Data Lakehouse And Machine Learning Pipeline For Aircraft Fuel Efficiency Experimentation,
2025
Air Force Institute of Technology
Data Lakehouse And Machine Learning Pipeline For Aircraft Fuel Efficiency Experimentation, Skyler G. Kepley
Theses and Dissertations
Fuel efficiency is crucial for the U.S. Air Force, impacting mission success, aircraft performance, and cost savings. This study presents an information system that integrates flight and maintenance data using a data lakehouse. It automates ingestion, enrichment, and predictive modeling, leveraging AutoML for optimization and SHAP for transparency. A case study on C-130J aircraft shows that optimizing D Check cycles can save 11.52 pounds of fuel per flight hour. These findings highlight the effectiveness of data-driven decision-making in aviation, offering a scalable, automated solution for improving fuel efficiency and reducing costs.
Machine Learning With Flight Data Recorder Data For Flight Fuel Consumption Predictions,
2025
Air Force Institute of Technology
Machine Learning With Flight Data Recorder Data For Flight Fuel Consumption Predictions, Adam C. Levandowski
Theses and Dissertations
This study applies advanced Machine Learning (ML) to Flight Data Recorder (FDR) data for fuel consumption predictions. It explores feature engineering, model selection, and Hyper-Parameter Optimization (HPO) across all flight phases. Baseline models like Ordinary Least Squares (OLS) regression, Multi- Layer Perceptrons (MLPs), and decision trees are compared to Deep Neural Networks (DNNs), Recurrent Neural Networks (RNNs) with Gated Recurrent Unit (GRU) layers, and XGBoost. Results analyze segmentation strategies, tailored features, and model performance. A counterfactual analysis compares ML models to operational fuel predictions, demonstrating their deployment potential. Findings establish a foundation for future ML-driven advancements in aviation fuel optimization.
Island Nation Duress: Simulating Passive Peer-To-Peer Bluetooth Communication During Disaster Relief,
2025
Air Force Institute of Technology
Island Nation Duress: Simulating Passive Peer-To-Peer Bluetooth Communication During Disaster Relief, Jason K. Medeiros
Theses and Dissertations
Pacific Islands under U.S. jurisdiction are highly vulnerable to natural disasters, yet many lack the infrastructure to effectively respond and recover. Clear communication during and after such events is critical for evacuation, hazard awareness, and first responders’ coordination. This research explores a simulation-based approach using Bluetooth communication to relay messages across Guam, assessing its efficiency through statistical analysis. By examining regional differences and geographic impacts on Bluetooth messaging, the study aims to identify key factors that enhance peer-to-peer communication for timely and effective disaster response.
Real-Time Decision-Making During Maritime Chokepoint Disruption Using Digital Twin,
2025
Air Force Institute of Technology
Real-Time Decision-Making During Maritime Chokepoint Disruption Using Digital Twin, Jared M. Orendorff
Theses and Dissertations
This research develops a digital twin of the global maritime shipping system to model disruptions in major shipping lanes like the Suez and Panama Canals. By incorporating live ship-tracking data, the model simulates closures, forecasts queue lengths, and determines the best rerouting options. Findings show that canal closures cause large traffic backlogs and increased congestion at alternative chokepoints, while rerouted ships may face higher piracy risks in regions like the Gulf of Guinea and the Strait of Malacca. This tool helps decision-makers respond effectively to maritime disruptions.
