arXiv subjects

Jonathan Smith

Publications and source records attributed to Jonathan Smith.

16 recordsLinked to original sources

arXiv2026

Marine Autonomous Vehicle Fleet Scheduling to Maximise Scientific Impact

The marine science community increasingly relies on Marine Autonomous Vehicles (MAVs) to collect the critical environmental data required to understand global ocean systems. However, as these operations scale, manually routing and planning large autonomous fleets becomes exponentially complex and time-consuming. To address this, we propose a mixed-integer linear programming (MILP) model designed to automate and optimise MAV deployment schedules. The model accounts for strict operational constraints, including battery capacities and time windows for data collection, while aiming to maximise total data collection and minimise both the number of deployed vehicles and their energy consumption. A key novelty of this framework is integrating conventional ship itineraries, allowing MAVs to support vessels with mid-mission battery swapping or accelerated transit between waypoints. Computational experiments demonstrate that the model is highly scalable, solving routing problems for fleets of dozens of MAVs in seconds, and scaling to hundreds of vehicles in only a few minutes. Beyond operational scheduling, the framework serves as a robust simulation tool for evaluating 'what-if' scenarios and analysing the impact of varying parameters on deployment strategies. Finally, the solution generates a suite of visualisations designed to enhance explainability and support strategic decision-making for stakeholders.

math.OC↗

arXiv2026

Multiscale Decomposition Reveals Predictable Interannual Variability and Climate Trends in Antarctic Sea Ice Loss

Antarctic sea ice has undergone unprecedented changes in recent years, raising questions about how this key geophysical system is responding to climate change. Decades of slow expansion were replaced by a precipitous decline in 2014-2017, a subsequent apparent recovery, and a renewed collapse from 2022 to the present. We diagnosed sea ice concentration (SIC) from satellite observations with a hierarchical decomposition method based on Dynamic Mode Decomposition (DMD) that finds coherent spatiotemporal modes. We find that the 2014-2017 decline and apparent recovery are the result of interacting interannual modes and that a climate change signal emerges in 2012, which becomes unambiguous by 2022 when it dominates over interannual variability. These rapid changes underscore the need for seasonal-to-annual forecasts of SIC. However, existing forecasts are subject to limited prediction horizons combined with high computational costs. Our predictive DMD model (IceDMD) is regularised to prioritize the stationary spatiotemporal modes found by the decomposition. The predictive model can forecast SIC anomalies in 2023-2024 up to two years in advance, outperforming all existing approaches with the additional benefits of physical interpretability and extremely cheap computational cost. Finally, this framework for regularising predictive DMD models can be generalized to a range of multi-scale systems.

physics.ao-ph↗

arXiv2026

Beware of GeeksBearing Gifts: Building True EU Frontier AI Sovereignty

Frontier artificial intelligence is reshaping all aspects of society, from economic output or military capability to democratic institutions. The EU is entering this transformation from a position of structural dependence: frontier models originate almost exclusively from the United States or China, the US holds approximately sixteen times the EU's AI supercomputing capacity, and only 15% of global hyperscale data centre capacity resides within EU borders. Although the European Commission has accelerated its policy response, existing initiatives remain fragmented and lack a cohesive vision for securing strategic autonomy across the full frontier AI value chain. Here we propose a unified framework connecting five sovereignty pillars (economic competitiveness, resilience, security and defence, European values, and foreign relations) to a decomposition of the frontier AI stack comprising five layers, 26 components, and 29 sub-components. This framework allows the identification of critical gaps, redundancies, and inter-pillar trade-offs that current EU policy leaves implicit. Our analysis of the AI Gigafactory Initiative illustrates how a sovereignty-centred lens reveals conflicts that narrowly economic framings obscure. Moreover, this framework offers policymakers a structured basis for designing, evaluating, and prioritising frontier AI interventions across multiple dimensions of European strategic autonomy across the 92 initiatives from four major Commission communications we. identify, and beyond.

cs.CY↗

arXiv2025

The promising potential of vision language models for the generation of textual weather forecasts

Despite the promising capability of multimodal foundation models, their application to the generation of meteorological products and services remains nascent. To accelerate aspiration and adoption, we explore the novel use of a vision language model for writing the iconic Shipping Forecast text directly from video-encoded gridded weather data. These early results demonstrate promising scalable technological opportunities for enhancing production efficiency and service innovation within the weather enterprise and beyond.

cs.LG↗

arXiv2025

Cultivating Pluralism In Algorithmic Monoculture: The Community Alignment Dataset

