Search NASA⌕ Search

Engineering topics

Krishna M Kalyanam

Publications and source records attributed to Krishna M Kalyanam.

At least 19 records
All sourcesNASA NTRSDOE OSTI
NASA NTRS2023

Strategic Deconfliction of Small Unmanned Aircraft Using Operational Volume Blocks at Crossing Waypoints

In this research, first, analytical case studies are performed to understand the parameters on which the minimum temporal separation between unmanned aircraft at crossing waypoints is dependent for enabling strategic deconfliction. The analytical expressions show that the minimum temporal separation is a function of the length and width of operational volume blocks, the relative positions of the active operational volume blocks, groundspeed of unmanned aircraft, and the incoming crossing angle. Next, the parametric study shows that the impact of the incoming crossing angle on the minimum temporal separation at a crossing waypoint increases with an increase in the width of the operational volume blocks. Finally, simulation studies are performed to understand the impact of operational volume block sizing, on-demand departure rate, minimum departure time separation, and the incoming crossing angle on the average ground delay of unmanned aircraft traveling on two routes with a single crossing waypoint and identical on-demand departure rate. Each unmanned aircraft’s estimated time of arrival at a crossing waypoint is adjusted by introducing a ground delay in departure time; no other controls (e.g., speed adjustments) are applied for strategic deconfliction. Simulation studies show that the impact of the minimum temporal separation at a crossing waypoint on the average ground delay of flights is negligible if the minimum departure time separation is at least two times the minimum temporal separation. Therefore, with an increase in minimum departure time separation at a depot, the impact of increased length of operational volume blocks enclosing the crossing waypoint on the ground delay is offset to an extent.

Operational intent↗
NASA NTRS2023

Strategic Deconfliction of Small Unmanned Aircraft Using Operational Volume Blocks at Crossing Waypoints

In this research, first, analytical case studies are performed to understand the parameters on which the minimum temporal separation between unmanned aircraft at crossing waypoints is dependent for enabling strategic deconfliction. The analytical expressions show that the minimum temporal separation is a function of the length and width of operational volume blocks, the relative positions of the active operational volume blocks, groundspeed of unmanned aircraft, and the incoming crossing angle. Next, the parametric study shows that the impact of the incoming crossing angle on the minimum temporal separation at a crossing waypoint increases with an increase in the width of the operational volume blocks. Finally, simulation studies are performed to understand the impact of operational volume block sizing, on-demand departure rate, minimum departure time separation, and the incoming crossing angle on the average ground delay of unmanned aircraft traveling on two routes with a single crossing waypoint and identical on-demand departure rate. Each unmanned aircraft’s estimated time of arrival at a crossing waypoint is adjusted by introducing a ground delay in departure time; no other controls (e.g., speed adjustments) are applied for strategic deconfliction. Simulation studies show that the impact of the minimum temporal separation at a crossing waypoint on the average ground delay of flights is negligible if the minimum departure time separation is at least two times the minimum temporal separation. Therefore, with an increase in minimum departure time separation at a depot, the impact of increased length of operational volume blocks enclosing the crossing waypoint on the ground delay is offset to an extent.

Operational Intent↗
NASA NTRS2022

An ODE-Fitting Approach to Estimate Critical Aircraft Performance Parameters for Trajectory Prediction

Ground-based decision support tools (DST) in air traffic management (ATM) typically perform trajectory prediction based on aircraft performance model (APM) parameters, but some or all of these parameters might not be readily available. In particular, the three critical parameters required for trajectory prediction are the thrust setting, drag coefficients, and takeoff weight of the aircraft. Unfortunately, these parameters are coupled and appear together in physics-based kinetic models. Past approaches utilize data from a specific phase of flight (climb, level flight or descent), where one or more of the parameters are assumed to be known and estimate the remaining unknown parameters. This approach introduces bias/errors and also does not extend to scenarios where all of the above parameters are not known with sufficient accuracy. This paper is the first of its kind to propose a generalized framework for simultaneous estimation of all three critical APM parameters (thrust, drag, and mass). The proposed approach utilizes data from both the climb and descent phases and fits the ordinary differential equation for altitude in each phase using historical trajectory data available from radar tracks or ADS-B. The approach yields a set of optimized APM parameters that are best suited to fit each historical flight record. The methodology is applied on on sample flights from three different aircraft types, and the results demonstrate low fit error and consequently will yield a high level of prediction accuracy.