Utility Of Self-Sensing Damage Technology Through A2/Ad Drone Combat Simulation,
2025
Air Force Institute of Technology
Utility Of Self-Sensing Damage Technology Through A2/Ad Drone Combat Simulation, Sidhanth Venkatasubramaniam
Theses and Dissertations
Since the introduction of the first unmanned aerial vehicle (UAV), UAVs have consistently improved in capability and versatility. The ability to perform military operations without the risk of losing human life is crucial for the United States military. The trade-off for this versatility is cost, and several ongoing research efforts are being made to improve UAV mission success and the lifespan of UAVs. An area of research that falls under the categories mentioned is self-damage detection. The Air Force Research Laboratories (AFRL) are developing a capability to enable a UAV to assess airframe damage, enabling real-time determination of damage potentially …
Improving Zero Shot Learning By Linking Multi-Label Cnns With Llms,
2025
Air Force Institute of Technology
Improving Zero Shot Learning By Linking Multi-Label Cnns With Llms, Michael A. Wegner
Theses and Dissertations
Classifying previously unseen objects poses a significant challenge for traditional computer vision algorithms, which rely on extensive labeled training data. Zero-shot reasoning offers a way to overcome this limitation. This research explores a novel method for image recognition using the Animals with Attributes 2 (AWA2) dataset as a proof of concept. A multi-label ResNet50 model predicts core attributes like color, ear shape, or number of limbs. Those attributes then feed into ChatGPT which leverages its extensive knowledge base to classify the animal based on the provided attributes. This novel approach skips the need to train on every possible class. Instead, …
Analysis Of An Army Recruiter Allocation Model (Ram),
2025
Air Force Institute of Technology
Analysis Of An Army Recruiter Allocation Model (Ram), Erik J. Wittendorf
Theses and Dissertations
The United States Army Recruiting Command’s mission to recruit America’s best and brightest volunteers that can deploy, fight, and win requires an effective distribution of its recruiting force to serve as local community ambassadors. This research analyzes an Army recruiter allocation model (RAM) and assesses its underlying assumptions, objective function, and constraints. A detailed study of relative market potential and production rates for up to 1,319 Army recruiting stations and 18,789 ZIP codes enables RAM modification recommendations leveraging evolving recruiting concepts and identifies areas of future work to continue improving the Army’s understanding of the recruiting environment.
An Analysis Of Development Phase Nre/Rec Costs In Dod Acquisition Efforts,
2025
Air Force Institute of Technology
An Analysis Of Development Phase Nre/Rec Costs In Dod Acquisition Efforts, Jason Aristizabal
Theses and Dissertations
Estimating Nonrecurring Engineering (NRE) and Recurring Engineering (REC) costs in defense acquisition programs remains challenging, especially in development. While production costs are studied, NRE/REC ratios in development receive little attention. This study analyzes NRE/REC ratios across WBS elements, commodity types, and time periods using defense program data. Results show significant variability, challenging the assumed 1:1 ratio. System Level, PME, and ST&E elements follow distinct trends, highlighting shifting cost structures. These findings stress the need for adaptive methodologies, enabling cost analysts to refine estimates based on historical trends and program-specific factors for improved resource planning.
Accuracy Of Time Phasing Missile And Munition Using The Continuous Distribution Function,
2025
Air Force Institute of Technology
Accuracy Of Time Phasing Missile And Munition Using The Continuous Distribution Function, Joseph Zobler
Theses and Dissertations
Accurate cost and schedule estimates are crucial for maintaining the U.S. military’s technological and operational superiority, ensuring efficient resource allocation and timely development of advanced defense systems. This research examines S-curve models for time-phasing non-recurring Research, Development, Test, and Evaluation (RDT&E) expenditures in missile and munition acquisition programs. This research evaluates the commonly used 60/40 rule, which assumes 60% of expenditures occur by 50% of the schedule, for its accuracy using Cost Assessment Data Enterprise (CADE) and Earned Value Management Central Repository (EVM-CR) data from 21 missile and munition development programs.
Cognitive Warfare In The South China Sea: Analyzing Media Influence And Public Opinion In Taiwan,
2025
Air Force Institute of Technology
Cognitive Warfare In The South China Sea: Analyzing Media Influence And Public Opinion In Taiwan, Wyatt F. Blatti
Theses and Dissertations
In a time where conflict extends beyond traditional battlefields, cognitive warfare emerges as a powerful tool to influence perceptions and gain strategic advantages. This study investigates China’s cognitive warfare strategies against Taiwan through trend analysis, topic modeling, and sentiment analysis of news media articles from March 2013 to August 2024 to uncover evolving techniques and mitigation efforts. The findings highlight the potential for tracking cognitive campaigns overtime but will require more than news media alone and suggests future research to better understand indicators of cognitive warfare.
Reinforcement Learning For Aeromedical Evacuation In Nonstationary Combat Environments,
2025
Air Force Institute of Technology
Reinforcement Learning For Aeromedical Evacuation In Nonstationary Combat Environments, Micah J. Kartchner
Theses and Dissertations
This research formulates the medical evacuation (MEDEVAC) dispatching problem as a sequential decision process and investigates the application of reinforcement learning under nonstationary conditions. We model the dynamic arrival rate of MEDEVAC requests using a nonstationary Hawkes process and design a Double Deep Q-Network algorithm that incorporates belief states to anticipate future requests. Through computational experimentation, we analyze the impact of belief formulation on decision quality and system performance. Results indicate that policies incorporating belief states significantly outperform myopic dispatching policies, reducing urgent casualty wait times by up to 49.68% and increasing on-time evacuations by up to 21.91%.
