Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed training”

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 199 records · Page 11
All sourcesNASA NTRSDOE OSTI
NASA NTRS2015

Using Satellite Observations of Cloud Vertical Distribution to Improve Global Model Estimates of Cloud Radiative Effect on Key Tropospheric Oxidants

Radiative effect of clouds is one of the major factors that affect tropospheric OH. Large differences in cloud distributions among current (chemistry-climate or chemical transport) models could contribute significantly to the wide model spread of tropospheric OH, which was reported by the ACCMIP activity (Voulgarakis et al., ACP 2013). CCCM, a 3-D cloud data product developed at NASA Langley and merged from multiple A-Train satellite observations, provides unprecedentedly strong constraints on the vertical distribution of clouds and therefore simulated effects of clouds on key tropospheric oxidants.

Liu, Hongyu↗
NASA NTRS1995

An adaptable product for material processing and life science missions

The Experiment Control System II (ECS-II) is designed to make available to the microgravity research community the same tools and mode of automated experimentation that their ground-based counterparts have enjoyed for the last two decades. The design goal was accomplished by combining commercial automation tools familiar to the experimenter community with system control components that interface with the on-orbit platform in a distributed architecture. The architecture insulates the tools necessary for managing a payload. By using commercial software and hardware components whenever possible, development costs were greatly reduced when compared to traditional space development projects. Using commercial-off-the-shelf (COTS) components also improved the usability documentation, and reducing the need for training of the system by providing familiar user interfaces, providing a wealth of readily available documentation, and reducing the need for training on system-specific details. The modularity of the distributed architecture makes it very amenable for modification to different on-orbit experiments requiring robotics-based automation.

Wassick, Gregory↗
NASA NTRS2000

Vehicle Dynamics due to Magnetic Launch Propulsion

The field of Magnetic Levitation Lind Propulsion (MagLev) has been around for over 30 years, primarily in high-speed rail service. In recent years, however, NASA has been looking closely at MagLev as a possible first stage propulsion system for spacecraft. This approach creates a variety of new problems that don't currently exist with the present MagLev trains around the world. NASA requires that a spacecraft of approximately 120,000 lbs be accelerated at two times the acceleration of gravity (2g's). This produces a greater demand on power over the normal MagLev trains that accelerate at around 0.1g. To be able to store and distribute up to 3,000 Mega Joules of energy in less than 10 seconds is a technical challenge. Another problem never addressed by the train industry and, peculiar only to NASA, is the control of a lifting body through the acceleration of and separation from the MagLev track. Very little is understood about how a lifting body will react with external forces, Such as wind gusts and ground effects, while being propelled along on soft springs such as magnetic levitators. Much study needs to be done to determine spacecraft control requirements as well as what control mechanisms and aero-surfaces should be placed on the carrier. Once the spacecraft has been propelled down the track another significant event takes place, the separation of the spacecraft from the carrier. The dynamics involved for both the carrier and the spacecraft are complex and coupled. Analysis of the reaction of the carrier after losing, a majority of its mass must be performed to insure control of the carrier is maintained and a safe separation of the spacecraft is achieved. The spacecraft angle of attack required for lift and how it will affect the carriage just prior to separation, along with the impacts of around effect and aerodynamic forces at ground level must be modeled and analyzed to define requirements on the launch vehicle design. Mechanisms, which can withstand the expected forces and allow the spacecraft to separate at the desired time must be developed. Modeling and analysis of the full-scale system must be developed to derive the requirements for design of the separation mechanisms. A description of several MagLev demonstrators will be presented and the testing and analysis to model the demonstrators will be included.

Galaboff, Zachary J.↗
NASA NTRS2013

Impact of the Dominant Large-scale Teleconnections on Winter Temperature Variability over East Asia

