Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Analytic hierarchy process”

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.

137 records · Page 8

Simulating Electron Dynamics of Complex Molecules with Time-Dependent Complete Active Space Configuration Interaction

In this paper, time-dependent electronic structure methods are growing in popularity as tools for modeling ultrafast and/or nonlinear processes, for computing spectra, and as the electronic structure component of mean-field molecular dynamics simulations. Time-dependent configuration interaction (TD-CI) offers several advantages over the widely used real-time time-dependent density functional theory: namely, that it correctly models Rabi oscillations; it offers a spin-pure description of open-shell systems; and a hierarchy of TD-CI methods can be defined that systematically approach the exact solution of the time-dependent Schrodinger equation (TDSE). In this work, we present a novel TD-CI approach that extends TD-CI to large complete active-space configuration expansions. Such extension is enabled by use of a direct configuration interaction approach that eliminates the need to explicitly build, store, or diagonalize the Hamiltonian matrix. Graphics processing unit (GPU) acceleration enables fast solution of the TDSE even for large active spaces—up to 12 electrons in 12 orbitals (853776 determinants) in this work. A symplectic split operator propagator yields long-time norm conservation. We demonstrate the applicability of our approach by computing the response of a large molecule with a strongly correlated ground state, decacene (C 42 H 24 ), to various pulses (δ-function, transform limited, chirped). Our simulations predict that chirped pulses can be used to induce dipole-forbidden transitions. Simulations of decacene using the 6-31G(d) basis set and a 12 electrons/12 orbitals active space took 20.1 h to propagate for 100 fs with a 1 attosecond time step on a single NVIDIA K40 GPU. Convergence with respect to time step is found to depend on the property being computed and the chosen active space.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Model Parameter Development for Complex Materials: Species-Specific Diffusion Barriers in 316 Stainless Steel from Systematic DFT Calculations

Vacancy-mediated diffusion barriers in 316 stainless steel have been systematically calculated using density functional theory to provide essential parameters for mesoscale microstructure evolution models. A statistical sampling approach employing 210 nudged elastic band calculations across multiple special quasi-random structures captures the effects of local chemical environments in this concentrated alloy. The computational methodology addresses challenges specific to chemically disordered systems, including proper magnetic treatment throughout multi-step calculations and validation against experimental structural properties. The calculated activation barriers reveal clear species-dependent diffusion behavior with the hierarchy Ni >> Fe ˜ Cr >> Mo. Nickel exhibits the highest barriers (0.74–1.31 eV, mean 1.045 eV), confirming its role as the slowest-diffusing major component. Iron and chromium show similar moderate barriers averaging 0.587 eV and 0.522 eV, respectively. Remarkably, molybdenum demonstrates exceptionally low barriers (0.12–0.28 eV, mean 0.194 eV), suggesting much higher mobility than previously recognized and potentially significant implications for precipitation kinetics and microstructure evolution. The barrier ranges remain consistent across different 316 SS compositions, supporting parameter transferability for modeling applications. The overall mean barrier of 0.64 eV provides a practical approximation for phase field simulations, while species-specific values enable detailed treatments of diffusion-controlled processes. This systematic approach establishes a validated framework for generating diffusion parameters in other concentrated alloys where experimental data are limited, while providing the first systematic set of species-specific barriers for predictive modeling of 316 stainless steel microstructure evolution.

36 MATERIALS SCIENCE↗

Broadening of Modeled Cloud Droplet Spectra Using Bin Microphysics in an Eulerian Spatial Domain

This study investigates droplet size distribution (DSD) characteristics from condensational growth and transport in Eulerian dynamical models with bin microphysics. A hierarchy of modeling frameworks is utilized, including parcel, one-dimensional (1D), and three-dimensional large-eddy simulation (LES). The bin DSDs from the 1D model, which includes only vertical advection and condensational growth, are nearly as broad as those from the LES and in line with observed DSD widths for stratocumulus clouds. These DSDs are much broader than those from Lagrangian microphysical calculations within a parcel framework that serve as a numerical benchmark for the 1D tests. In contrast, the bin-modeled DSDs are similar to the Lagrangian microphysical benchmark for a rising parcel in which Eulerian transport is not considered. These results indicate that numerical diffusion associated with vertical advection is a key contributor to broadening DSDs in the 1D model and LES. This DSD broadening from vertical numerical diffusion is unphysical, in contrast to the physical mixing processes that previous studies have indicated broaden DSDs in real clouds. It is proposed that artificial DSD broadening from vertical numerical diffusion compensates for underrepresented horizontal variability and mixing of different droplet populations in typical LES configurations with bin microphysics, or the neglect of other mechanisms that broaden DSDs such as growth of giant cloud condensation nuclei. These results call into question the ability of Eulerian dynamical models with bin microphysics to investigate the physical mechanisms for DSD broadening, even though they may reasonably simulate overall DSD characteristics.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Active Flash: Performance-Energy Tradeoffs for Out-of-Core Processing on Non-Volatile Memory Devices

