arXiv subjects

John Taylor

Publications and source records attributed to John Taylor.

At least 19 recordsLinked to original sources

arXiv2026

Season-Aware Hybrid Convolutional-Transformer for Antarctic Sea Ice Concentration Forecasting

Antarctic sea ice concentration (SIC) forecasting is an important yet challenging task due to the coexistence of complex spatial structure, long-range temporal dependencies, and strong seasonal variability. Conventional convolution-based models are effective at capturing local spatial patterns, but often have limited ability to model long-term temporal evolution. To address these challenges, we build on a hybrid Convolutional-Transformer forecasting framework for monthly Antarctic SIC forecasting. This framework combines convolutional encoding for spatial feature extraction with factorised self-attention for spatio-temporal dependency modelling. We further introduce two seasonal prior mechanisms: a month-aware positional encoding that injects calendar-month information into the token representation, and a seasonal temporal bias that encourages attention to periodically related historical states. Experimental results show that the proposed framework achieves better performance than convolutional and recurrent baselines across both classification and regression metrics. Ablation studies further indicate that the seasonal prior mechanisms provide consistent additional gains in both short- and long-horizon prediction. These results demonstrate the value of combining convolutional structures, attention mechanisms, and periodic prior information for Antarctic SIC forecasting.

cs.LG↗

arXiv2026

Domain-Decomposed Lagrangian Data Assimilation for Drifting Sea-Ice Floe Dynamics

Sea ice dynamics are crucial to the global climate system, yet traditional continuum (e.g., viscous-plastic) models often fail to represent the discrete floe interactions that dominate in the marginal ice zone. Lagrangian discrete element methods (DEMs) resolve floe-scale physics more realistically, but their high particle counts make ensemble data assimilation (DA) more expensive. We consider a highly-simplified floe model and propose a scalable, domain-decomposed DA framework that couples Lagrangian particle observations with an ensemble transform Kalman filter (ETKF) to recover the underlying ocean flow field in a multiscale setting. The Eulerian domain is first partitioned into subdomains. We then impose an ETKF in each subdomain to recover the local fine-scale ocean features. A Gaussian-weighted blending step then reconstructs a globally consistent flow field across subdomain boundaries. Numerical experiments demonstrate consistently better skill scores that are characterised by normalised root mean square error (NRMSE) and pattern correlation coefficients (PCC), compared to the global and expensive DA baseline. Results suggest that the domain-decomposed DA method is an alternative, scalable approach for particle-based sea-ice floe dynamics and ocean flow recovery.

cs.CE↗

arXiv2025

C3PO IV: co-natal stars depleted in refractories are magnetically more active -- possible imprints of planets

Chemical abundance anomalies in twin stars have recently been considered tell-tale signs of interactions between stars and planets. While such signals are prevalent, their nature remains a subject of debate. On one hand, exoplanet formation may induce chemical depletion in host stars by locking up refractory elements. On the other hand, exoplanet engulfment can result in chemical enrichment, both processes potentially producing similar differential signals. In this study, we aim to observationally disentangle these processes by using the Ca II infrared triplet to measure the magnetic activity of 125 co-moving star pairs with high SNR, high-resolution spectra from the Magellan, Keck, and VLT telescopes. We find that co-natal star pairs in which the two stars exhibit significant chemical abundance differences also show differences in their magnetic activity, with stars depleted in refractories being magnetically more active. Furthermore, the strength of this correlation between differential chemical abundances and differential magnetic activity increases with condensation temperature. One possible explanation is that the chemical anomaly signature may be linked to planet formation, wherein refractory elements are locked into planets, and the host stars become more active due to more efficient contraction during the pre-main-sequence phase or star-planet tidal and magnetic interactions.

astro-ph.EP↗

arXiv2024

Signal processing and spectral modeling for the BeEST experiment

The Beryllium Electron capture in Superconducting Tunnel junctions (BeEST) experiment searches for evidence of heavy neutrino mass eigenstates in the nuclear electron capture decay of $^7$Be by precisely measuring the recoil energy of the $^7$Li daughter. In Phase-III, the BeEST experiment has been scaled from a single superconducting tunnel junction (STJ) sensor to a 36-pixel array to increase sensitivity and mitigate gamma-induced backgrounds. Phase-III also uses a new continuous data acquisition system that greatly increases the flexibility for signal processing and data cleaning. We have developed procedures for signal processing and spectral fitting that are sufficiently robust to be automated for large data sets. This article presents the optimized procedures before unblinding the majority of the Phase-III data set to search for physics beyond the standard model.