Monthly mean geopotential height for the past 33 DJF seasons archived in Modern Era Retrospective analysis for Research and Applications reanalysis is decomposed into the large-scale teleconnection patterns to explain their impacts on winter temperature variability over East Asia. Following Arctic Oscillation (AO) that explains the largest variance, East Atlantic/West Russia (EA/WR), West Pacific (WP) and El Nino-Southern Oscillation (ENSO) are identified as the first four leading modes that significantly explain East Asian winter temperature variation. While the northern part of East Asia north of 50N is prevailed by AO and EA/WR impacts, temperature in the midlatitudes (30N-50N), which include Mongolia, northeastern China, Shandong area, Korea, and Japan, is influenced by combined effect of the four leading teleconnections. ENSO impact on average over 33 winters is relatively weaker than the impact of the other three teleconnections. WP impact, which has received less attention than ENSO in earlier studies, characterizes winter temperatures over Korea, Japan, and central to southern China region south of 30N mainly by advective process from the Pacific. Upper level wave activity fluxes reveal that, for the AO case, the height and circulation anomalies affecting midlatitude East Asian winter temperature is mainly located at higher latitudes north of East Asia. Distribution of the fluxes also explains that the stationary wave train associated with EA/WR propagates southeastward from the western Russia, affecting the East Asian winter temperature. Investigation on the impact of each teleconnection for the selected years reveals that the most dominant teleconnection over East Asia is not the same at all years, indicating a great deal of interannual variability. Comparison in temperature anomaly distributions between observation and temperature anomaly constructed using the combined effect of four leading teleconnections clearly show a reasonable consistency between them, demonstrating that the seasonal winter temperature distributions over East Asia are substantially explained by these four large-scale circulation impacts.

El Nino-Southern Oscillation↗
DOE OSTI2024

Voltage Calculations in Secondary Distribution Networks via Physics-Inspired Neural Network Using Smart Meter Data

The increasing penetration of distributed energy resources (DERs) leads to voltage issues across distribution networks, necessitating voltage calculations by utilities. Electric model-free voltage calculation offers an enticing solution. However, most researches mainly focus on primary distribution networks ignoring secondary distribution networks and commonly overlook extreme voltage case calculations, which require the model’s extrapolation abilities. Here, in addressing the gaps, this paper presents a customized physics-inspired neural network (PINN) model, the structure of which is inspired by the derived coupled power flow model of primary-secondary distribution networks. To ensure precision and rapid convergence, a crafted training framework for the PINN model is proposed. The PINN’s “structure-mimetic” design enables superior extrapolation for unseen scenarios and enhances physical information awareness. We demonstrate this through two applications: hosting capacity analysis and customer-transformer connectivity. The effectiveness and advantages of the proposed PINN model are validated on two public testing systems and one utility distribution feeder model.

Distribution network↗
NASA NTRSDate not supplied

Three-Dimensional Structure and Modeling of a Normal Bifurcated Shock Train from Experimental Measurements

An asymmetric, bifurcated normal shock train in a Mach 2 constant area, rectangular duct is investigated in the University of Michigan Direct Connect Isolator facility. High-speed schlieren imaging, wall static pressure measurements, surface oil flow visualization, and particle image velocimetry of a shock train are synthesized into a three-dimensional representation of shock train structure. This visualization is then used to inform the underlying flow physics of the distributed fluid dynamical processes along the structure. The detailed, three-dimensional morphology of the flow profile entering the shock train is shown to have a significant impact on the separated flow morphology of the shock train. This results in skewed supersonic core flow with alternating separation bubbles in the surrounding boundary layers. Finally, the efficacy of the prevailing pseudo-shock models in the literature is analyzed with the support of the available flow measurements. None are found to simultaneously model both the pressure and streamwise Mach number profile of the UMDCI pseudo-shock.

Hypersonics↗
DOE OSTI2025

Object detection with deep learning for rare event search in the GADGET II TPC

In the pursuit of identifying rare two-particle events within the GADGET II Time Projection Chamber (TPC), this paper presents a comprehensive approach for leveraging Convolutional Neural Networks (CNNs) and various data processing methods. To address the inherent complexities of 3D TPC track reconstructions, the data is expressed in 2D projections and 1D quantities. This approach capitalizes on the diverse data modalities of the TPC, allowing for the efficient representation of the distinct features of the 3D events, with no loss in topology uniqueness. Additionally, it leverages the computational efficiency of 2D CNNs and benefits from the extensive availability of pre-trained models. Given the scarcity of real training data for the rare events of interest, simulated events are used to train the models to detect real events. To account for potential distribution shifts when predominantly depending on simulations, significant perturbations are embedded within the simulations. This produces a broad parameter space that works to account for potential physics parameter and detector response variations and uncertainties. These parameter-varied simulations are used to train sensitive 2D CNN object detectors. When combined with 1D histogram peak detection algorithms, this multi-modal detection framework is highly adept at identifying rare, two-particle events in data taken during experiment 21072 at the Facility for Rare Isotope Beams (FRIB), demonstrating a 100% recall for events of interest. Here, we present the methods and outcomes of our investigation and discuss the potential future applications of these techniques.

