http://bura.brunel.ac.uk/handle/2438/8625 2026-07-03T19:32:12Z http://bura.brunel.ac.uk/handle/2438/33555 Title: An interpretable convolutional neural network framework for fluid dynamics Authors: Agyei-Baah, K; Rizwanur Rahman, M; Smith, E Abstract: Modelling fluid dynamics with machine learning (ML) has advanced rapidly, yet most data driven approaches remain opaque because they rely on complex architectures to capture nonlinear flow behaviour. This lack of interpretability limits their reliability and hinders understanding of when and why they succeed or fail. To address this, we present a transparent approach that provides insights into how data-driven fluids dynamics and machine learning (ML) work. This is achieved by training a convolutional neural network (CNN), on data from a simple laminar fluid flow, to behave as an operator that exactly matches the finite-difference numerics, providing a direct link between well-established theory and this new world of ML models. Importantly, the model demonstrates strong generalisation capability by reproducing the dynamics for a wide range of distinct and unseen flow conditions within the same flow category. The CNN learns the forward Euler three-point stencil weights, capturing physical principles such as consistency and symmetry despite having only three tuneable weights. This interpretable ML model goes beyond pure numerical training (numCNN), the approach is shown to work when trained on analytical (anCNN) and even molecular dynamics (mdCNN) data. In some cases, the physics is not captured, and thanks to the simple and interpretable form, these CNNs provide insight into the limits, pitfalls and best practice of data-driven fluid models. Because the approach is based on finite-difference operators, it naturally extends to many structured-grid computational fluid dynamics (CFD) problems, including turbulent, multiphase and multiscale flows as well as systems beyond the continuum such as molecular dynamics (MD). To support reproducibility and accelerate adoption, all simulation code, training pipelines, pretrained models, and processed datasets are available open source on GitHub under kwamea-b/CNN-numerical-schemes. Description: Data Availability: All simulation code, training pipelines, pretrained models, and processed datasets as a cohesive software package are made available on GitHub at https://github.com/kwamea-b/CNN_ numerical_schemes and will be uploaded to a persistent data server with a permanent DOI. 2026-06-22T00:00:00Z http://bura.brunel.ac.uk/handle/2438/33551 Title: Real‐World Deployment of a Dynamic Selective LASER Weeding System Using Multispectral Imagery Authors: Wane, S; Wang, M; Butler, M; Cheein, FA Abstract: The use of chemical treatments for weed control is increasingly challenged by weed resistance, regulatory restrictions on chemicals and the risk of soil and water contamination that can pose health hazards. Chemical weed treatments are unsustainable, prompting exploration of alternative methods such as boiling water, electrocution and directed fire. However, these approaches are limited: water-based treatments require a reliable water supply in the field, and electric or fire-based methods pose additional environmental risks. This work proposes a targeted light amplified stimulation of emission by radiation (LASER) treatment and selective spraying system integrated with automatic weed identification. The system, mounted on the rear of a tractor, utilises a bispectral imaging setup to distinguish weeds from crops. Close-to-crop weeds are automatically selected for LASER treatment, whereas a selective sprayer targets other weeds with a glyphosate globule. This integrated system approach is named ‘Hyperweeding’. The results demonstrate successful separation of row crops from weeds, achieving a contamination-free crop with a significant reduction in glyphosate usage, and effectively treating weeds at speeds of 0.1 m • s⁻¹. Description: Data Availability Statement: All relevant data are included within the article. 2026-06-27T00:00:00Z http://bura.brunel.ac.uk/handle/2438/33544 Title: Accurate and robust real-time prediction of September Arctic sea ice Authors: Kondrashov, D; Sudakow, I; Livina, V; Yang, Q Abstract: We describe the real-time forecasting of September 2024 Arctic sea ice extent using a theory-guided machine learning method based on data-adaptive harmonic decomposition and frequency-based nonlinear stochastic modeling, as part of the Sea Ice Outlook. Compared to standard statistical and machine learning models, this method adeptly accounts for non-linear behavior, effectively incorporates memory effects, and handles a wide range of time scale variations, from synoptic (stochastic-like) weather effects to low-frequency (red-noise like) variability, significantly enhancing the accuracy and reliability of sea ice prediction. Description: Data Availability: The data that support the findings of this study are available from the corresponding author upon reasonable request. The NSIDC daily data by region is available at https://nsidc.org/sea-ice-today/sea-ice-tools . 2026-02-03T00:00:00Z http://bura.brunel.ac.uk/handle/2438/33537 Title: Endogenous Sex Hormones (FSH, Oestradiol, Testosterone and SHBG) and Type 2 Diabetes Risk in Postmenopausal Women: A Systematic Review and Meta-Analysis Authors: Liu, CC-Y; König, CS; Ramachandran, S Abstract: Background/Objectives: Menopause is accompanied by substantial changes in endogenous sex hormones that influence metabolic regulation. However, the associations of specific hormones with type 2 diabetes (T2D) risk in postmenopausal women remain inconsistent. This study aimed to quantify the relationships between incident T2D and follicle-stimulating hormone (FSH), oestradiol, testosterone, and sex hormone-binding globulin (SHBG), and to examine cross-sectional differences in hormone concentrations between postmenopausal women with and without T2D. Methods: MEDLINE, Embase and Cochrane CENTRAL were searched from database inception to 21 June 2024. Eligible studies included prospective cohort, nested case–control and case–control designs. Associations with incident T2D were pooled using Hartung–Knapp–Sidik–Jonkman random-effects meta-analysis. Both categorical and continuous estimates were extracted, prioritising maximally adjusted models. Risk of bias was assessed using ROBINS-E and the Newcastle–Ottawa Scale. Results: Sixteen studies (18 articles; 𝑛 = 16,180) were included. Higher SHBG was consistently associated with lower T2D risk in cohort analyses (RR 0.55; 95% CI 0.38–0.72; I² ≈ 0%). Higher FSH was also associated with lower risk (high vs. low: HR 0.55, 95% CI 0.29–0.81), although continuous estimates showed heterogeneity. Higher oestradiol was associated with increased T2D risk (RR 1.61, 95% CI 1.18–2.03; I² ≈ 6%), while testosterone was not significantly associated with incident T2D (RR 1.11, 95% CI 0.73–1.50). Cross-sectional analyses indicated lower SHBG and higher testosterone in women with T2D. Conclusions: Endogenous hormone profiles and SHBG concentrations are associated with T2D in postmenopausal women, with the most consistent evidence for an inverse association between SHBG and incident T2D. Because the available evidence is observational and partly heterogeneous, these findings should be interpreted as associations rather than causal or clinically predictive effects. Standardised measurement, repeated pre-diagnostic sampling and external validation are required before these biomarkers can be considered for routine risk stratification. Description: Data Availability Statement: Data used in this study were extracted from published articles and are available within the manuscript and Supplementary Materials. Extracted datasets and analysis code are available from the corresponding author upon reasonable request.; Supplementary Materials: The following supporting information can be downloaded at: https://www.mdpi.com/article/10.3390/endocrines7020026/s1, Figure S1: Subgroup analysis—forest plot of SHBG level between T2D and non-T2D women; Figure S2: Subgroup analysis—forest plot of testosterone level between T2D and non-T2D women; Figure S3: Forest plot of oestradiol level between T2D and non-T2D women; Figure S4: Sensitivity analysis—forest plot of oestradiol level between T2D and non-T2D women; Search strategies. 2026-06-08T00:00:00Z