How can large language models (LLMs) serve users with varying preferences that may conflict across cultural, political, or other dimensions? To advance this challenge, this paper establishes four key results. First, we demonstrate, through a large-scale multilingual human study with representative samples from five countries (N=15,000), that humans exhibit substantially more variation in preferences than the responses of 21 state-of-the-art LLMs. Second, we show that existing methods for preference dataset collection are insufficient for learning the diversity of human preferences even along two of the most salient dimensions of variability in global values, due to the underlying homogeneity of candidate responses. Third, we argue that this motivates the need for negatively-correlated sampling when generating candidate sets, and we show that simple prompt-based techniques for doing so greatly enhance the performance of alignment methods in learning heterogeneous preferences. Fourth, based on this novel candidate sampling approach, we collect and open-source Community Alignment} the largest and most representative multilingual and multi-turn preference dataset to date, featuring 233,319 comparisons from annotators spanning five countries. Overall, we hope that the Community Alignment dataset will be a valuable resource for improving the effectiveness of LLMs for a diverse global population.

cs.LG↗

arXiv2025

Self-driving technologies need the help of the public: A narrative review of the evidence

If public trust is lost in a new technology early in its life cycle it can take much more time for the benefits of that technology to be realised. Eventually tens-of-millions of people will collectively have the power to determine self-driving technology success of failure driven by their perception of risk, data handling, safety, governance, accountability, benefits to their life and more. This paper reviews the evidence on safety critical technology covering trust, engagement, and acceptance. The paper takes a narrative review approach concluding with a scalable model for self-driving technology education and engagement. The paper find that if a mismatch between the publics perception and expectations about self driving systems emerge it can lead to misuse, disuse, or abuse of the system. Furthermore we find from the evidence that industrial experts often misunderstand what matters to the public, users, and stakeholders. However we find that engagement programmes that develop approaches to defining the right information at the right time, in the right format orientated around what matters to the public creates the potential for ever more sophisticated conversations, greater trust, and moving the public into a progressive more active role of critique and advocacy. This work has been undertaken as part of the Partners for Automated Vehicle Education (PAVE) United Kingdom programme.

cs.HC↗

arXiv2024

Predicting quantum materials properties using novel faithful machine learning embeddings

Machine Learning (ML) is accelerating the progress of materials prediction and classification, with particular success in CGNN designs. While classical ML methods remain accessible, advanced deep networks are still challenging to build and train. We introduce two new adaptations and refine two existing ML networks for generic crystalline quantum materials properties prediction and optimization. These new models achieve state-of-the-art performance in predicting TQC classification and strong performance in predicting band gaps, magnetic classifications, formation energies, and symmetry group. All networks easily generalize to all quantum crystalline materials property predictions. To support this, full implementations and automated methods for data handling and materials predictions are provided, facilitating the use of deep ML methods in quantum materials science. Finally, dataset error rates are analyzed using an ensemble model to identify and highlight highly atypical materials for further investigations.

cond-mat.other↗

arXiv2024

Case Studies of AI Policy Development in Africa

Artificial Intelligence (AI) requires new ways of evaluating national technology use and strategy for African nations. We conduct a survey of existing 'readiness' assessments both for general digital adoption and for AI policy in particular. We conclude that existing global readiness assessments do not fully capture African states' progress in AI readiness and lay the groundwork for how assessments can be better used for the African context. We consider the extent to which these indicators map to the African context and what these indicators miss in capturing African states' on-the-ground work in meeting AI capability. Through case studies of four African nations of diverse geographic and economic dimensions, we identify nuances missed by global assessments and offer high-level policy considerations for how states can best improve their AI readiness standards and prepare their societies to capture the benefits of AI.

cs.CY↗

arXiv2021

Temporal Dependencies in Feature Importance for Time Series Predictions

Time series data introduces two key challenges for explainability methods: firstly, observations of the same feature over subsequent time steps are not independent, and secondly, the same feature can have varying importance to model predictions over time. In this paper, we propose Windowed Feature Importance in Time (WinIT), a feature removal based explainability approach to address these issues. Unlike existing feature removal explanation methods, WinIT explicitly accounts for the temporal dependence between different observations of the same feature in the construction of its importance score. Furthermore, WinIT captures the varying importance of a feature over time, by summarizing its importance over a window of past time steps. We conduct an extensive empirical study on synthetic and real-world data, compare against a wide range of leading explainability methods, and explore the impact of various evaluation strategies. Our results show that WinIT achieves significant gains over existing methods, with more consistent performance across different evaluation metrics. The code for our work is publicly available at \url{https://github.com/layer6ai-labs/WinIT}.

cs.LG↗

arXiv2020

Non-Pharmaceutical Intervention Discovery with Topic Modeling

We consider the task of discovering categories of non-pharmaceutical interventions during the evolving COVID-19 pandemic. We explore topic modeling on two corpora with national and international scope. These models discover existing categories when compared with human intervention labels while reduced human effort needed.