In this abstract, we study the performance and energy tradeoffs involved in migrating data analysis into the flash device, a process we refer to as Active Flash. The Active Flash paradigm is similar to 'active disks', which has received considerable attention. Active Flash allows us to move processing closer to data, thereby minimizing data movement costs and reducing power consumption. It enables true out-of-core computation. The conventional definition of out-of-core solvers refers to an approach to process data that is too large to fit in the main memory and, consequently, requires access to disk. However, in Active Flash, processing outside the host CPU literally frees the core and achieves real 'out-of-core' analysis. Moving analysis to data has long been desirable, not just at this level, but at all levels of the system hierarchy. However, this requires a detailed study on the tradeoffs involved in achieving analysis turnaround under an acceptable energy envelope. To this end, we first need to evaluate if there is enough computing power on the flash device to warrant such an exploration. Flash processors require decent computing power to run the internal logic pertaining to the Flash Translation Layer (FTL), which is responsible for operations such as address translation, garbage collection (GC) and wear-leveling. Modern SSDs are composed of multiple packages and several flash chips within a package. The packages are connected using multiple I/O channels to offer high I/O bandwidth. SSD computing power is also expected to be high enough to exploit such inherent internal parallelism within the drive to increase the bandwidth and to handle fast I/O requests. More recently, SSD devices are being equipped with powerful processing units and are even embedded with multicore CPUs (e.g. ARM Cortex-A9 embedded processor is advertised to reach 2GHz frequency and deliver 5000 DMIPS; OCZ RevoDrive X2 SSD has 4 SandForce controllers, each with 780MHz max frequency Tensilica core). Efforts that take advantage of the available computing cycles on the processors on SSDs to run auxiliary tasks other than actual I/O requests are beginning to emerge. Kim et al. investigate database scan operations in the context of processing on the SSDs, and propose dedicated hardware logic to speed up scans. Also, cluster architectures have been explored, which consist of low-power embedded CPUs coupled with small local flash to achieve fast, parallel access to data. Processor utilization on SSD is highly dependent on workloads and, therefore, they can be idle during periods with no I/O accesses. We propose to use the available processing capability on the SSD to run tasks that can be offloaded from the host. This paper makes the following contributions: (1) We have investigated Active Flash and its potential to optimize the total energy cost, including power consumption on the host and the flash device; (2) We have developed analytical models to analyze the performance-energy tradeoffs for Active Flash, by treating the SSD as a blackbox, this is particularly valuable due to the proprietary nature of the SSD internal hardware; and (3) We have enhanced a well-known SSD simulator (from MSR) to implement 'on-the-fly' data compression using Active Flash. Our results provide a window into striking a balance between energy consumption and application performance.

42 ENGINEERING↗

Structural and Dynamical Roles of Bound Polymer Chains in Rubber Reinforcement

The addition of nanofillers to rubber matrices is a powerful route to improve the mechanical properties. Here, we focus on a molecular understanding of basic mechanisms that are important for the reinforcement in rubbers. The key role in this process is ascribed to bound rubber (BR) that engages with the matrix as well as with adjacent nanofillers. To date, this understanding has been impeded by the lack of experimental tools to directly probe the BR chains buried in a polymer matrix composed of the same polymer. To tackle this challenge, we combine neutron scattering/spectroscopy techniques with isotope-labeling and molecular dynamics simulations. The system is a simplified carbon-black-filled polybutadiene. The combined experimental and computational results provide new insights into the local structural and dynamical heterogeneities of BR chains and their interactions with the matrix polymer, highlighting (i) the structural partition of the bound chains into three components (i.e., trains, loops, and tails) and their fractions; (ii) their dynamical hierarchies, i.e., the trains that remain immobile on the filler surface, the loops that are fairly large and hence allow the interdigitation of matrix chains, and the tails with their unique characteristics to reach far out into the matrix and entangle with matrix chains. These multiple roles of the constituent components of the BR chains promote the formation of a well-developed adhesive polymer–filler interface, enhancing the elastic property of a filled rubber. Finally, the comprehensive understanding derived and validated by the model rubber will be translatable to many other polymer nanocomposites.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Concept Lens: Visual Comparison and Evaluation of Generative Model Manipulations

