Subjects in figures have consented to appearing in publications. The Biometric Recognition at Altitude and Range (BRIAR) Program is a US Government sponsored initiative to advance the state of the art of biometric recognition under military-grade and specialized cameras at ranges up to 1,000-challenging conditions. The overarching goal is to develop m, at view angles up to 50, and during both constrained and end-to-end software systems capable of overcoming severe unconstrained imaging scenarios. Model development and atmospheric distortion and difficult imaging conditions, perform testing is driven by continued expansion of the dataset and person detection and tracking, and fuse multi-modal efforts to improve its quality by refining collection, curation, data for effective biometric recognition. To enable the development, and annotation methods [4]. The addition of more diverse testing, and evaluation of these software systems, the data, both in terms of the demographics pool of its enrolled BRIAR Testing and Evaluation Team has gone great lengths subjects and the imaging conditions of the collection, will to build and extend a one-of-a-kind dataset of images and help to ensure that recognition models are equitable and video over the course of multiple data collection events.

State-space formulations allow for Gaussian process (GP) regression with linear-in-time computational cost in spatio-temporal settings, but performance typically suffers in the presence of outliers. In this paper, we adapt and specialise the robust and conjugate GP (RCGP) framework of Altamirano et al. (2024) to the spatio-temporal setting. In doing so, we obtain an outlier-robust spatio-temporal GP with a computational cost comparable to classical spatio-temporal GPs. We also overcome the three main drawbacks of RCGPs: their unreliable performance when the prior mean is chosen poorly, their lack of reliable uncertainty quantification, and the need to carefully select a hyperparameter by hand. We study our method extensively in finance and weather forecasting applications, demonstrating that it provides a reliable approach to spatio-temporal modelling in the presence of outliers.

Selecting cost-effective optimal sensor configurations for subsequent inference of parameters in black-box stochastic systems faces significant computational barriers. We propose a novel and robust approach, modelling the joint distribution over input parameters and solution with a joint energy-based model, trained on simulation data. Unlike existing simulation-based inference approaches, which must be tied to a specific set of point evaluations, we learn a functional representation of parameters and solution. This is used as a resolution-independent plug-and-play surrogate for the joint distribution, which can be conditioned over any set of points, permitting an efficient approach to sensor placement. We demonstrate the validity of our framework on a variety of stochastic problems, showing that our method provides highly informative sensor locations at a lower computational cost compared to conventional approaches.

It is vital that we develop appropriate statistical models to represent and extract valuable insights from these large datasets, since the bridges constitute critical infrastructure within modern transportation networks. The process of monitoring engineered systems via streaming data is typically referred to as Structural Health Monitoring (SHM) and while successful applications have been emerging in recent years, a number of challenges remain for practical implementation [5]. During model design, these concerns usually centre around low variance data: that is, measurements are not available for the entire range of expected operational, environmental, and damage conditions. Consider a bridge following construction, this will have a relatively small dataset that should only be associated with normal operation. On the other hand, a structure with historical data might still not experience low-probability events - such as extreme weather or landslides. An obvious solution considers sharing data (or information) between structures; this has been the focus of a large body of recent work [6-8].

Data from populations of systems are prevalent in many industrial applications. Machines and infrastructure are increasingly instrumented with sensing systems, emitting streams of telemetry data with complex interdependencies. In practice, data-centric monitoring procedures tend to consider these assets (and respective models) as distinct -- operating in isolation and associated with independent data. In contrast, this work captures the statistical correlations and interdependencies between models of a group of systems. Utilising a Bayesian multilevel approach, the value of data can be extended, since the population can be considered as a whole, rather than constituent parts. Most interestingly, domain expertise and knowledge of the underlying physics can be encoded in the model at the system, subgroup, or population level. We present an example of acoustic emission (time-of-arrival) mapping for source location, to illustrate how multilevel models naturally lend themselves to representing aggregate systems in engineering. In particular, we focus on constraining the combined models with domain knowledge to enhance transfer learning and enable further insights at the population level.

Energy-Based Models (EBMs) have proven to be a highly effective approach for modelling densities on finite-dimensional spaces. Their ability to incorporate domain-specific choices and constraints into the structure of the model through composition make EBMs an appealing candidate for applications in physics, biology and computer vision and various other fields. In this work, we present a novel class of EBM which is able to learn distributions of functions (such as curves or surfaces) from functional samples evaluated at finitely many points. Two unique challenges arise in the functional context. Firstly, training data is often not evaluated along a fixed set of points. Secondly, steps must be taken to control the behaviour of the model between evaluation points, to mitigate overfitting. The proposed infinite-dimensional EBM employs a latent Gaussian process, which is weighted spectrally by an energy function parameterised with a neural network. The resulting EBM has the ability to utilize irregularly sampled training data and can output predictions at any resolution, providing an effective approach to up-scaling functional data. We demonstrate the efficacy of our proposed approach for modelling a range of datasets, including data collected from Standard and Poor's 500 (S\&P) and UK National grid.