physics.ins-det↗

arXiv2024

Tackling fluffy clouds: robust field boundary delineation across global agricultural landscapes with Sentinel-1 and Sentinel-2 Time Series

Accurate delineation of agricultural field boundaries is essential for effective crop monitoring and resource management. However, competing methodologies often face significant challenges, particularly in their reliance on extensive manual efforts for cloud-free data curation and limited adaptability to diverse global conditions. In this paper, we introduce PTAViT3D, a deep learning architecture specifically designed for processing three-dimensional time series of satellite imagery from either Sentinel-1 (S1) or Sentinel-2 (S2). Additionally, we present PTAViT3D-CA, an extension of the PTAViT3D model incorporating cross-attention mechanisms to fuse S1 and S2 datasets, enhancing robustness in cloud-contaminated scenarios. The proposed methods leverage spatio-temporal correlations through a memory-efficient 3D Vision Transformer architecture, facilitating accurate boundary delineation directly from raw, cloud-contaminated imagery. We comprehensively validate our models through extensive testing on various datasets, including Australia's ePaddocks - CSIRO's national agricultural field boundary product - alongside public benchmarks Fields-of-the-World, PASTIS, and AI4SmallFarms. Our results consistently demonstrate state-of-the-art performance, highlighting excellent global transferability and robustness. Crucially, our approach significantly simplifies data preparation workflows by reliably processing cloud-affected imagery, thereby offering strong adaptability across diverse agricultural environments. Our code and models are publicly available at https://github.com/feevos/tfcl.

cs.CV↗

arXiv2024

Direct Experimental Constraints on the Spatial Extent of a Neutrino Wavepacket

Despite their high relative abundance in our Universe, neutrinos are the least understood fundamental particles of nature. They also provide a unique system to study quantum coherence and the wavelike nature of particles in fundamental systems due to their extremely weak interaction probabilities. In fact, the quantum properties of neutrinos emitted in experimentally relevant sources are virtually unknown and the spatial extent of the neutrino wavepacket is only loosely constrained by reactor neutrino oscillation data with a spread of 13 orders of magnitude. Here, we present the first direct limits of this quantity through a new experimental concept to extract the energy width, $\sigma_{\textrm{N},E}$, of the recoil daughter nucleus emitted in the nuclear electron capture (EC) decay of $^7$Be. The final state in the EC decay process contains a recoiling $^7$Li nucleus and an electron neutrino ($\nu_e$) which are entangled at their creation. The $^7$Li energy spectrum is measured to high precision by directly embedding $^7$Be radioisotopes into a high resolution superconducting tunnel junction that is operated as a cryogenic sensor. The lower limit on the spatial uncertainty of the recoil daughter was found to be $\sigma_{\textrm{N}, x} \geq 6.2$\,pm, which implies the final-state system is localized at a scale more than a thousand times larger than the nucleus itself. From this measurement, the first direct lower limits on the spatial extent of the neutrino wavepacket were extracted using two different theoretical methods. These results have wide-reaching implications in several areas including the nature of spatial localization at sub-atomic scales, interpretation of neutrino physics data, and the potential reach of future large-scale experiments.

nucl-ex↗

arXiv2023

PAUNet: Precipitation Attention-based U-Net for rain prediction from satellite radiance data

This paper introduces Precipitation Attention-based U-Net (PAUNet), a deep learning architecture for predicting precipitation from satellite radiance data, addressing the challenges of the Weather4cast 2023 competition. PAUNet is a variant of U-Net and Res-Net, designed to effectively capture the large-scale contextual information of multi-band satellite images in visible, water vapor, and infrared bands through encoder convolutional layers with center cropping and attention mechanisms. We built upon the Focal Precipitation Loss including an exponential component (e-FPL), which further enhanced the importance across different precipitation categories, particularly medium and heavy rain. Trained on a substantial dataset from various European regions, PAUNet demonstrates notable accuracy with a higher Critical Success Index (CSI) score than the baseline model in predicting rainfall over multiple time slots. PAUNet's architecture and training methodology showcase improvements in precipitation forecasting, crucial for sectors like emergency services and retail and supply chain management.