trajectory prediction, aircraft performance model,↗
NASA NTRSDate not supplied

Machine Learning based Aircraft Performance Model Estimation for Trajectory Prediction

The accurate prediction of aircraft trajectory by ground-based decision support tools is a critical component of air traffic management in the US National Airspace System (NAS). Accurate predictions of where the aircraft will be in the future or when they will arrive at specific locations (e.g., fixes) is a key enabler for sequencing and efficient arrival management of flights. Traditional physics based aircraft trajectory prediction relies on a simplified point-mass total energy model whose parameters are referred to as Aircraft Performance Model (APM) parameters. Even though the performance coefficients and weight of an aircraft are a vital part of the aircraft performance model’s predictions and accuracy, these coefficients are proprietary in nature and therefore, unavailable to decision-support tools. Current approaches freeze some coefficients to default base of aircraft data (BADA) values and optimize others. However, the APM parameters are highly coupled by the flight dynamics and prioritizing one parameter over others leads to bias and skewed predictions. To alleviate this problem, we provide a combined optimization framework to predict all the critical (thrust, drag and weight) APM parameters. This paper is focused on training Machine Learning (ML) models that map historical flights to optimized APM parameters that provide the best fit (in terms of prediction error). Our dataset obtained from NASA’s Sherlock data warehouse is comprised of thousands of historical flights and includes weather and track data collected from 2019. Using different subsets of relevant features (e.g., aircraft type), we trained several ML models to estimate the aircraft’s take off weight, drag polar coefficients (both parasitic and lift induced), and thrust settings (multiplier applied to the maximum engine thrust). The chosen flights are from three of the most common aircraft types (B738, B737, and A320) arriving at four airports (LAX, DEN, MSP, and DFW). Our ML approach is comprised of two different solutions: 1- using a subset of features that are known prior to the flight departure and do not change during flight (such as engine type, current temperature at departure & destination airports, aircraft type) and 2 - using a subset of temporal features of the flight trajectory (such as cruise altitude, Mach, airspeed, and rate of climb) in addition to the pre-departure features from the first solution. The labels or target variables are the APM parameters that were obtained by an optimized ordinary differential equations (ODE) fitting process (applied to individual flights). The ODE-fitting is very time intensive and is therefore performed offline. Thus, training an ML model to learn the relationship between the flight features and ODE-generated labels enables faster estimation of the APM parameters and is therefore amenable to real-time prediction. Various ML models including linear regression, random forest, XGBoost, and neural network were trained, and the results are compared. After model validation and hyperparameter-tuning, we observed that the Random Forest model outperformed the other three models by the overall mean square error (MSE) of 2% for the first solution and 1.5% for the second solution. Finally, the ML-derived parameters are compared against default BADA APM parameters using NASA’s Autonomy Development toolkit (ADK) simulation software. The simulation results for one of each aircraft type is shown and discussed.

Aida Sharif Rohani↗
NASA NTRSDate not supplied

Predicting Airport Runway Configurations for Decision-Support Using Supervised Learning

