Nick Pepper
YOU?
Author Swipe
View article: AirTrafficGen: Configurable Air Traffic Scenario Generation with Large Language Models
AirTrafficGen: Configurable Air Traffic Scenario Generation with Large Language Models Open
The manual design of scenarios for Air Traffic Control (ATC) training is a demanding and time-consuming bottleneck that limits the diversity of simulations available to controllers. To address this, we introduce a novel, end-to-end approac…
View article: The Future of (Environmental) History: A Roundtable Discussion
The Future of (Environmental) History: A Roundtable Discussion Open
In April 2023, eighteen scholars from nine different subjects representing the humanities, natural and social sciences came together for a one-day workshop at St John’s College, Durham. Despite our differences, all had one aim: the study o…
View article: Air Traffic Controller Task Demand via Graph Neural Networks: An Interpretable Approach to Airspace Complexity
Air Traffic Controller Task Demand via Graph Neural Networks: An Interpretable Approach to Airspace Complexity Open
Real-time assessment of near-term Air Traffic Controller (ATCO) task demand is a critical challenge in an increasingly crowded airspace, as existing complexity metrics often fail to capture nuanced operational drivers beyond simple aircraf…
View article: Probabilistic Simulation of Aircraft Descent via a Physics-Informed Machine Learning Approach
Probabilistic Simulation of Aircraft Descent via a Physics-Informed Machine Learning Approach Open
This paper presents a method for generating probabilistic descent trajectories in simulations of real-world airspace. A dataset of 116,066 trajectories harvested from Mode S radar returns in UK airspace was used to train and test the model…
View article: Geometric Principles for Machine Learning of Dynamical Systems
Geometric Principles for Machine Learning of Dynamical Systems Open
Mathematical descriptions of dynamical systems are deeply rooted in topological spaces defined by non-Euclidean geometry. This paper proposes leveraging structure-rich geometric spaces for machine learning to achieve structural generalizat…
View article: SeAr PC: Sensitivity Enhanced Arbitrary Polynomial Chaos
SeAr PC: Sensitivity Enhanced Arbitrary Polynomial Chaos Open
This paper presents a method for performing Uncertainty Quantification in high-dimensional uncertain spaces by combining arbitrary polynomial chaos with a recently proposed scheme for sensitivity enhancement (1). Including available sensit…
View article: Learning Generative Models for Climbing Aircraft from Radar Data
Learning Generative Models for Climbing Aircraft from Radar Data Open
Accurate trajectory prediction (TP) for climbing aircraft is hampered by the presence of epistemic uncertainties concerning aircraft operation, which can lead to significant misspecification between predicted and observed trajectories. Thi…
View article: Context-Aware Generative Models for Prediction of Aircraft Ground Tracks
Context-Aware Generative Models for Prediction of Aircraft Ground Tracks Open
Trajectory prediction (TP) plays an important role in supporting the decision-making of Air Traffic Controllers (ATCOs). Traditional TP methods are deterministic and physics-based, with parameters that are calibrated using aircraft surveil…
View article: A probabilistic model for aircraft in climb using monotonic functional Gaussian process emulators
A probabilistic model for aircraft in climb using monotonic functional Gaussian process emulators Open
Ensuring vertical separation is a key means of maintaining safe separation between aircraft in congested airspace. Aircraft trajectories are modelled in the presence of significant epistemic uncertainty, leading to discrepancies between ob…
View article: Probabilistic Machine Learning to Improve Generalisation of Data-Driven Turbulence Modelling
Probabilistic Machine Learning to Improve Generalisation of Data-Driven Turbulence Modelling Open
A probabilistic machine learning model is introduced to augment the $k-ω SST$ turbulence model in order to improve the modelling of separated flows and the generalisability of learnt corrections. Increasingly, machine learning methods have…
View article: A Probabilistic Model for Aircraft in Climb using Monotonic Functional Gaussian Process Emulators
A Probabilistic Model for Aircraft in Climb using Monotonic Functional Gaussian Process Emulators Open
Ensuring vertical separation is a key means of maintaining safe separation between aircraft in congested airspace. Aircraft trajectories are modelled in the presence of significant epistemic uncertainty, leading to discrepancies between ob…
View article: Adaptive learning for reliability analysis using Support Vector Machines
Adaptive learning for reliability analysis using Support Vector Machines Open
Given an expensive computational model of a system subject to reliability requirements, this work shows how to approximate the failure probability by learning adaptively the high-likelihood regions of the Limit State Function using Support…
View article: Machine Learning Methods in CFD for Turbomachinery: A Review
Machine Learning Methods in CFD for Turbomachinery: A Review Open
Computational Fluid Dynamics is one of the most relied upon tools in the design and analysis of components in turbomachines. From the propulsion fan at the inlet, through the compressor and combustion sections, to the turbines at the outle…