Ethnicity and race are vital for understanding representation, yet individual-level data are often unavailable. Recent methodological advances have allowed researchers to impute racial and ethnic classifications based on publicly available information, but predictions vary in their accuracy and can introduce statistical biases in downstream analyses. We provide an overview of common estimation methods, including Bayesian approaches and machine learning techniques that use names or images as inputs. We propose and test a hybrid approach that combines surname-based Bayesian estimation with the use of publicly available images in a convolutional neural network. We find that the proposed approach not only reduces statistical bias in downstream analyses but also improves accuracy in a sample of over 16,000 local elected officials. We conclude with a discussion of caveats and describe settings where the hybrid approach is especially suitable.

In recent years, integrating physical constraints within deep neural networks has emerged as an effective approach for expediting direct numerical simulations in two-phase flow. This paper introduces physics-informed neural networks (PINNs) that utilise the phase-field method to model three-dimensional two-phase flows. We present a fully connected neural network architecture with residual blocks and spatial parallel training using the overlapping domain decomposition method across multiple graphics processing units to enhance the accuracy and computational efficiency of PINNs for the phase-field method (PF-PINNs). The proposed PINNs framework is applied to a bubble rising scenario in a three-dimensional infinite water tank to quantitatively assess the performance of PF-PINNs. Furthermore, the computational cost and parallel efficiency of the proposed method was evaluated, demonstrating its potential for widespread application in complex training environments.

A deep reinforcement learning method for training a jellyfish-like swimmer to effectively track a moving target in a two-dimensional flow was developed. This swimmer is a flexible object equipped with a muscle model based on torsional springs. We employed a deep Q-network (DQN) that takes the swimmer’s geometry and dynamic parameters as inputs, and outputs actions that are the forces applied to the swimmer. In particular, an action regulation was introduced to mitigate the interference from complex fluid–structure interactions. The goal of these actions is to navigate the swimmer to a target point in the shortest possible time. In the DQN training, the data on the swimmer’s motions were obtained from simulations using the immersed boundary method. During tracking a moving target, there is an inherent delay between the application of forces and the corresponding response of the swimmer’s body due to hydrodynamic interactions between the shedding vortices and the swimmer’s own locomotion. Our tests demonstrate that the swimmer, with the DQN agent and action regulation, is able to dynamically adjust its course based on its instantaneous state. This work extends the application scope of machine learning in controlling flexible objects within fluid environments.

Understanding the properties of lower-carbon concrete products is essential for their effective utilization. Insufficient empirical test data hinders practical adoption of these emerging products, and a lack of training data limits the effectiveness of current machine learning approaches for property prediction. This work employs a random forest machine learning model combined with a just-in-time approach, utilizing newly available data throughout the concrete lifecycle to enhance predictions of 28 and 56 day concrete strength. The machine learning hyperparameters and inputs are optimized through a novel unified metric that combines prediction accuracy and uncertainty estimates through the coefficient of determination and the distribution of uncertainty quality. This study concludes that optimizing solely for accuracy selects a different model than optimizing with the proposed unified accuracy and uncertainty metric. Experimental validation compares the 56-day strength of two previously unseen concrete mixes to the machine learning predictions. Even with the sparse dataset, predictions of 56-day strength for the two mixes were experimentally validated to within 90% confidence interval when using slump as an input and further improved by using 28-day strength.

Microwaves (MWs) have emerged as a promising sensing technology to complement optical methods for monitoring floating plastic litter. This study uses machine learning (ML) to identify optimal MW frequencies for detecting floating macroplastics (>5 cm) across S, C, and X-bands. Data were obtained from dedicated wideband backscattering radio measurements conducted in a controlled indoor scenario that mimics deep-sea conditions. The paper presents new strategies to directly analyze the frequency domain signals using ML algorithms, instead of generating an image from those signals and analyzing the image. We propose two ML workflows, one unsupervised, to characterize the difference in feature importance across the measured MW spectrum, and the other supervised, based on multilayer perceptron, to study the detection accuracy in unseen data. For the tested conditions, the backscatter response of the plastic litter is optimal at X-band frequencies, achieving accuracies up to 90% and 80% for lower and higher water wave heights, respectively. Multiclass classification is also investigated to distinguish between different types of plastic targets. ML results are interpreted in terms of the physical phenomena obtained through numerical analysis, and quantified through an energy-based metric.