One of the most challenging tasks for air traffic controllers is runway configuration management (RCM). It deals with the optimal selection of runways to operate on (for arrivals and departures) based on traffic, surface wind speed, wind direction, other environmental variables, noise constraints, and several other airport-specific factors. It affects the efficiency of the National Airspace System (NAS) and both surface and airspace operations can benefit from better understanding future runway configurations. In this paper, we present a comprehensive implementation of predictive models for runway configuration estimation from large volumes of historical data. Specifically, operational data from two full years (2018 and 2019) is collected, analyzed, and fused together to build the data product used in this work. The data set differs from prior work in the field in terms of its scope, resolution, and variety of factors collected and considered. Meteorological data is collected from two different sources – current weather conditions from METAR (Meteorological Terminal Aviation Routine Weather Report) and forecast weather conditions from Localized Aviation MOS Program (LAMP). Operational data from the Federal Aviation Administration (FAA) Aviation System Performance Metrics (ASPM) related to scheduled and actual number of arrivals and departures, average taxi times, etc. are collected. NASA’s Sherlock Data Warehouse is used to identify critical information such as go-arounds, and other events that might impact RCM decision-making. All data is collected and aggregated over 15-minute intervals throughout the two years. This provides a resolution like the timescales that might be necessary for runway configuration management decision-making. A variety of supervised learning algorithms are tested including Support Vector Machine, Random Forest, Gradient Boosting, etc. including tuning of the model hyperparameters. The modeling process is applied and presented on two representative U.S. airports – Charlotte Douglas International Airport (KCLT) and Denver International Airport (KDEN). The two airports present different levels of complexity in terms of the total number of configurations used and provide a balanced perspective on the generalizability of the developed approach to other airports in the NAS. Initial results are promising (F1 score of 0.91 at KCLT and 0.83 at KDEN) for data in the test set. The final paper will contain a comprehensive comparison between different models and model building strategies as well as further refined results. Most important predictors for each airport will be identified along with a discussion and recommendations on adapting the framework to other scenarios.

Tejas G Puranik↗
NASA NTRSDate not supplied

Predicting Airport Runway Configurations for Decision-Support Using Supervised Learning

One of the most challenging tasks for air traffic controllers is runway configuration management (RCM). It deals with the optimal selection of runways to operate on (for arrivals and departures) based on current and forecast of traffic, surface wind speed, wind direction, other environmental variables, noise constraints, and several other airport-specific factors. In this paper, a methodology using supervised learning is developed to build a predictive model for RCM decision-support from large volumes of historical data. Data from two full years (2018 and 2019) related to current and forecast weather, demand/capacity, etc. is collected, analyzed, and fused together. A variety of supervised learning algorithms are tested for predicting runway configuration and hyperparameter tuning is carried out to select the best performing model. The validation process involves two airports of low (Charlotte Douglas International Airport, CLT) and high (Denver International Airport, DEN) complexity of configuration decision-making. The results show significant promise for the two airports with test accuracy of 93% (CLT) and 73% (DEN). The methodology is scalable and generalizable to other airports across the U.S. National Airspace System.

air traffic management↗
NASA NTRSDate not supplied

Aerial Vehicle Routing and Scheduling for UAS Traffic Management: A Hybrid Monte Carlo Tree Search Approach

We present the Multi-Route Weighted Package Delivery Problem (MRWPDP) and a scalable solution methodology as a major step towards enabling an airspace deconfliction service for drone delivery operations. The problem is motivated by Strategic deconfliction under the FAA’s “Unmanned Aircraft Systems Traffic Management” Concept of Operations. MRWPDP falls under a class of vehicle routing and scheduling problems, and as such is NP-Hard. In MRWPDP, a graph network is given which consists of depots, drop-off sites, and multiple routes connecting the two. In addition, routes are weighted by the associated ground risk and total travel distance for package delivery. The goal is to optimally schedule the departure time and assign routes to a known set of vehicles at the depot. We propose a heuristic solution to the problem by borrowing techniques from Mixed Integer Linear Programming (MILP), Constraint Programming, and Monte Carlo Tree Search (MCTS). The resulting hybrid framework is MCTS with Bound-and-Prune (BP) and rapid simulated updates (U), or MCTS-BP-U. This approach is able to quickly provide a feasible solution for MRWPDP, even for large problem instances up to 1000 vehicles. We provide a MILP formulation of MRWPDP and compare its performance against MCTS-BP-U in terms of solution quality. An agent-based model simulation is conducted as a final step to validate the efficacy of our approach.

air traffic scheduling↗
NASA NTRSDate not supplied

Prediction of Aircraft Estimated Time of Arrival Using A Supervised Learning Approach

We present a novel data-driven approach for prediction of the estimated time of arrival (ETA) of aircraft in the terminal area via the implementation of a Random Forest regression model. The model uses data fused from a number of sources (flight track, weather, flight plan information, etc.) and provides predictions for the remaining flight time for aircraft landing at Dallas/Fort Worth (DFW) International Airport. The predictions are made when the aircraft is at a distance of 200-miles from the airport. The results show that the model is able to predict estimated time of arrival to within ± 5 min for 90% of the flights in the test data with the mean absolute error being lower at 145 seconds. This paper covers the entire pipeline of data collection, preprocessing, setup and training of the ML model, and the results obtained for DFW.