physics.ao-ph↗

arXiv2023

SSG2: A new modelling paradigm for semantic segmentation

State-of-the-art models in semantic segmentation primarily operate on single, static images, generating corresponding segmentation masks. This one-shot approach leaves little room for error correction, as the models lack the capability to integrate multiple observations for enhanced accuracy. Inspired by work on semantic change detection, we address this limitation by introducing a methodology that leverages a sequence of observables generated for each static input image. By adding this "temporal" dimension, we exploit strong signal correlations between successive observations in the sequence to reduce error rates. Our framework, dubbed SSG2 (Semantic Segmentation Generation 2), employs a dual-encoder, single-decoder base network augmented with a sequence model. The base model learns to predict the set intersection, union, and difference of labels from dual-input images. Given a fixed target input image and a set of support images, the sequence model builds the predicted mask of the target by synthesizing the partial views from each sequence step and filtering out noise. We evaluate SSG2 across three diverse datasets: UrbanMonitor, featuring orthoimage tiles from Darwin, Australia with five spectral bands and 0.2m spatial resolution; ISPRS Potsdam, which includes true orthophoto images with multiple spectral bands and a 5cm ground sampling distance; and ISIC2018, a medical dataset focused on skin lesion segmentation, particularly melanoma. The SSG2 model demonstrates rapid convergence within the first few tens of epochs and significantly outperforms UNet-like baseline models with the same number of gradient updates. However, the addition of the temporal dimension results in an increased memory footprint. While this could be a limitation, it is offset by the advent of higher-memory GPUs and coding optimizations.

cs.CV↗

arXiv2023

Diagnosing tracer transport in convective penetration of a stably stratified layer

We use large-eddy simulations to study the penetration of a buoyant plume carrying a passive tracer into a stably stratified layer with constant buoyancy frequency. Using a buoyancy-tracer volume distribution, we develop a method for objectively partitioning plume fluid in buoyancy-tracer space into three regions, each of which corresponds to a coherent region in physical space. Specifically, we identify a source region where undiluted plume fluid enters the stratified layer, a transport region where much of the transition from undiluted to mixed fluid occurs in the plume cap, and an accumulation region corresponding to a radially spreading intrusion. This method enables quantification of different measures of turbulence and mixing within each of the three regions, including potential energy and turbulent kinetic energy dissipation rates, an activity parameter, and the instantaneous mixing efficiency. We find that the most intense buoyancy gradients lie in a thin layer at the cap of the penetrating plume. This provides the primary stage of mixing between plume and environment and exhibits a mixing efficiency around 50%. Newly generated mixtures of environmental and plume fluid join the intrusion and experience relatively weak turbulence and buoyancy gradients. As the intrusion spreads radially, environmental fluid surrounding the intrusion is mixed into the intrusion with moderate mixing efficiency. This dominates the volume of environmental fluid entrained into the region containing plume fluid. However, the 'strongest' entrainment, as measured by the specific entrainment rate, is largest in the plume cap where the most buoyant environmental fluid is entrained.

physics.flu-dyn↗

arXiv2023

Earth Virtualization Engines -- A Technical Perspective

Participants of the Berlin Summit on Earth Virtualization Engines (EVEs) discussed ideas and concepts to improve our ability to cope with climate change. EVEs aim to provide interactive and accessible climate simulations and data for a wide range of users. They combine high-resolution physics-based models with machine learning techniques to improve the fidelity, efficiency, and interpretability of climate projections. At their core, EVEs offer a federated data layer that enables simple and fast access to exabyte-sized climate data through simple interfaces. In this article, we summarize the technical challenges and opportunities for developing EVEs, and argue that they are essential for addressing the consequences of climate change.

physics.ao-ph↗

arXiv2023

Machine Learning based Parameter Sensitivity of Regional Climate Models -- A Case Study of the WRF Model for Heat Extremes over Southeast Australia

Heatwaves and bushfires cause substantial impacts on society and ecosystems across the globe. Accurate information of heat extremes is needed to support the development of actionable mitigation and adaptation strategies. Regional climate models are commonly used to better understand the dynamics of these events. These models have very large input parameter sets, and the parameters within the physics schemes substantially influence the model's performance. However, parameter sensitivity analysis (SA) of regional models for heat extremes is largely unexplored. Here, we focus on the southeast Australian region, one of the global hotspots of heat extremes. In southeast Australia Weather Research and Forecasting (WRF) model is the widely used regional model to simulate extreme weather events across the region. Hence in this study, we focus on the sensitivity of WRF model parameters to surface meteorological variables such as temperature, relative humidity, and wind speed during two extreme heat events over southeast Australia. Due to the presence of multiple parameters and their complex relationship with output variables, a machine learning (ML) surrogate-based global sensitivity analysis method is considered for the SA. The ML surrogate-based Sobol SA is used to identify the sensitivity of 24 adjustable parameters in seven different physics schemes of the WRF model. Results show that out of these 24, only three parameters, namely the scattering tuning parameter, multiplier of saturated soil water content, and profile shape exponent in the momentum diffusivity coefficient, are important for the considered meteorological variables. These SA results are consistent for the two different extreme heat events. Further, we investigated the physical significance of sensitive parameters. This study's results will help in further optimising WRF parameters to improve model simulation.