Past research alerts to the increasingly unpleasant climate surrounding public debate on social media. Female politicians, in particular, are reporting serious attacks targeted at them. Yet, research offers inconclusive insights regarding the gender gap in online incivility. This paper aims to address this gap by comparing politicians with varying levels of prominence and public status in different institutional contexts. Using a machine learning approach for analyzing over 23 million tweets addressed to politicians in Germany, Spain, the United Kingdom, and the United States, we find little consistent evidence of a gender gap in the proportion of incivility. However, more prominent politicians are considerably and consistently more likely than others to receive uncivil attacks. While prominence influences US male and female politicians’ probability to receive uncivil tweets the same way, women in our European sample receive incivility regardless of their status. Most importantly, the incivility varies in quality and across contexts, with women, especially in more plurality contexts, receiving more identity-based attacks than other politicians.

This study provides a comprehensive analysis of the impact of helideck surface conditions on the safe operation of helicopter landing and take-off platforms on offshore drilling vessels. Over time, the deterioration of helideck surface coatings necessitates periodic friction coefficient testing every two years in compliance with international standards. Surface coatings that fail to meet the required thresholds are replaced, and the performance of the renewed surface is reassessed using the Helideck Micro GripTester (HMGT), in accordance with U.K. Safety Regulation Group CAP 437 (2023) standards for offshore helicopter landing areas. The findings indicate that the renewed helideck surface coatings lead to a significant increase in the coefficient of friction, thereby enhancing the stability of helicopters upon landing and while on deck. Independent sample t-test and correlation analyses confirmed statistically significant differences between the old and new surface conditions, demonstrating the positive impact of surface improvements on coefficient of friction and, therefore, operational safety. Furthermore, machine learning techniques were employed to model and analyse the non-linear relationships between surface conditions and flow number. The model results demonstrate that variations in helideck surface coatings directly influence helicopter performance and operational safety. These findings underscore the critical importance of regular resurfacing and friction testing in ensuring the safety and reliability of offshore helicopter operations.

Recent advancements in data science and artificial intelligence have significantly transformed plant sciences, particularly through the integration of image recognition and deep learning technologies. These innovations have profoundly impacted various aspects of plant research, including species identification, disease detection, cellular signaling analysis, and growth monitoring. This review summarizes the latest computational tools and methodologies used in these areas. We emphasize the importance of data acquisition and preprocessing, discussing techniques such as high-resolution imaging and unmanned aerial vehicle (UAV) photography, along with image enhancement methods like cropping and scaling. Additionally, we review feature extraction techniques like colour histograms and texture analysis, which are essential for plant identification and health assessment. Finally, we discuss emerging trends, challenges, and future directions, offering insights into the applications of these technologies in advancing plant science research and practical implementations.

Turbulence closures are essential for predictive fluid flow simulations in both natural and engineering systems. While machine learning offers promising avenues, existing data-driven turbulence models often fail to generalise beyond their training datasets. This study identifies the root cause of this limitation as the conflation of generalisable flow physics and dataset-specific behaviours. We address this challenge using symbolic regression, which yields interpretable, white-box expressions. By decomposing the learned corrections into inner-layer, outer-layer and pressure-gradient components, we isolate universal physics from flow-specific features. The model is trained progressively using high-fidelity datasets for plane channel flows, zero-pressure-gradient turbulent boundary layers (ZPGTBLs), and adverse pressure-gradient turbulent boundary layers (PGTBLs). For example, direct application of a model trained on channel flow data to ZPGTBLs results in incorrect skin friction predictions. However, when only the generalisable inner-layer component is retained and combined with an outer-layer correction specific to ZPGTBLs, predictions improve significantly. Similarly, a pressure-gradient correction derived from PGTBL data enables accurate modelling of aerofoil flows with both favourable and adverse pressure gradients. The resulting symbolic corrections are compact, interpretable, and generalise across configurations – including unseen geometries such as aerofoils and Reynolds numbers outside the training set. The models outperform baseline Reynolds-averaged Navier–Stokes closures (e.g. the Spalart–Allmaras and shear stress transport models) in both a priori and a posteriori tests. These results demonstrate that explicit identification and retention of generalisable components is key to overcoming the generalisation challenge in machine-learned turbulence closures.