Machine learning↗
NASA NTRSDate not supplied

Machine Learning Approach for Aircraft Performance Model Parameter Estimation for Trajectory Prediction Applications

Inaccurate prediction of aircraft trajectory by ground-based decision support tools (DST) is a major concern in air traffic management (ATM). Aircraft trajectory prediction tools rely on a simplified point-mass aircraft performance model (APM) to make their predictions. Even though the performance coefficients and weight of an aircraft are a vital part of the APM’s predictions and accuracy, these coefficients are proprietary in nature and therefore, unavailable to DSTs. Current ATM research focuses on improving the estimate of some APM parameters by freezing all other coefficients. This simplified approach introduces unwanted sources of bias and negatively impacts the accuracy of the performance model. In this paper, we apply machine learning (ML) techniques for the simultaneous prediction of three key APM parameters (two drag coefficients and the initial aircraft weight). To accomplish this, we employ an ordinary differential equation (ODE) fitting approach to generate optimized APM parameter labels customized to each individual flight record. Subsequently, we train ML models to capture the relationship between the historical data and the optimized APM parameters. Two different ML model solutions are applied and APM coefficients are predicted for unseen flights. The results indicate that the ML models are able to capture the relationship between APM parameters and flight-related features with good accuracy.

trajectory prediction, machine learning, aircraft ↗
NASA NTRSDate not supplied

Traffic Flow Analysis for Package Delivery Drones using a Queueing Model

A key component of the small unmanned aircraft systems traffic management ecosystem is the design of scalable algorithms for strategic deconfliction of drones prior to takeoff. In this work, we focus on efficient flow management of drones on a network of intersecting edges subject to two kinds of spacing constraints: 1) between any two adjacent vehicles on an edge and 2) between any two vehicles on two different edges arriving one after the other at an intersection. The spacing is designed to enable non-intersection of operational volumes corresponding to two different vehicles thereby properly separating the vehicles inside each volume. For simplicity, we assume a constant ground speed for the drones and fixed dimensions for the operational volume blocks. The deconfliction is managed by adjusting the takeoff time of the drones, thereby regulating their arrival time at various crossing waypoints in the network. This framework allows us to study the maximum flow (throughput) of vehicles on a network of edges connecting depots to drop off sites subject to the temporal spacing constraints. The departure scheduling of individual drones results in a combinatorial optimization problem. To alleviate this, we solve a max-flow formulation and use queueing theory to simplify the analysis and provide upper bounds to the underlying optimization problem for individual drone departure scheduling. Our results indicate that throughput drops rapidly after the density of drones in the network passes the max-flow limits.

Alexey A Munishkin↗
NASA NTRSDate not supplied

Aerial Vehicle Routing and Scheduling for UAS Traffic Management: A Hybrid Monte Carlo Tree Search Approach

We present the Multi-Route Weighted Package Delivery Problem (MRWPDP) and a scalable solution methodology as a major step towards enabling an airspace deconfliction service for drone delivery operations. The problem is motivated by Strategic deconfliction under the FAA’s “Unmanned Aircraft Systems Traffic Management” Concept of Operations. MRWPDP falls under a class of vehicle routing and scheduling problems, and as such is NP-Hard. In MRWPDP, a graph network is given which consists of depots, drop-off sites, and multiple routes connecting the two. In addition, routes are weighted by the associated ground risk and total travel distance for package delivery. The goal is to optimally schedule the departure time and assign routes to a known set of vehicles at the depot. We propose a heuristic solution to the problem by borrowing techniques from Mixed Integer Linear Programming (MILP), Constraint Programming, and Monte Carlo Tree Search (MCTS). The resulting hybrid framework is MCTS with Bound-and-Prune (BP) and rapid simulated updates (U), or MCTS-BP-U. This approach is able to quickly provide a feasible solution for MRWPDP, even for large problem instances up to 1000 vehicles. We provide a MILP formulation of MRWPDP and compare its performance against MCTS-BP-U in terms of solution quality. An agent-based model simulation is conducted as a final step to validate the efficacy of our approach.