An Agent-Based Modeling Framework For Evaluating The Linkage Between Disaster Facility Damage And Mental Health,
2025
Air Force Institute of Technology
An Agent-Based Modeling Framework For Evaluating The Linkage Between Disaster Facility Damage And Mental Health, Emily S. Reeves
Theses and Dissertations
This research establishes a novel agent-based modeling framework to establish the linkage between disaster-induced facility damage and mental health outcomes and the evaluation of treatment methods within the civilian and USAF mental health spheres. The study models the degradation and recovery of agent mental health using simulated data and evaluates the efficacy of three distinct treatment approaches through statistical methods. The methodology integrate agent-based modeling with resilient engineering concepts to simulate mental health resilience curves based on vulnerability, exposure, and facility damage. Agents’ mental health indices were tracked through phases of degradation, stagnation, and recovery based on the three treatments …
Understanding The Acceptance Of Digital Tools Within An Air Force Environment Using The Utaut2 Model,
2025
Air Force Institute of Technology
Understanding The Acceptance Of Digital Tools Within An Air Force Environment Using The Utaut2 Model, Britton J. Edwards
Theses and Dissertations
This research paper explores factors influencing digital tool adoption in a military context, using a modified UTAUT2 model with the inclusion of Military Status as a moderating factor. The study examines the moderating effects of Military Status on Social Influence towards Behavioral Intention and Behavioral Intention on Use Behavior. Data was collected through a Likert-scale survey from respondents across multiple Department of the Air Force (DAF) organizations. Findings revealed Social Influence had the potential to positively influence Behavioral Intention to use digital tools, but military experience did not significantly moderate this relationship. However, past experience with the legacy tool and …
Performing Requirements Specification And Analysis Through Open Generative Pre-Trained Transformers,
2025
Air Force Institute of Technology
Performing Requirements Specification And Analysis Through Open Generative Pre-Trained Transformers, Harvey J. Hurst
Theses and Dissertations
Every acquisition program begins with a requirement, and for those programs to succeed, robust requirements engineering (RE) must be implemented. RE encompasses eliciting, analyzing, specifying, and validating requirements—a critical process throughout a program's lifecycle. Despite its importance, RE faces challenges such as scope creep, ambiguity, redundancy, and inadequate automation support, often exacerbated by reliance on historical data. To address these issues, this thesis leverages advancements in Generative Technology, particularly large language models (LLMs) such as Generative Pre-Trained Transformers (GPTs). This research developed two GPT-based tools: the Single Requirement Analysis Tool and the Set of Requirements Analysis Tool. These tools were …
Model-Based Approach To Support Safety Driven Design And Satisfy Mil-Std-882e Requirements With Stpa Coordination: A Case History In Suas Defense Acquisition,
2025
Air Force Institute of Technology
Model-Based Approach To Support Safety Driven Design And Satisfy Mil-Std-882e Requirements With Stpa Coordination: A Case History In Suas Defense Acquisition, Daniel A. Shea
Theses and Dissertations
Increasingly complex defense systems that are routinely overbudget and behind schedule are driving digital engineering initiatives in the defense acquisition industry. MBSE offers a solution to counter this issue but the lack of guidance on how to implement it has led to significant experimentation. One MBSE area of interest is system safety. This research demonstrates how to conduct model-based Systems Theoretic Process Analysis (STPA) to meet the unique system safety process requirements from MIL-STD882E. Based in systems theory, STPA extended for coordination enables a safety-driven design process of complex systems. This research investigated conducting STPA in the SysML-RAAML modeling language …
A Reinforcement Learning Approach For Maneuvering And Firing Decisions In Sead Operations,
2025
Air Force Institute of Technology
A Reinforcement Learning Approach For Maneuvering And Firing Decisions In Sead Operations, Nathaniel Garcia
Theses and Dissertations
