Between 2023 and 2024, the Endangered Archaeology in the Middle East and North Africa (EAMENA) project, in collaboration with the Libyan Department of Antiquities (DoA), organised and conducted a series of training workshops and fieldwork campaigns in Libya, funded by the British Council’s Cultural Protection Fund (CPF). The workshops provided training to over 20 members of the DoA in a newly-developed Machine Learning Automated Change Detection (MLACD) tool. This remote sensing method was developed by the Leicester EAMENA team to detect landscape change and aid heritage monitoring efforts. The MLACD method was applied to four case studies in Libya: Lefakat (Cyrenaica), Bani Walid (Tripolitania), the region south of Derna (Cyrenaica) and Jarma (Fazzan). Each of these case studies was followed by a survey campaign by Libyan archaeologists to validate the results of the method, survey the archaeological sites identified, record their condition and assess the disturbances and threats affecting them. This article will provide an overview of the aims and successful outcomes of the EAMENA-CPF training programme, as well as an introduction to the MLACD method and its application to Libyan heritage, providing background and context for the individual case studies, which will be published more fully in separate articles.

Early identification of risk for attention-deficit hyperactivity disorder (ADHD) symptoms can enable more timely interventions and improve long-term outcomes. While previous research has linked various maternal and perinatal factors to ADHD, few studies have examined these predictors collectively in a single comprehensive analysis. This study aimed to assess whether later ADHD symptoms can be predicted from information available at birth, specifically ethnicity, maternal metabolic markers, mental health, and socioeconomic status. It additionally aimed to identify the most influential predictors. Using data from the Born in Bradford (BiB) study, we applied multiple linear regression (LR) and machine learning techniques to predict ADHD symptoms as measured by the Hyperactivity/Inattention subscale of the Strengths and Difficulties Questionnaire (SDQ). A 10-fold cross-validated LR model explained 6.97% of the variance in SDQ scores. In the random forest model, infant male sex and maternal smoking during pregnancy emerged as the top predictors. These findings provide proof of principle for early identification of children at risk of ADHD. Future models may benefit from incorporating additional perinatal data to improve predictive accuracy.

Trustworthy volumetric flow measurements are essential in many applications such as power plant controls or district heating systems. Flow metering under disturbed flow conditions, such as downstream of bends, is a challenge and leads to errors of up to 20 %. In this paper, an algorithm based on a shallow neural network (SNN) is developed, leading to a significant error reduction for strongly disturbed flow profiles. To cover a wide range of disturbances, the training dataset was chosen to consist of three base types of elbow configurations. For 83 % of the test data, the SNN produces a smaller error than the state-of-the-art approach. The average error is reduced from 2.25 % to 0.42 %. For the SNN, an error of less than 1 % can be achieved for downstream distances greater than 10 pipe diameters. The SNN demonstrated robustness to various reductions of the training dataset, as well as to noisy input data. Additionally, simulation data of a realistic pipe system with a significantly different geometry compared with the training data was used for testing. In this strong extrapolation, the mean error of the SNN was always smaller than the state-of-the-art approach and an error of less than 1 % could be achieved for more than 10 pipe diameters downstream of the last disturbance.

In this study, a metasurface (MS) polarization converter combined with a two-port dielectric antenna is constructed and studied. The feeding configuration, which consists of a printed line connected to an aperture, offers built-in filtering capabilities. In addition to converting linear to circular polarization between 2.49 and 3.25 GHz, the suspended MS layer enhances port isolation to less than −20 dB. In addition, the suggested radiator’s |S11| is projected using the Random Forest and XGBoost machine learning (ML) models, which demonstrate satisfactory agreement with simulation data. The antenna effectively functions over 2.33–3.35 GHz, demonstrating that it is a leading contender for sub-6 GHz 5G communication systems. Fabricated measurements support both simulation and ML predictions.

