During the coronavirus pandemic in the United Kingdom, media outlets shifted their focus from divisive political issues to more neutral topics like lifestyle, sports, and entertainment. This study explores how this change in media content relates to partisan divides in satisfaction with democracy. Using data from a representative survey of 201,144 individuals, we linked respondents’ perceptions of democratic performance to their daily media exposure. We did so by analysing 1.5 million tweets from British newspapers using a topic modelling algorithm to identify shifts in topic salience and sentiment using sentiment analysis. Our findings reveal a decline in partisan media exposure during the pandemic, associated with increased satisfaction with democracy at both individual and collective levels, and a narrowing of cross-party divides. These results contribute to discussions on affective polarization, the winner-loser gap in democratic evaluation, and media framing effects, highlighting the potential influence of depoliticized news coverage on democratic attitudes.

With the increasing volume of scientific literature, there is a need to streamline the screening process for titles and abstracts in systematic reviews, reduce the workload for reviewers, and minimize errors. This study validated artificial intelligence (AI) tools, specifically Llama 3 70B via Groq’s application programming interface (API) and ChatGPT-4o mini via OpenAI’s API, for automating this process in biomedical research. It compared these AI tools with human reviewers using 1,081 articles after duplicate removal. Each AI model was tested in three configurations to assess sensitivity, specificity, predictive values, and likelihood ratios. The Llama 3 model’s LLA_2 configuration achieved 77.5% sensitivity and 91.4% specificity, with 90.2% accuracy, a positive predictive value (PPV) of 44.3%, and a negative predictive value (NPV) of 97.9%. The ChatGPT-4o mini model’s CHAT_2 configuration showed 56.2% sensitivity, 95.1% specificity, 92.0% accuracy, a PPV of 50.6%, and an NPV of 96.1%. Both models demonstrated strong specificity, with CHAT_2 having higher overall accuracy. Despite these promising results, manual validation remains necessary to address false positives and negatives, ensuring that no important studies are overlooked. This study suggests that AI can significantly enhance efficiency and accuracy in systematic reviews, potentially revolutionizing not only biomedical research but also other fields requiring extensive literature reviews.

The 2018/2019 trade conflict between the United States and China impacted a broad array of agricultural products, including soybeans. Previous trade studies using gravity models fail to account for trends and complex seasonal patterns observed in the data. This study uses a machine learning (ML) approach to estimate losses in soybean export value and volume from the trade war. We find that models using ML techniques outperform traditional models and estimate losses in the value of soybean exports of $10.16 billion/year. The ML models fit the complex export trade data series well, highlighting the importance of utilizing improved modeling approaches.

The present study explores the value of machine learning techniques in the classification of communication content in experiments. Previously human-coded datasets are used to both train and test algorithm-generated models that relate word counts to categories. For various games, the computer models of the classification are able to match out-of-sample the human classification to a considerable extent. The analysis raises hope that the substantial effort going into such studies can be reduced by using computer algorithms for classification. This would enable a quick and replicable analysis of large-scale datasets at reasonable costs and widen the applicability of such approaches. The paper gives an easily accessible technical introduction into the computational method.

Elastoinertial turbulence (EIT) is a chaotic state that emerges in the flows of dilute polymer solutions. Direct numerical simulation (DNS) of EIT is highly computationally expensive due to the need to resolve the multiscale nature of the system. While DNS of two-dimensional (2-D) EIT typically requires $O(10^6)$ degrees of freedom, we demonstrate here that a data-driven modelling framework allows for the construction of an accurate model with 50 degrees of freedom. We achieve a low-dimensional representation of the full state by first applying a viscoelastic variant of proper orthogonal decomposition to DNS results, and then using an autoencoder. The dynamics of this low-dimensional representation is learned using the neural ordinary differential equation (NODE) method, which approximates the vector field for the reduced dynamics as a neural network. The resulting low-dimensional data-driven model effectively captures short-time dynamics over the span of one correlation time, as well as long-time dynamics, particularly the self-similar, nested travelling wave structure of 2-D EIT in the parameter range considered.

In today’s world, smart algorithms—artificial intelligence (AI) and other intelligent systems—are pivotal for promoting the development agenda. They offer novel support for decision-making across policy planning domains, such as analysing poverty alleviation funds and predicting mortality rates. To comprehensively assess their efficacy and implications in policy formulation, this paper conducts a systematic review of 207 publications. The analysis underscores their integration within and across stages of the policy planning cycle: problem diagnosis and goal articulation; resource and constraint identification; design of alternative solutions; outcome projection; and evaluation. However, disparities exist in smart algorithm applications across stages, economic development levels, and Sustainable Development Goals (SDGs). While these algorithms predominantly focus on resource identification (29%) and contribute significantly to designing alternatives—such as long-term national energy policies—and projecting outcomes, including predicting multi-scenario land-use ecological security strategies, their application in evaluation remains limited (10%). Additionally, low-income nations have yet to fully harness AI’s potential, while upper-middle-income countries effectively leverage it. Notably, smart algorithm applications for SDGs also exhibit unevenness, with more emphasis on SDG 11 than on SDG 5 and SDG 17. Our study identifies literature gaps. Firstly, despite theoretical shifts, a disparity persists between physical and socioeconomic/environmental planning applications. Secondly, there is limited attention to policy-making in development initiatives, which is critical for improving lives. Future research should prioritise developing adaptive planning systems using emerging powerful algorithms to address uncertainty and complex environments. Ensuring algorithmic transparency, human-centered approaches, and responsible AI are crucial for AI accountability, trust, and credibility.