The integration of automated processes in defense continues to expand, enhancing the lethality of military forces. Artificial intelligence accelerates decision-making cycles, removes the constraints of human-operated hardware, and improves coordination by enabling seamless integration across multiple systems. Suppression of Enemy Air Defenses (SEAD) missions are critical to the United States (U.S.) military, as they neutralize hostile air defense systems, ensuring air superiority and enabling safe and effective operations for aircraft in contested environments. Therefore, it is necessary to pair emerging autonomous capabilities with an important mission set in defense. This research investigates the Autonomous Unmanned Air-to-Ground Strike (AUAGS) problem, modeling …
Symbology Detection And Numerical Recognition For T-38 Heads-Up Display Recordings,
2025
Air Force Institute of Technology
Symbology Detection And Numerical Recognition For T-38 Heads-Up Display Recordings, Ben T. Hepner
Theses and Dissertations
The extraction of symbology and numerical data from the T-38 Heads-Up Display (HUD) enhances post-flight analysis and supports real-time decision-making. This research develops a deep learning pipeline using YOLO-based object detection and Optical Character Recognition (OCR) to analyze HUD video data. Model evaluations showed mAP0.5:0.95 ranging from 0.422 (YOLOv11m, hard test set) to 0.696 (YOLOv8m, medium test set), demonstrating robust symbology detection. Numeric detection performed well (mAP0.5:0.95 = 0.764), but OCR struggled with glare and resolution limitations, achieving a recognition accuracy of 17.35%. These results validate deep learning for HUD data extraction but highlight the need for improved robustness …
Evaluating The Performance Of Conformal Prediction Generated Uncertainty Sets In Robust Optimization,
2025
Air Force Institute of Technology
Evaluating The Performance Of Conformal Prediction Generated Uncertainty Sets In Robust Optimization, Zion C. Johnson
Theses and Dissertations
Uncertainty is a major challenge in optimization, especially in problems where unpredictable costs impact decision-making. Robust optimization addresses this by modeling uncertainty via uncertainty sets. These sets are then used such that solutions hold under worst-case scenarios, with success depending on the accuracy of the uncertainty sets. This research examines the use of conformal prediction to construct uncertainty sets for RO, an approach that has not been widely explored. We test split and full conformal prediction in a robust optimization minimum cost flow problem, and comparing them to interval-based and normal-based ellipsoidal uncertainty sets. Experiments run across different network structures …
Proximal Policy Optimization Applied To The Beyond Visual Range Air Combat Maneuvering Problem,
2025
Air Force Institute of Technology
Proximal Policy Optimization Applied To The Beyond Visual Range Air Combat Maneuvering Problem, Daniel B. Joseph
Theses and Dissertations
Artificial intelligence (AI) grows ever-more important in warfighting. Emerging technologies allow for the use of AI to control aircraft and weapons systems. This research investigates the application of reinforcement learning (RL) through the Proximal Policy Optimization (PPO) algorithm to a two-versus-two (2v2) beyond-visual-range (BVR) air combat maneuvering problem (ACMP). Implemented in the Advanced Framework for Simulation, Integration, and Modeling (AFSIM), the methodology frames the engagement as a Markov decision process, wherein an autonomous RL agent learns continuous control decisions—throttle, pitch, roll, and yaw—under a cooperative communication scheme. A multi-phase curriculum-learning approach facilitates the progressive acquisition of flight stability, weapon deployment, …
Learning To Dogfight: Proximal Policy Optimization Vs. Double Deep Q Network For 2v2 Air Combat With Directed Energy Weapons In Afsim,
2025
Air Force Institute of Technology
Learning To Dogfight: Proximal Policy Optimization Vs. Double Deep Q Network For 2v2 Air Combat With Directed Energy Weapons In Afsim, Caden W. Wilson
Theses and Dissertations
This research utilizes reinforcement learning (RL) to train two blue agents each imbued with a directed energy weapon (DEW) in a 2v2 within visual range air combat maneuvering problem. A phased solution approach is employed to repeatedly tune and train several RL algorithm implementations: Proximal Policy Optimization (PPO) and Double Deep Q Network (DDQN). Phase I of training includes reward shaping for basic flight elements such as altitude, airspeed, and target proximity. Phase II of training builds off policies developed in Phase I, but rewards emphasize winning the aerial engagement by any means necessary. DDQN significantly outperforms PPO in Phase …