This study explores the potential of applying machine learning (ML) methods to identify and predict areas at risk of food insufficiency using a parsimonious set of publicly available data sources. We combine household survey data that captures monthly reported food insufficiency with remotely sensed measures of factors influencing crop production and maize price observations at the census enumeration area (EA) in Malawi. We consider three machine-learning models of different levels of complexity suitable for tabular data (TabNet, random forests, and LASSO) and classical logistic regression and examine their performance against the historical occurrence of food insufficiency. We find that the models achieve similar accuracy levels with differential performance in terms of precision and recall. The Shapley additive explanation decomposition applied to the models reveals that price information is the leading contributor to model fits. A possible explanation for the accuracy of simple predictors is the high spatiotemporal path dependency in our dataset, as the same areas of the country are repeatedly affected by food crises. Recurrent events suggest that immediate and longer-term responses to food crises, rather than predicting them, may be the bigger challenge, particularly in low-resource settings. Nonetheless, ML methods could be useful in filling important data gaps in food crises prediction, if followed by measures to strengthen food systems affected by climate change. Hence, we discuss the tradeoffs in training these models and their use by policymakers and practitioners.

Monitoring wildlife populations in vast, remote landscapes poses significant challenges for conservation and management, particularly when studying elusive species that range across inaccessible terrain. Traditional survey methods often prove impractical or insufficient in such environments, necessitating innovative technological solutions. This study evaluates the effectiveness of deep learning for automated Bactrian camel detection in drone imagery across the complex desert terrain of the Gobi Desert of Mongolia. Using YOLOv8 and a dataset of 1479 high-resolution drone-captured images of Bactrian camels, we developed and validated an automated detection system. Our model demonstrated strong detection performance with high precision and recall values across different environmental conditions. Scale-aware analysis revealed distinct performance patterns between medium- and small-scale detections, informing optimal drone flight parameters. The system maintained consistent processing efficiency across various batch sizes while preserving detection quality. These findings advance conservation monitoring capabilities for Bactrian camels and other wildlife in remote ecosystems, providing wildlife managers with an efficient tool to track population dynamics and inform conservation strategies in expansive, difficult-to-access habitats.

Resilient enterprises thrive under adverse conditions given their preparedness for crises. This study proposes that executives’ vigilant managerial cognition is essential for enhancing enterprise resilience. To measure this cognition, the study developed a textual index using machine learning methods and analyzed a sample of Chinese enterprises to assess the impact of executives’ vigilant managerial cognition on enterprise resilience. The findings indicate that this cognition is positively related to enterprise resilience, where the relationship is stronger in enterprises with robust internal controls. The primary contribution of this study is the conceptualization of vigilant managerial cognition and its established positive relationship with enterprise resilience. Furthermore, by introducing a novel quantitative measure of managerial cognition through textual analysis and machine learning, the study paves the way for future research on managerial cognition within firms.

Plastic chemicals are numerous and ubiquitous in modern life and pose significant risks to human health. Observational epidemiological studies have been instrumental in identifying consistent and statistically significant associations between exposure to certain chemicals and adverse health outcomes. However, these studies often fail to establish causality due to the complexity of real-world chemical mixtures, confounding factors, reverse causation, and study designs that lack measures reflecting underlying genetic and cellular mechanisms indicating causal pathways to harm. Addressing these limitations requires moving beyond traditional ‘black-box’ epidemiology, which mainly focuses on the strength of associations. We propose adopting hybrid epidemiological methodologies that incorporate genetic susceptibility and molecular mechanisms to uncover biological pathways, combined with machine learning and statistical analysis of chemical mixtures, to strengthen the causal evidence linking exposure to harm. By integrating observational multi-omics data with experimental and mechanistic models, hybrid epidemiology offers a transformative path to improve causal evidence and public health interventions. In addition, machine learning and statistical methods provide a more nuanced understanding of the health effects of exposures to plastic chemical mixtures, facilitating the identification of interactions within chemical mixtures and the influence of biological pathways. This paradigm shift is critical addressing the complex challenges of plastic exposure and protecting human health.