cs.CL↗

arXiv2019

Plasma-photonic spatiotemporal synchronization of relativistic electron and laser beams

Modern particle accelerators and their applications increasingly rely on precisely coordinated interactions of intense charged particle and laser beams. Femtosecond-scale synchronization alongside micrometre-scale spatial precision are essential e.g. for pump-probe experiments, seeding and diagnostics of advanced light sources and for plasma-based accelerators. State-of-the-art temporal or spatial diagnostics typically operate with low-intensity beams to avoid material damage at high intensity. As such, we present a plasma-based approach, which allows measurement of both temporal and spatial overlap of high-intensity beams directly at their interaction point. It exploits amplification of plasma afterglow arising from the passage of an electron beam through a laser-generated plasma filament. The corresponding photon yield carries the spatiotemporal signature of the femtosecond-scale dynamics, yet can be observed as a visible light signal on microsecond-millimetre scales.

physics.plasm-ph↗

arXiv2018

Pocket Code: a mobile app for game jams to facilitate classroom learning through game creation

Game jams are a way to create games under fast-paced conditions and certain constraints. The increase in game jam events all over the world, their engaging and creative nature, with the aim of sharing results among players can be seen in the high participation rate of such events (2013: 16,705 participants from 319 jam sites in 63 countries produced 3248 games) . This promising concept can be easily transferred to a classroom setting.

cs.CY↗

arXiv2018

Pocket Game Jams: a Constructionist Approach at Schools

The constructionist approach is more interested in constructing personal experience than about acquiring information. It states that learning is most effective when building knowledge through active engagement. Experiential and discovery learning by challenges inspire creativity, and projects allow independent thinking and new ways of learning information. This paper describes how the "No One Left Behind" (NOLB) project plans to integrate this approach into school curricula using two concepts. The first one is to enable students to create their own games with Pocket Code by using its easy-to-learn visual programming language. The second concept is to foster collaboration and teamwork through hands-on sessions by conducting Game Jams using Pocket Code, so called Pocket Game Jams. We present insights into such a Pocket Game Jam and give an outlook on how we will use this concept.

cs.CY↗

arXiv2017

Energy efficiency studies for dual-grating dielectric laser-driven accelerators

Dielectric laser-driven accelerators (DLAs) can provide high accelerating gradients in the GV/m range due to their having higher breakdown thresholds than metals, which opens the way for the miniaturization of the next generation of particle accelerator facilities. Two kinds of scheme, the addition of a Bragg reflector and the use of pulse-front-tilted (PFT) laser illumination, have been studied separately to improve the energy efficiency for dual-grating DLAs. The Bragg reflector enhances the accelerating gradient of the structure, while the PFT increases the effective interaction length. In this paper, we investigate numerically the advantages of using the two schemes in conjunction. Our calculations show that, for a 100-period structure with a period of 2 micrometer, such a design effectively increases the energy gain by more than 100 % when compared to employing the Bragg reflector with a normal laser, and by about 50 % when using standard structures with a PFT laser. A total energy gain of as much as 2.6 MeV can be obtained for a PFT laser beam when illuminating a 2000-period dual-grating structure with a Bragg reflector.

physics.acc-ph↗

arXiv2017

Simulation studies for dielectric wakefield programme at CLARA facility

Short, high charge electron bunches can drive high magnitude electric fields in dielectric lined structures. The interaction of the electron bunch with this field has several applications including high gradient dielectric wakefield acceleration (DWA) and passive beam manipulation. The simulations presented provide a prelude to the commencement of an experimental DWA programme at the CLARA accelerator at Daresbury Laboratory. The key goals of this program are: tunable generation of THz radiation, understanding of the impact of transverse wakes, and design of a dechirper for the CLARA FEL. Computations of longitudinal and transverse phase space evolution were made with Impact-T and VSim to support both of these goals.

physics.acc-ph↗

arXiv2017

Hierarchical Label Inference for Video Classification

Videos are a rich source of high-dimensional structured data, with a wide range of interacting components at varying levels of granularity. In order to improve understanding of unconstrained internet videos, it is important to consider the role of labels at separate levels of abstraction. In this paper, we consider the use of the Bidirectional Inference Neural Network (BINN) for performing graph-based inference in label space for the task of video classification. We take advantage of the inherent hierarchy between labels at increasing granularity. The BINN is evaluated on the first and second release of the YouTube-8M large scale multilabel video dataset. Our results demonstrate the effectiveness of BINN, achieving significant improvements against baseline models.

cs.CV↗