Generative models are becoming a transformative technology for the creation and editing of images. However, it remains challenging to harness these models for precise image manipulation. These challenges often manifest as inconsistency in the editing process, where both the type and amount of semantic change, depend on the image being manipulated. Moreover, there exist many methods for computing image manipulations, whose development is hindered by the matter of inconsistency. This paper aims to address these challenges by improving how we evaluate, compare, and explore the space of manipulations offered by a generative model. We present Concept Lens, a visual interface that is designed to aid users in understanding semantic concepts carried in image manipulations, and how these manipulations vary over generated images. Given the large space of possible images produced by a generative model, Concept Lens is designed to support the exploration of both generated images, and their manipulations, at multiple levels of detail. To this end, the layout of Concept Lens is informed by two hierarchies: a hierarchical organization of (1) original images, grouped by their similarities, and (2) image manipulations, where manipulations that induce similar changes are grouped together. This layout allows one to discover the types of images that consistently respond to a group of manipulations, and vice versa, manipulations that consistently respond to a group of codes. We show the benefits of this design across multiple use cases, specifically, studying the quality of manipulations for a single method, and offering a means of comparing different methods.

clustering↗

Tuning 3-D Nanomaterial Architectures Using Atomic Layer Deposition to Direct Solution Synthesis

The ability to synthesize nanoarchitected materials with tunable geometries provides a means to control their functional properties, with applications in biological, environmental, and energy fields. To this end, various bottom-up and top-down synthesis processes have been developed. However, many of these processes require prepatterning or etching steps, making them challenging to scale-up to complex, nonplanar substrates. Furthermore, the ability to integrate nanomaterials into hierarchical arrays with precise control of feature spacing and orientation remains a challenge. One approach to overcome these patterning challenges is the use of surface modification layers to guide the resulting geometry of nanomaterial architectures grown from the substrate. A powerful strategy to accomplish this is what we will refer to as “surface-directed assembly,” where the resulting geometric parameters (feature size, shape, orientation) are predetermined by the initial surface layer. In particular, the use of Atomic Layer Deposition (ALD) to form a surface layer, followed by solution-based growth processes, has the ability to synthesize architected structures with tunable geometries on complex, nonplanar surfaces. Over the past decade, we have reported a series of studies where surface-directed assembly is used to synthesize ZnO nanowires (NWs) on top of a variety of substrates. In this case, a thin film of ZnO is deposited onto the substrate using ALD, which can guide the NW diameter, spacing, and angular orientation with respect to the substrate by controlling epitaxial relationships. Furthermore, we have shown that by depositing a submonolayer overcoat of a secondary material (e.g., amorphous TiO 2 ), nucleation sites are partially blocked, which can further tune the spacing between nanowires while minimizing changes to their other geometric properties. This approach can be used to generate multilevel hierarchical structures, such as hyperbranched NW arrays with tunable control of each level of hierarchy using ALD. Finally, we have demonstrated that the tunable control of geometric parameters can be scaled-up to curved, nonplanar substrates. This highlights the power of ALD to conformally and uniformly deposit the seed layers on complex substrates with subnanometer precision. To complement these seeded hydrothermal approaches, we expanded this strategy to include conversion chemistry of the initial ALD seed layers. For example, by replacing ZnO with Al 2 O 3 as the seed layer without changing the hydrothermal growth conditions, Al–Zn layered-double hydroxide nanosheets can be formed instead of nanowires. In another example of conversion chemistry, a solution anion-exchange process was used to incorporate sulfur into ALD metal oxide films. In both of these conversion processes, the properties of the initial ALD film enabled tuning of the resulting nanostructure geometry. In this Account, we describe the use of ALD to guide the growth of diverse nanomaterial systems, with tunable control over their geometry and composition. We further show how these approaches can be used to tune functional properties for a range of applications, including superomniphobic surfaces, antibiofouling coatings, and photocatalysis. In conclusion, we conclude with an outlook on how the combination of ALD and solution synthesis can enable future directions in scalable nanomanufacturing to overcome the limitations of traditional top-down and bottom-up approaches.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Digital Maskless Photolithographic Patterning of DNA-Functionalized Poly(ethylene glycol) Diacrylate Hydrogels with Visible Light Enabling Photodirected Release of Oligonucleotides