Convolutional neural network↗
DOE OSTI2024

Harnessing Machine Learning and Data Fusion for Accurate Undocumented Well Identification in Satellite Images

This study utilizes satellite data to detect undocumented oil and gas wells, which pose significant environmental concerns, including greenhouse gas emissions. Three key findings emerge from the study. Firstly, the problem of imbalanced data is addressed by recommending oversampling techniques like Rotation–GaussianBlur–Solarization data augmentation (RGS), the Synthetic Minority Over-Sampling Technique (SMOTE), or ADASYN (an extension of SMOTE) over undersampling techniques. The performance of borderline SMOTE is less effective than that of the rest of the oversampling techniques, as its performance relies heavily on the quality and distribution of data near the decision boundary. Secondly, incorporating pre-trained models trained on large-scale datasets enhances the models’ generalization ability, with models trained on one county’s dataset demonstrating high overall accuracy, recall, and F1 scores that can be extended to other areas. This transferability of models allows for wider application. Lastly, including persistent homology (PH) as an additional input improves performance for in-distribution testing but may affect the model’s generalization for out-of-distribution testing. A careful consideration of PH’s impact on overall performance and generalizability is recommended. Overall, this study provides a robust approach to identifying undocumented oil and gas wells, contributing to the acceleration of a net-zero economy and supporting environmental sustainability efforts.

SMOTE↗
DOE OSTI2024

Updimensioning strategy derived from synthetic equiaxed grain structures for approximating 3D grain size distributions from 2D visualizations with 1D parameters

We generated synthetic equiaxed grain structures using computer graphics software to explore the relationship between various grain size determination methods and true three-dimensional (3D) grain diameters. Mirroring grain measurement techniques, the synthetic 3D grain structures are imaged as 2D micrographs which are measured to yield 1D grain size parameters. Synthetic grain structures provide data at a mass scale and permit exploration of both polished and fractured surface micrographs, revealing one-to-one correspondence between exposed 2D grain cross-sections and individual 3D grains. Analysis of this correspondence yielded a procedure to approximate 3D equiaxed grain size and volume distributions based on the mode of the 2D fractograph grain size distribution. The 3D approximation procedure is shown to be less susceptible to different imaging conditions that affect small, undiscernible grains compared to the standard planimetric and linear intercept methods, which by design also tend to underestimate the 3D grain diameter. The procedure requires larger sample sizes to lower variance and a deeper analysis which could become more practical with machine learning (ML) models for grain boundary segmentation, which synthetic grain structures can help train. This work lays the foundation for analyzing other grain distributions such as columnar and composite grains in similar depth.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Emission line predictions for mock galaxy catalogues: a new differentiable and empirical mapping from DESI

ABSTRACT We present a simple, differentiable method for predicting emission line strengths from rest-frame optical continua using an empirically determined mapping. Extensive work has been done to develop mock galaxy catalogues that include robust predictions for galaxy photometry, but reliably predicting the strengths of emission lines has remained challenging. Our new mapping is a simple neural network implemented using the JAX Python automatic differentiation library. It is trained on Dark Energy Spectroscopic Instrument Early Release data to predict the equivalent widths (EWs) of the eight brightest optical emission lines (including H α, H β, [O ii], and [O iii]) from a galaxy’s rest-frame optical continuum. The predicted EW distributions are consistent with the observed ones when noise is accounted for, and we find Spearman’s rank correlation coefficient ρs > 0.87 between predictions and observations for most lines. Using a non-linear dimensionality reduction technique, we show that this is true for galaxies across the full range of observed spectral energy distributions. In addition, we find that adding measurement uncertainties to the predicted line strengths is essential for reproducing the distribution of observed line-ratios in the BPT diagram. Our trained network can easily be incorporated into a differentiable stellar population synthesis pipeline without hindering differentiability or scalability with GPUs. A synthetic catalogue generated with such a pipeline can be used to characterize and account for biases in the spectroscopic training sets used for training and calibration of photo-z’s, improving the modelling of systematic incompleteness for the Rubin Observatory LSST and other surveys.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