High-resolution particle image velocimetry (PIV) particle-to-velocity analyses using small interrogation areas (IAs) often require substantial processing time. To overcome this limitation, a generative adversarial network (GAN)-based model is proposed to achieve spatio-temporal super-resolution (SR) reconstruction from low-resolution PIV data with large IAs, thereby significantly reducing post-processing time. Time-resolved PIV measurements of plasma-induced vortex flows, covering vortex formation, growth, transition and breakdown stages, are employed to train and evaluate the model with multi-scale vortical structures. By sequentially constructing spatial and temporal datasets, the GAN-based model enables reliable SR reconstruction at different scaling factors. Reconstruction accuracy is systematically assessed using time-averaged, instantaneous and phase-averaged velocity fields. At SR factors of $\times$4 and $\times$8, the reconstructed fields closely match high-resolution references, effectively capturing both fluctuating velocities and small-scale vortical structures. In contrast, $\times$16 reconstructions exhibit diminished accuracy due to the loss of fine-scale information from highly downsampled inputs. For time-averaged fields, high-resolution reconstructions reliably capture plasma jet characteristics at all SR factors. To enhance generalisation, transfer learning is introduced to fine tune the parameters of SR-related layers in the generator, enabling accurate reconstructions under varying vortex dynamics. In addition, the efficiency gains in PIV particle-to-velocity analysis and the fundamental limitations on achievable SR factors imposed by spatio-temporal data correlations are discussed. This study demonstrates that GAN-based spatio-temporal SR models offer a promising approach to accelerate PIV analyses while maintaining high reconstruction fidelity with diverse flow conditions.

Background. Despite the growing recognition of adolescent suicide as a pressing concern, traditional methods for identifying suicide risk often fail to capture the complex interplay of socio-ecological and psychological factors. The advent of machine learning (ML) offers a transformative opportunity to improve suicide risk prediction and intervention strategies. Objective. This study aims to utilize ML techniques to analyze socio-ecological and psychological risk factors to predict suicide ideation, plans and attempts among a nationally representative sample of Ghanaian adolescents. Methods. A cross-sectional survey was conducted with 1,703 adolescents aged 12–18 years across Ghana measuring psychological factors (depression symptoms, anxiety symptoms etc) and socio-ecological factors (bullying, parental support etc) using validated measures. Descriptive statistics were conducted and random forest and logistic regression models were employed for suicide risk prediction, i.e., ‘ideation, plans and attempts’. Model performance was evaluated using accuracy, sensitivity, specificity and feature importance analysis. Results. Psychological factors such as depression symptoms (r = .42, p < .01), anxiety (r = .38, p < .01) and perceived stress (r = .35, p < .01) were the strongest predictors of suicide ideation, plans and attempts, while parental support emerged as a significant protective factor (r = −.34, p < .01). The random forest model demonstrated good predictive performance (accuracy = 78.3%, AUC = 0.81). Gender differences were observed. Conclusions. This study is the first to apply ML techniques to a nationally representative dataset of Ghanaian adolescents for suicide risk prediction, i.e., ‘ideation, plans and attempts’. The findings highlight the potential of ML to provide precise tools for early identification of at-risk individuals.

Transonic buffet presents time-dependent aerodynamic characteristics associated with shock, turbulent boundary layer and their interactions. Despite strong nonlinearities and a large degree of freedom, there exists a dominant dynamic pattern of a buffet cycle, suggesting the low dimensionality of transonic buffet phenomena. This study seeks a low-dimensional representation of transonic airfoil buffet at a high Reynolds number with machine learning. Wall-modelled large-eddy simulations of flow over the OAT15A supercritical airfoil at two Mach numbers, $M_\infty = 0.715$ and 0.730, respectively producing non-buffet and buffet conditions, at a chord-based Reynolds number of ${Re} = 3\times 10^6$ are performed to generate the present datasets. We find that the low-dimensional nature of transonic airfoil buffet can be extracted as a sole three-dimensional latent representation through lift-augmented autoencoder compression. The current low-order representation not only describes the shock movement but also captures the moment when the separation occurs near the trailing edge in a low-order manner. We further show that it is possible to perform sensor-based reconstruction through the present low-dimensional expression while identifying the sensitivity with respect to aerodynamic responses. The present model trained at ${Re} = 3\times 10^6$ is lastly evaluated at the level of a real aircraft operation of ${Re} = 3\times 10^7$, exhibiting that the phase dynamics of lift is reasonably estimated from sparse sensors. The current study may provide a foundation towards data-driven real-time analysis of transonic buffet conditions under aircraft operation.