air traffic scheduling↗
NASA NTRSDate not supplied

Towards an Aviation Large Language Model by Fine-tuning and Evaluating Transformers

In the aviation domain, there are many applications for machine learning and artificial intelligence tools that utilize natural language. For example, there is a desire to know the commonalities in written safety reports such as voluntary post incidents reports or aerial wildfire operations reports to better understand the risks present. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement. These applications can benefit from the use of state-of-the-art natural language processing techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of adaptation of NLP tools to the aviation domain by fine-tuning transformer based models using aviation data sets. In 2018, a novel language model based on neural units (also called transformers) was created and became known as “Bidirectional Encoder Representations from Transformers” or BERT. This architecture combined with large amounts of English training data and innovative semi-supervised training tasks set the standard for what would later emerge as Large Language Models. The performance of these models was further improved by hyperparameter tuning and refinement of the semi-supervised training task and resulted in “Robustly Optimized BERT Pre-training Approach through hyperparameter tuning” or RoBERTa models. These pre-trained Large Language Models proved to be useful for a wide variety of natural language processing tasks such as text classification and question answering through a process called fine-tuning. The transformer architecture with pre-trained weights served as the basis with the last few layers replaced with layers fine-tuned to perform a new task e.g., a layer that provides a label for the entire input text. This process of fine-tuning can also be used to adapt the models to new domains; e.g., BioBERT started with the pre-trained BERT model and was completed by additional fine-tuning and training on biomedical documents. Transformer-based architectures can also be used to create rich representations of text called embeddings which can serve as the input to other machine learning models. This allows simpler algorithms such as logistic regression to use context-rich representations of the text while still remaining quick to train and evaluate. In the world of aviation, there is a growing demand for natural language processing and understanding but the domain presents unique challenges. Due to the technical content (and specialized language) of most aviation documents, fine-tuning pre-trained Large Language Models to specific tasks has not met the benchmark on natural language processing tasks set by simpler models trained from scratch on the data. To address this deficiency, this paper evaluates the improvements from fine-tuning a Large Language Model on a large set of aviation documents using the original semi-supervised training tasks before performing specific natural language tasks. In fine-tuning, a domain-specific dataset is used on the original training task but with the pre-trained Large Language Model instead of starting from a random initialization. This approach allows the model to be adapted to the specific domain language without discarding the information gained from training on general English data. This paper utilized two major dataset types to train and assess the RoBERTa fine-tuning performance. The first are 7,057 Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the semi-supervised fine-tuning. The second type is the 494 document classification labels to be used for evaluation. This down-stream evaluation aims to show the performance of the fine-tuned model, better understand how much data is needed for an effective fine-tuning, and how fine-tuning can be adapted for different applications in-the domain. After semi-supervised training, evaluation begins by encoding the documents for classification using the fine-tuned RoBERTa model. Then a logistic regression classifier is trained to label the document type and compared against our ground truth labels. This currently leads to a 82.8% accuracy on 10-fold cross validation showing improvement over baseline RoBERTa which achieved 81.0%. We plan to measure the improvements on additional tasks and it is expected that these improvements will lead to more robust models that can tackle the natural language processing challenges present in aviation datasets.