Soft biomaterials possessing structural hierarchy have growing applications in lab-on-chip devices, artificial tissues, and micromechanical and chemomechanical systems. The ability to integrate sets of biomolecules, specifically DNA, within hydrogel substrates at precise locations could offer the potential to form and modulate complex biochemical processes with DNA-based molecular switches in such materials and provide a means of creating dynamic spatial patterns, thus enabling spatiotemporal control of a wide array of reaction-diffusion phenomena prevalent in biological systems. In this paper, we develop a means of photopatterning two-dimensional DNA-functionalized poly(ethylene glycol) diacrylate (PEGDA) hydrogel architectures with an aim toward these applications. While PEGDA photopatterning methods are well-established for the fabrication of hydrogels, including those containing oligonucleotides, the photoinitiators typically used have significant crosstalk with many UV-photoswitchable chemistries including nitrobenzyl derivatives. We demonstrate the digital photopatterning of PEGDA-co-DNA hydrogels using a blue light-absorbing (470 nm peak) photoinitiator system and macromer comprised of camphorquinone, triethanolamine, and poly(ethylene glycol) diacrylate ($M$ n = 575) that minimizes absorption in the UV-A wavelength range commonly used to trigger photoswitchable chemistries. We demonstrate this method using digital maskless photolithography within microfluidic devices that allows for the reliable construction of multidomain structures. The method achieves feature resolutions as small as 25 μm, and the resulting materials allow for lateral isotropic bulk diffusion of short single-stranded (ss) DNA oligonucleotides. Finally, we show how the use of these photoinitiators allows for orthogonal control of photopolymerization and UV-photoscission of acrylate-modified DNA containing a 1-(2-nitrophenyl) ethyl spacer to selectively cleave DNA from regions of a PEGDA substrate.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Structural Emergence in Particle Dispersions

Particle dispersions, such as pigment-based inks, comprise weakly bound, milled nanoparticles. The properties of these pigments depend on both their chemical composition and a rather complex structural hierarchy which emerges from these dispersions. The emergence of structure under semidilute conditions is related to the structure of the dilute particles, the particle spacing (mesh size), processing history, and the interaction potential. Kinetic simulations could predict such emergence using these input parameters. In this paper, organic pigments are studied as an example of the importance of emergent structure to predict properties such as brilliance and opacity. Organic pigments are used to impart color to commercial inks, plastics, coatings, and cosmetics. In many cases, dilute pigments are mass fractal structures consisting of aggregated nanoparticles held together by weak van der Waals forces. In water, surfactant is added to create a pigment dispersion (an ink). The final properties of a pigment emerge from a complex interplay between aggregation and dispersion of aggregates as a function of concentration. Samples of the organic pigment yellow 14, PY14, were milled to four primary particle sizes to study the effect on structural emergence. The interaction between surfactant-stabilized PY14 aggregates in an aqueous medium was quantified by the second virial coefficient, A 2 , which reflects long-range interactions. The degree of aggregation is associated with short-range attractive interactions between primary particles. In this series of pigments, the degree of aggregation increases dramatically with reduction in primary particle size. Concurrently, the second-order virial coefficient, A 2 , increases reflecting stronger long-range repulsive interactions with particle size. Structural emergence can be understood through the percolation concentration and the filler mesh size. A 2 is translated into a repulsive interaction potential for use in dissipative particle dynamics simulations to enable predictive modeling. Furthermore, this description of the interactions between dispersed pigment aggregates allows for a more scientific and predictive approach to understand structural emergence.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Random heteropolymers as enzyme mimics

Despite successes in replicating the primary–secondary–tertiary structure hierarchy of protein, it remains elusive to synthetically materialize protein functions that are deeply rooted in their chemical, structural and dynamic heterogeneities. We propose that for polymers with backbone chemistries different from that of proteins, programming spatial and temporal projections of sidechains at the segmental level can be effective in replicating protein behaviours; and leveraging the rotational freedom of polymer can mitigate deficiencies in monomeric sequence specificity and achieve behaviour uniformity at the ensemble level. Here, guided by the active site analysis of about 1,300 metalloproteins, we design random heteropolymers (RHPs) as enzyme mimics based on one-pot synthesis. We introduce key monomers as the equivalents of the functional residues of protein and statistically modulate the chemical characteristics of key monomer-containing segments, such as segmental hydrophobicity. The resultant RHPs form pseudo-active sites that provide key monomers with protein-like microenvironments, co-localize substrates with catalytic or cofactor-binding sidechains and catalyse reactions such as oxidation and cyclization of citronellal with isopulegol/menthoglycol selectivity. This RHP design led to enzyme-like materials that can retain catalytic activity under non-biological conditions, are compatible with scalable processing and have expanded substrate scope, including environmentally long-lasting antibiotic tetracycline.

36 MATERIALS SCIENCE↗

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↗