physics.ao-ph↗

arXiv2022

Movement Analytics: Current Status, Application to Manufacturing, and Future Prospects from an AI Perspective

Data-driven decision making is becoming an integral part of manufacturing companies. Data is collected and commonly used to improve efficiency and produce high quality items for the customers. IoT-based and other forms of object tracking are an emerging tool for collecting movement data of objects/entities (e.g. human workers, moving vehicles, trolleys etc.) over space and time. Movement data can provide valuable insights like process bottlenecks, resource utilization, effective working time etc. that can be used for decision making and improving efficiency. Turning movement data into valuable information for industrial management and decision making requires analysis methods. We refer to this process as movement analytics. The purpose of this document is to review the current state of work for movement analytics both in manufacturing and more broadly. We survey relevant work from both a theoretical perspective and an application perspective. From the theoretical perspective, we put an emphasis on useful methods from two research areas: machine learning, and logic-based knowledge representation. We also review their combinations in view of movement analytics, and we discuss promising areas for future development and application. Furthermore, we touch on constraint optimization. From an application perspective, we review applications of these methods to movement analytics in a general sense and across various industries. We also describe currently available commercial off-the-shelf products for tracking in manufacturing, and we overview main concepts of digital twins and their applications.

cs.AI↗

arXiv2022

Optimizing the optimizer for data driven deep neural networks and physics informed neural networks

We investigate the role of the optimizer in determining the quality of the model fit for neural networks with a small to medium number of parameters. We study the performance of Adam, an algorithm for first-order gradient-based optimization that uses adaptive momentum, the Levenberg and Marquardt (LM) algorithm a second order method, Broyden,Fletcher,Goldfarb and Shanno algorithm (BFGS) a second order method and LBFGS, a low memory version of BFGS. Using these optimizers we fit the function y = sinc(10x) using a neural network with a few parameters. This function has a variable amplitude and a constant frequency. We observe that the higher amplitude components of the function are fitted first and the Adam, BFGS and LBFGS struggle to fit the lower amplitude components of the function. We also solve the Burgers equation using a physics informed neural network(PINN) with the BFGS and LM optimizers. For our example problems with a small to medium number of weights, we find that the LM algorithm is able to rapidly converge to machine precision offering significant benefits over other optimizers. We further investigated the Adam optimizer with a range of models and found that Adam optimiser requires much deeper models with large numbers of hidden units containing up to 26x more parameters, in order to achieve a model fit close that achieved by the LM optimizer. The LM optimizer results illustrate that it may be possible build models with far fewer parameters. We have implemented all our methods in Keras and TensorFlow 2.

cs.LG↗

arXiv2022

A Deep Learning Model for Forecasting Global Monthly Mean Sea Surface Temperature Anomalies

Sea surface temperature (SST) variability plays a key role in the global weather and climate system, with phenomena such as El Ni\~{n}o-Southern Oscillation regarded as a major source of interannual climate variability at the global scale. The ability to be able to make long-range forecasts of sea surface temperature anomalies, especially those associated with extreme marine heatwave events, has potentially significant economic and societal benefits. We have developed a deep learning time series prediction model (Unet-LSTM) based on more than 70 years (1950-2021) of ECMWF ERA5 monthly mean sea surface temperature and 2-metre air temperature data. The Unet-LSTM model is able to learn the underlying physics driving the temporal evolution of the 2-dimensional global sea surface temperatures. The model accurately predicts sea surface temperatures over a 24 month period with a root mean square error remaining below 0.75$^\circ$C for all predicted months. We have also investigated the ability of the model to predict sea surface temperature anomalies in the Ni\~{n}o3.4 region, as well as a number of marine heatwave hot spots over the past decade. Model predictions of the Ni\~{n}o3.4 index allow us to capture the strong 2010-11 La Ni\~{n}a, 2009-10 El Nino and the 2015-16 extreme El Ni\~{n}o up to 24 months in advance. It also shows long lead prediction skills for the northeast Pacific marine heatwave, the Blob. However, the prediction of the marine heatwaves in the southeast Indian Ocean, the Ningaloo Ni\~{n}o, shows limited skill. These results indicate the significant potential of data driven methods to yield long-range predictions of sea surface temperature anomalies.