ATM↗
NASA NTRSDate not supplied

Enhancing Air Traffic Control Planning with Automatic Speech Recognition

The decisions made during the Federal Aviation Administration Air Traffic Control System Command Center's planning teleconferences hold significant sway over the National Airspace System. Held every two hours, these teleconferences convene air traffic managers and stakeholders from across the nation to discuss airspace conditions, weather, and constraints, leading to the formulation and adjustment of traffic management initiatives. Given the critical nature of these decisions, the need for accurate and efficient record-keeping is paramount. In recent years, the application of automatic speech recognition has gained popularity across diverse industries, including aviation. While traditional applications focus on transcribing air traffic control communication, this paper explores a unique application of automatic speech recognition by converting the audio from planning teleconferences into text transcriptions. This innovative approach addresses key challenges in the field, presenting potential benefits for quality assurance, real-time participation, and downstream natural language processing tasks. A notable breakthrough in the machine learning community, namely the transformer neural network architecture, forms the backbone of the proposed solution in this paper. The transformer architecture's role in this research represents a paradigm shift in the efficiency of automatic speech recognition models. By reducing the amount of in-domain training data required, this architecture allows for the fine-tuning of such models like Whisper, originally pretrained on vast English speech datasets. The adaptability of the transformer architecture proves invaluable in capturing the nuances of aviation terminology and specific language used in planning teleconferences. Leveraging the Whisper model as a baseline, our research details the fine-tuning and validation using a dataset comprising 20 hours of meticulously transcribed planning teleconferences. Notably, the baseline pretrained Whisper model exhibited a word error rate of 18.77%. Through the fine-tuning process, the model achieved a substantial improvement, demonstrating an impressive performance with a reduced word error rate of 6.82%. This substantial decrease in WER not only highlights the effectiveness of the transformer architecture but also emphasizes the practical advancements achieved through the application of automatic speech recognition in this specific domain. The utilization of automatic speech recognition in planning teleconferences in this work introduces several novelties. Firstly, the creation of text transcriptions offers a valuable tool for quality assurance and facilitates the efficient review of teleconferences. This is an important aspect of the proposed solution, given the time-sensitive and high-stakes nature of decisions made during these meetings. Furthermore, text-searchable transcriptions provide a streamlined approach for locating and validating critical information, potentially saving hours of manual effort in searching through audio recordings. Moreover, our research identifies a key use case for external facilities and stakeholders. In situations where attendance at the planning teleconference is not feasible, having access to text transcriptions in real-time or shortly after the teleconference ends, proves to be a time-saving and informative resource. This feature enhances collaboration and ensures that stakeholders can stay abreast of important discussions and decisions even in their absence. Despite the efficiency gains facilitated by the transformer architecture in automatic speech recognition technology, it is essential to acknowledge the human factors in data creation. Subject matter experts play a crucial role in accurately transcribing planning teleconferences due to the specificity and complexity of the information discussed. The research dataset, consisting of 20 hours of transcribed planning teleconferences, forms the foundation for fine-tuning and validating the Whisper model. The achieved word error rate of 6.82% demonstrates promising advancements, particularly in recognizing essential aviation terminology within the teleconferences. In conclusion, this paper presents a comprehensive exploration of the application of automatic speech recognition in Air Traffic Control System Command Center planning teleconferences, leveraging the transformer architecture for enhanced efficiency. The novel contributions lie in the improved accessibility of decision-making records, real-time participation opportunities for external stakeholders, and the potential for downstream natural language processing advancements. As the aviation industry continues to evolve, the integration of automatic speech recognition technologies holds the promise of revolutionizing decision-making processes and contributing to the overall safety and efficiency of air traffic management.

ATM↗
NASA NTRSDate not supplied

Applying Machine Learning Tools for Runway Configuration Decision Support

Determining optimal runway configurations at airports, a responsibility assigned to air traffic controllers, is a challenging task. The decision-making process is intricate and involves consideration of many factors such as prevailing wind condition, convective weather, visibility, cloud ceilings, departure and arrival demand, traffic flow, equipment status, and other airport constraints. In a previous work, we developed a Runway Configuration Assistance tool using an offline reinforcement learning method called conservative Q-learning. In this paper, we evaluate and validate our Runway Configuration Assistance tool as a decision support for air traffic controllers. We validated our tool using three airports with differing levels of complexity: Charlotte Douglas International Airport, Denver International Airport, and Dallas Fort Worth International Airport. We quantified the performance of the Runway Configuration Assistance tool based on (1) agreement with historical air traffic controller decisions and (2) violation of decisions that would be obvious to subject-matter experts. Our tool showed promising results in both performance metrics for the three airports, despite the complexities in the runway configuration decision-making process. We also discuss challenges in using machine learning in general to aid air traffic management and identify deployment considerations for the Runway Configuration Assistance tool.