Model-free estimation of completeness, uncertainties, and outliers in atomistic machine learning using information theory

Abstract An accurate description of information is relevant for a range of problems in atomistic machine learning (ML), such as crafting training sets, performing uncertainty quantification (UQ), or extracting physical insights from large datasets. However, atomistic ML often relies on unsupervised learning or model predictions to analyze information contents from simulation or training data. Here, we introduce a theoretical framework that provides a rigorous, model-free tool to quantify information contents in atomistic simulations. We demonstrate that the information entropy of a distribution of atom-centered environments explains known heuristics in ML potential developments, from training set sizes to dataset optimality. Using this tool, we propose a model-free UQ method that reliably predicts epistemic uncertainty and detects out-of-distribution samples, including rare events in systems such as nucleation. This method provides a general tool for data-driven atomistic modeling and combines efforts in ML, simulations, and physical explainability.

36 MATERIALS SCIENCE↗
NASA NTRS1994

A distributed computing model for telemetry data processing

We present a new approach to distributing processed telemetry data among spacecraft flight controllers within the control centers at NASA's Johnson Space Center. This approach facilitates the development of application programs which integrate spacecraft-telemetered data and ground-based synthesized data, then distributes this information to flight controllers for analysis and decision-making. The new approach combines various distributed computing models into one hybrid distributed computing model. The model employs both client-server and peer-to-peer distributed computing models cooperating to provide users with information throughout a diverse operations environment. Specifically, it provides an attractive foundation upon which we are building critical real-time monitoring and control applications, while simultaneously lending itself to peripheral applications in playback operations, mission preparations, flight controller training, and program development and verification. We have realized the hybrid distributed computing model through an information sharing protocol. We shall describe the motivations that inspired us to create this protocol, along with a brief conceptual description of the distributed computing models it employs. We describe the protocol design in more detail, discussing many of the program design considerations and techniques we have adopted. Finally, we describe how this model is especially suitable for supporting the implementation of distributed expert system applications.

Barry, Matthew R.↗
DOE OSTI2025

Physics consistent machine learning framework for inverse modeling with applications to ICF capsule implosions

In high energy density physics (HEDP) and inertial confinement fusion (ICF), predictive modeling is complicated by uncertainty in parameters that characterize various aspects of the modeled system, such as those characterizing material properties, equation of state (EOS), opacities, and initial conditions. Typically, however, these parameters are not directly observable. What is observed instead is a time sequence of radiographic projections using X-rays. In this work, we define a set of sparse hydrodynamic features derived from the outgoing shock profile and outer material edge, which can be obtained from radiographic measurements, to directly infer such parameters. Our machine learning (ML)-based methodology involves a pipeline of two architectures, a radiograph-to-features network (R2FNet) and a features-to-parameters network (F2PNet), that are trained independently and later combined to approximate a posterior distribution for the parameters from radiographs. We show that the machine learning architectures are able to accurately infer initial conditions and EOS parameters, and that the estimated parameters can be used in a hydrodynamics code to obtain density fields, shocks, and material interfaces that satisfy thermodynamic and hydrodynamic consistency. Finally, we demonstrate that features resulting from an unknown EOS model can be successfully mapped onto parameters of a chosen analytical EOS model, implying that network predictions are learning physics, with a degree of invariance to the underlying choice of EOS model. To the best of our knowledge, our framework is the first demonstration of recovering both thermodynamic and hydrodynamic consistent density fields from noisy radiographs.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Efficiently predicting pressure-composition-temperature diagrams to discover low-stability metal hydrides

Quantitatively accurate computational predictions of metal hydride thermodynamics are challenging but critical for alloy performance optimization across a multitude of technological domains, including hydrogen storage, compression, purification, and getters. Recent machine learning approaches have demonstrated great success in this area, but can potentially suffer from several shortcomings since they rely on imbalanced experimental training data and can have poor out-of-distribution (ood) test performance. Here, in this study, we circumvent such pitfalls by developing a computationally efficient, first principles-based workflow for direct prediction of metal hydride phase equilibrium, i.e., the pressure-composition-temperature (PCT) diagram. We then demonstrate its utility on predicting low stability hydrides derived from compositionally complex C14 Laves phase AB2 alloys. Specifically, we computationally predict and then experimentally validate an AB 2 alloy series (z < 0.6 for Ti 2−z Zr z CrMnFeNi) with ideal hydriding thermodynamics for a two-stage metal hydride-based compressor for pressurizing boil off from liquefied hydrogen. Importantly, this study lays the groundwork for accurate and efficient discovery/optimization of ood, low-stability hydrides for which purely data-driven approaches lack sufficient accuracy.