With ambitious action required to achieve global climate mitigation goals, climate change has become increasingly salient in the political arena. This article presents a dataset of climate change salience in 1,792 political manifestos of 620 political parties across different party families in forty-five OECD, European, and South American countries from 1990 to 2022. Importantly, our measure uniquely isolates climate change salience, avoiding the conflation with general environmental and sustainability content found in other work. Exploiting recent advances in supervised machine learning, we developed the dataset by fine-tuning a pre-trained multilingual transformer with human coding, employing a resource-efficient and replicable pipeline for multilingual text classification that can serve as a template for similar tasks. The dataset unlocks new avenues of research on the political discourse of climate change, on the role of parties in climate policy making, and on the political economy of climate change. We make the model and the dataset available to the research community.

The simulation of turbulent flow requires many degrees of freedom to resolve all the relevant time and length scales. However, due to the dissipative nature of the Navier–Stokes equations, the long-term dynamics is expected to lie on a finite-dimensional invariant manifold with fewer degrees of freedom. In this study, we build low-dimensional data-driven models of pressure-driven flow through a circular pipe. We impose the ‘shift-and-reflect’ symmetry to study the system in a minimal computational cell (e.g. the smallest domain size that sustains turbulence) at a Reynolds number of 2500. We build these models by using autoencoders to parametrise the manifold coordinates and neural ordinary differential equation to describe their time evolution. Direct numerical simulations (DNSs) typically require of the order of $\mathcal{O}(10^5)$ degrees of freedom, while our data-driven framework enables the construction of models with fewer than 20 degrees of freedom. Remarkably, these reduced-order models effectively capture crucial features of the flow, including the streak breakdown. In short-time tracking, these models accurately track the true trajectory for one Lyapunov time, as well as the leading Lyapunov exponent, while at long-times, they successfully capture key aspects of the dynamics such as Reynolds stresses and energy balance. The model can quantitatively capture key characteristics of the flow, including the streak breakdown and regeneration cycle. Additionally, we report new exact coherent states found in the DNS with the aid of these low-dimensional models. This approach leads to the discovery of seventeen previously unknown solutions within the turbulent pipe flow system, notably featuring relative periodic orbits characterised by the longest reported periods for such flow conditions.

With the growing amount of historical infrastructure data available to engineers, data-driven techniques have been increasingly employed to forecast infrastructure performance. In addition to algorithm selection, data preprocessing strategies for machine learning implementations plays an equally important role in ensuring accuracy and reliability. The present study focuses on pavement infrastructure and identifies four categories of strategies to preprocess data for training machine-learning-based forecasting models. The Long-Term Pavement Performance (LTPP) dataset is employed to benchmark these categories. Employing random forest as the machine learning algorithm, the comparative study examines the impact of data preprocessing strategies, the volume of historical data, and forecast horizon on the accuracy and reliability of performance forecasts. The strengths and limitations of each implementation strategy are summarized. Multiple pavement performance indicators are also analysed to assess the generalizability of the findings. Based on the results, several findings and recommendations are provided for short-to medium-term infrastructure management and decision-making: (i) in data-scarce scenarios, strategies that incorporate both explanatory variables and historical performance data provides better accuracy and reliability, (ii) to achieve accurate forecasts, the volume of historical data should at least span a time duration comparable to the intended forecast horizon, and (iii) for International Roughness Index and transverse crack length, a forecast horizon up to 5 years is generally achievable, but forecasts beyond a three-year horizon are not recommended for longitudinal crack length. These quantitative guidelines ultimately support more effective and reliable application of data-driven techniques in infrastructure performance forecasting.