Persistent malnutrition is associated with poor clinical outcomes in cancer. However, assessing its reversibility can be challenging. The present study aimed to utilise machine learning (ML) to predict reversible malnutrition (RM) in patients with cancer. A multicentre cohort study including hospitalised oncology patients. Malnutrition was diagnosed using an international consensus. RM was defined as a positive diagnosis of malnutrition upon patient admission which turned negative one month later. Time-series data on body weight and skeletal muscle were modelled using a long short-term memory architecture to predict RM. The model was named as WAL-net, and its performance, explainability, clinical relevance and generalisability were evaluated. We investigated 4254 patients with cancer-associated malnutrition (discovery set = 2977, test set = 1277). There were 2783 men and 1471 women (median age = 61 years). RM was identified in 754 (17·7 %) patients. RM/non-RM groups showed distinct patterns of weight and muscle dynamics, and RM was negatively correlated to the progressive stages of cancer cachexia (r = –0·340, P < 0·001). WAL-net was the state-of-the-art model among all ML algorithms evaluated, demonstrating favourable performance to predict RM in the test set (AUC = 0·924, 95 % CI = 0·904, 0·944) and an external validation set (n 798, AUC = 0·909, 95 % CI = 0·876, 0·943). Model-predicted RM using baseline information was associated with lower future risks of underweight, sarcopenia, performance status decline and progression of malnutrition (all P < 0·05). This study presents an explainable deep learning model, the WAL-net, for early identification of RM in patients with cancer. These findings might help the management of cancer-associated malnutrition to optimise patient outcomes in multidisciplinary cancer care.

Rotorcraft engines are highly complex, nonlinear thermodynamic systems operating under varying environmental and flight conditions. Simulating their dynamics is crucial for design, fault diagnostics and deterioration control, requiring robust control systems to estimate performance throughout the flight envelope. Numerical simulations provide accurate assessments in both steady and unsteady scenarios through physics-based and mathematical models, although their development is challenging due to the engine’s complex physics and strong dependencies on environmental conditions. In this context, data-driven machine-learning techniques have gained significant interest for their ability to capture nonlinear dynamics and enable online performance estimation with competitive accuracy. This work explores different neural network architectures to model the turboshaft engine of Leonardo’s AW189P4 prototype, aiming to predict engine torque. The models are trained on a large database of real flight tests, covering a variety of operational manoeuvers under different conditions, thus offering a comprehensive performance representation. Additionally, sparse identification of nonlinear dynamics (SINDy) is applied to derive a low-dimensional model from the available data, capturing the relationship between fuel flow and engine torque. The resulting model highlights SINDy’s ability to recover underlying engine physics and suggests its potential for further investigations into engine complexity. The paper details the development and prediction results of each model, demonstrating that data-driven approaches can exploit a broader range of parameters compared to standard transfer function-based methods, enabling the use of trained schemes to simulate nonlinear effects in different engines and helicopters.

Contactless manipulation of small objects is essential for biomedical and chemical applications, such as cell analysis, assisted fertilisation and precision chemistry. Established methods, including optical, acoustic and magnetic tweezers, are now complemented by flow control techniques that use flow-induced motion to enable precise and versatile manipulation. However, trapping multiple particles in fluid remains a challenge. This study introduces a novel control algorithm capable of steering multiple particles in flow. The system uses rotating disks to generate flow fields that transport particles to precise locations. Disk rotations are governed by a feedback control policy based on the optimising a discrete loss framework, which combines fluid dynamics equations with path objectives into a single loss function. Our experiments, conducted in both simulations and with the physical device, demonstrate the capability of the approach to transport two beads simultaneously to predefined locations, advancing robust contactless particle manipulation for biomedical applications.