08 HYDROGEN↗
DOE OSTI2024

Effectiveness of denoising diffusion probabilistic models for fast and high-fidelity whole-event simulation in high-energy heavy-ion experiments

Artificial intelligence (AI) generative models, such as generative adversarial networks (GANs), variational autoencoders, and normalizing flows, have been widely used and studied as efficient alternatives for traditional scientific simulations. However, they have several drawbacks, including training instability and inability to cover the entire data distribution, especially for regions where data are rare. This is particularly challenging for whole-event, full-detector simulations in high-energy heavy-ion experiments, such as sPHENIX at the Relativistic Heavy Ion Collider and Large Hadron Collider experiments, where thousands of particles are produced per event and interact with the detector. This work investigates the effectiveness of denoising diffusion probabilistic models (DDPMs) as an AI-based generative surrogate model for the sPHENIX experiment that includes the heavy-ion event generation and response of the entire calorimeter stack. DDPM performance in sPHENIX simulation data is compared with a popular rival, GANs. Results show that both DDPMs and GANs can reproduce the data distribution where the examples are abundant (low-to-medium calorimeter energies). Nonetheless, DDPMs significantly outperform GANs, especially in high-energy regions where data are rare. Additionally, DDPMs exhibit superior stability compared to GANs. The results are consistent between both central and peripheral centrality heavy-ion collision events. Moreover, DDPMs offer a substantial speedup of approximately a factor of 100 compared to the traditional Geant4 simulation method.

42 ENGINEERING↗
DOE OSTI2025

Contrastive learning for robust representations of neutrino data

In neutrino physics, analyses often depend on large simulated datasets, making it essential for models to generalize effectively to real-world detector data. Contrastive learning, a well-established technique in deep learning, offers a promising solution to this challenge. By applying controlled data augmentations to simulated data, contrastive learning enables the extraction of robust and transferable features. This improves the ability of models trained on simulations to adapt to real experimental data distributions. In this paper, we investigate the application of contrastive learning methods in the context of neutrino physics. Through a combination of empirical evaluations and theoretical insights, we demonstrate how contrastive learning enhances model performance and adaptability. Additionally, we compare it to other domain adaptation techniques, highlighting the unique advantages of contrastive learning for this field. Published by the American Physical Society 2025

Wilkinson, Alex (ORCID:0000000253404506)↗
NASA NTRS2005

Astrobiology at Arizona State University: An Overview of Accomplishments

During our five years as an NAI charter member, Arizona State University sponsored a broadly-based program of research and training in Astrobiology to address the origin, evolution and distribution of life in the Solar System. With such a large, diverse and active team, it is not possible in a reasonable space, to cover all details of progress made over the entire five years. The following paragraphs provide an overview update of the specific research areas pursued by the Arizona State University (ASU) Astrobiology team at the end of Year 5 and at the end of the 4 month and subsequent no cost month extensions. for a more detailed review, the reader is referred to the individual annual reports (and Executive Summaries) submitted to the NAI at the end of each of our five years of membership. Appended in electronic form is our complete publication record for all five years, plus a tabulation of undergraduates, graduate students and post-docs supported by our program during this time. The overarching theme of ASU s Astrobiology program was "Exploring the Living Universe: Studies of the Origin, Evolution and Distribution of Life in the Solar System". The NAi-funded research effort was organized under three basic sub- themes: 1. Origins of the Basic Building Blocks of Life. 2. Early Biosphere Evolution. and 3. Exploring for Life in the Solar System. These sub-theme areas were in turn, subdivided into Co-lead research modules. In the paragraphs that follow, accomplishments for individual research modules are briefly outlined, and the key participants presented in tabular form. As noted, publications for each module are appended in hard copy and digital formats, under the name(s) of lead co-Is.

Farmer, Jack↗
NASA NTRSDate not supplied

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↗