Runway Configuration Management↗
NASA NTRSDate not supplied

Rolling Horizon with K-Position Search Method for Strategic Deconfliction of Package Delivery UAS

In this research, the strategic deconfliction of unmanned aircraft systems for an urban package delivery environment with two depots and multiple drop-off locations is studied. This research aims to formulate a mathematical model to compute both the departure sequence and scheduled time of departure for each unmanned aircraft system at a depot, considering temporal constraints at en-route crossing waypoints and depots for strategic deconfliction. However, the problem formulation results in an NP-hard mixed-integer nonlinear programming problem for the global optimal solution, so instead, a "rolling horizon with𝑘-position search"heuristic method is developed. The simulation studies show that an increase in the value of𝑘(the parameter used to determine the size of the local neighborhood) reduces the average ground delay at the cost of an increase in the computation time for a given problem size. The study also shows an order of magnitude increase in the maximum number of flights scheduled with the integration of rolling horizon (time decomposition) compared to those without the integration of rolling horizon in the heuristic algorithm for a given computation time cut off.

UTM↗
NASA NTRSDate not supplied

Document Classification Techniques for Aviation Letters of Agreement

Often when working with historic air traffic management (ATM) documents, it is helpful to classify them into specific categories. In this paper, we conduct a thorough review of natural language processing techniques to perform this classification task on Letters of Agreement (LOAs), technical aviation documents outlining rules for utilizing US airspace. We evaluate multiple techniques for representing the text in the documents as embeddings: unigram and bigram Term Frequency Inverse Document Frequency (TFIDF), Word2Vec, Doc2Vec, GloVe and RoBERTa. We investigate a wide range of classification models: K-Nearest Neighbors, Random Forest, Support Vector Machines (SVM), Logistic Regression, Naive Bayes, Feed-Forward Neural Network, Convolutional Neural Networks (CNNs) and Long-Short Term Memory (LSTM). By comparing the different methods, we found the best overall approach for our task was to use unigram TFIDF representations with SVM while also gaining insight into how the other methodologies performed on a small technical datasets.

ATM↗
NASA NTRSDate not supplied

Towards an Aviation Large Language Model by Fine-tuning and Evaluating Transformers

In the aviation domain, there are many applications for machine learning and artificial intelligence tools that utilize natural language. For example, there is a desire to know the commonalities in written safety reports such as voluntary post incidents reports or create more accurate transcripts of air traffic management conversations. Another use-case is the possibility of extracting airspace procedures and constraints currently written in documents such as Letters of Agreement (LOA) which is used as the evaluation case in this paper. These applications can benefit from the use of state-of-the-art Natural Language Processing (NLP) techniques when adapted to the language/phraseology specific to the aviation domain. This paper evaluates the viability of transferring pre-trained large language models to the aviation domain by adapting transformer based models using aviation datasets. This paper utilized two datasets to adapt a ‘Robustly Optimized Bidirectional Encoder Representations from Transformers Approach’ (RoBERTa) model and two down-stream classification tasks to assess its performance. These datasets are all built upon Letters of Agreement which are Federal Aviation Administration (FAA) documents that formalize airspace operations across the national airspace system. The first two datasets are used for the adaptation of RoBERTa to the aviation domain and were of different sizes to assess the number of documents needed to adapt to the aviation domain. They contain many examples of ‘aviation English’ using domain specific terminology and phrasing which serves as a representative basis to perform the unsupervised adaptation. The second dataset is a separate set of LOA documents with two sets of classification labels to be used for evaluation; one at the document level and one at the line level. These down-stream evaluations allowed the measurement of improvement by adapting RoBERTa. The accuracy increased by 4-6% on both tasks and the F1 score on the class of interest increased by 4-8% from the adaptation.

Air Traffic Management↗