physics.ao-ph↗

arXiv2021

Anthropogenic Mixing of Seasonally Stratified Shelf Seas by Offshore Wind Farm Infrastructure

The offshore wind energy sector has rapidly expanded over the past two decades, providing a renewable energy solution for coastal nations. Sector development has been led in Europe, but is growing globally. Most developments to date have been in well-mixed, i.e. unstratified, shallow-waters near to shore. Sector growth is, for the first time, pushing developments to deep water, into a brand new environment: seasonally stratified shelf seas. Seasonally stratified shelf seas, where water density varies with depth, have a disproportionately key role in primary production, marine ecosystem and biochemically cycles. Infrastructure will directly mix stratified shelf seas. The magnitude of this mixing, additional to natural background processes, has yet to be fully quantified. If large enough it may erode shelf sea stratification. Therefore, offshore wind growth may destabilize and fundamentally change shelf sea systems. However, enhanced mixing may also positively impact some marine ecosystems. This paper sets the scene for sector development into this new environment, reviews the potential physical and environmental benefits and impacts of large scale industrialization of seasonally stratified shelf seas and identifies areas where research is required to best utilise, manage and mitigate environmental change.

physics.ao-ph↗

arXiv2021

Exploiting the Power of Levenberg-Marquardt Optimizer with Anomaly Detection in Time Series

The Levenberg-Marquardt (LM) optimization algorithm has been widely used for solving machine learning problems. Literature reviews have shown that the LM can be very powerful and effective on moderate function approximation problems when the number of weights in the network is not more than a couple of hundred. In contrast, the LM does not seem to perform as well when dealing with pattern recognition or classification problems, and inefficient when networks become large (e.g. with more than 500 weights). In this paper, we exploit the true power of LM algorithm using some real world aircraft datasets. On these datasets most other commonly used optimizers are unable to detect the anomalies caused by the changing conditions of the aircraft engine. The challenging nature of the datasets are the abrupt changes in the time series data. We find that the LM optimizer has a much better ability to approximate abrupt changes and detect anomalies than other optimizers. We compare the performance, in addressing this anomaly/change detection problem, of the LM and several other optimizers. We assess the relative performance based on a range of measures including network complexity (i.e. number of weights), fitting accuracy, over fitting, training time, use of GPUs and memory requirement etc. We also discuss the issue of robust LM implementation in MATLAB and Tensorflow for promoting more popular usage of the LM algorithm and potential use of LM optimizer for large-scale problems.

cs.LG↗

arXiv2018

Expected Optimal Time for the NMR Implementation of Shor's Algorithm for Factorising 15

In this paper, we briefly discuss the methodology for simulating a quantum computer which performs Shor's algorithm on a 7-qubit system to factorise 15. Using this simulation and the overlooked quantum brachistochrone method, we devised a Monte Carlo algorithm to calculate the expected time a theoretical quantum computer could perform this calculation under the same energy conditions as current working quantum computers. We found that, experimentally, a nuclear magnetic resonance quantum computer would take $1.59 \pm 0.04$ s to perform our simulated computation, whereas the expected optimal time under the same energy conditions is $0.955 \pm 0.004$ ms. Moreover, we found that the expected time is inversely proportional to the energy variance of our qubit states (as expected). Finally, we propose this theoretical method for analysing the time-efficiency of future quantum computing experiments.

quant-ph↗

arXiv2013

Chaos in Topological Spaces

We give a definition of chaos for a continuous self-map of a general topological space. This definition coincides with the Devanney definition for chaos when the topological space happens to be a metric space. We show that in a uniform Hausdorff space, there is a meaningful definition of sensitive dependence on initial conditions, and prove that if a map is chaotic on a such a space, then it necessarily has sensitive dependence on initial conditions. The proof is interesting in that it explains very clearly what causes a chaotic process to have sensitive dependence. Finally, we construct a chaotic map on a non-metrizable topological space.

math.DS↗