the class hierarchy. The second structure is the independent structure. In this setting, as the name suggests, we do not consider the dependency of the decisions in the different dimensions of the output of the model. Instead, for each dimension, we train a multi-class classifier independently. Table 1 summarizes GS model statistics for training, validation and testing. The table documents the effect of limiting data to the time steps when there was actually a TMI in place or when a TMI had just terminated. This resulted in a more balanced distribution of the GS class(GS positive class)versus “No GS”(GS negative class), which might help the training process. While JFK and LGA follow very similar distributions, with 40% and 42% GS positive class respectively, EWR has proportionally fewer GS incidents at 28%. Our subsequent phase involves evaluating the performance of both hierarchical structure and independent structure using different state-of-the-art multi-class classifier models such as Random Forest, Decision Trees, K-nearest Neighbors, and Logistic Regression and forecast the duration and scope of the GSs.

Farzan Masrour Shalmani↗