There is a growing focus on understanding the complexity of dietary patterns and how they relate to health and other factors. Approaches that have not traditionally been applied to characterize dietary patterns, such as latent class analysis and machine learning algorithms, may offer opportunities to characterize dietary patterns in greater depth than previously considered. However, there has not been a formal examination of how this wide range of approaches has been applied to characterize dietary patterns. This scoping review synthesized literature from 2005-2022 applying methods not traditionally used to characterize dietary patterns, referred to as novel methods. MEDLINE, CINAHL, and Scopus were searched using keywords including latent class analysis, machine learning, and least absolute shrinkage and selection operator. Of 5274 records identified, 24 met the inclusion criteria. Twelve of 24 articles were published since 2020. Studies were conducted across 17 countries. Nine studies used approaches with applications in machine learning, such as classification models, neural networks, and probabilistic graphical models, to identify dietary patterns. The remaining studies applied methods such as latent class analysis, mutual information, and treelet transform. Fourteen studies assessed associations between dietary patterns characterized using novel methods and health outcomes, including cancer, cardiovascular disease, and asthma. There was wide variation in the methods applied to characterize dietary patterns and in how these methods were described. The extension of reporting guidelines and quality appraisal tools relevant to nutrition research to consider specific features of novel methods may facilitate consistent reporting and enable synthesis to inform policies and programs.

Systematic reviews play important roles but manual efforts can be time-consuming given a growing literature. There is a need to use and evaluate automated strategies to accelerate systematic reviews. Here, we comprehensively tested machine learning (ML) models from classical and deep learning model families. We also assessed the performance of prompt engineering via few-shot learning of GPT-3.5 and GPT-4 large language models (LLMs). We further attempted to understand when ML models can help automate screening. These ML models were applied to actual datasets of systematic reviews in education. Results showed that the performance of classical and deep ML models varied widely across datasets, ranging from 1.2 to 75.6% of work saved at 95% recall. LLM prompt engineering produced similarly wide performance variation. We searched for various indicators of whether and how ML screening can help. We discovered that the separability of clusters of relevant versus irrelevant articles in high-dimensional embedding space can strongly predict whether ML screening can help (overall R = 0.81). This simple and generalizable heuristic applied well across datasets and different ML model families. In conclusion, ML screening performance varies tremendously, but researchers and software developers can consider using our cluster separability heuristic in various ways in an ML-assisted screening pipeline.

We analysed the performance of convolutional autoencoders in generating reduced-order representations of the temperature field of two-dimensional Rayleigh–Bénard flows at $\textit{Pr} =1$ and Rayleigh numbers extending from $10^6$ to $10^8$, capturing the range where the flow transitions to turbulence. We present a way of estimating the minimum number of dimensions needed by the autoencoders to capture all the relevant physical scales of the data that is more apt for highly multiscale flows than previous criteria applied to lower-dimensional systems. We compare our architecture with two regularized variants as well as with linear methods, and find that manually fixing the dimension of the latent space produces the best results. We show how the estimated minimum dimension presents a sharp increase around $Ra\sim 10^7$, when the flow starts to transition to turbulence. Furthermore, we show how this dimension does not follow the same scaling as the physically relevant scales, such as the dissipation length scale and the thermal boundary layer.

Ambient air pollution remains a global challenge, with adverse impacts on health and the environment. Addressing air pollution requires reliable data on pollutant concentrations, which form the foundation for interventions aimed at improving air quality. However, in many regions, including the United Kingdom, air pollution monitoring networks are characterized by spatial sparsity, heterogeneous placement, and frequent temporal data gaps, often due to issues such as power outages. We introduce a scalable data-driven supervised machine learning model framework designed to address temporal and spatial data gaps by filling missing measurements within the United Kingdom. The machine learning framework used is LightGBM, a gradient boosting algorithm based on decision trees, for efficient and scalable modeling. This approach provides a comprehensive dataset for England throughout 2018 at a 1 km2 hourly resolution. Leveraging machine learning techniques and real-world data from the sparsely distributed monitoring stations, we generate 355,827 synthetic monitoring stations across the study area. Validation was conducted to assess the model’s performance in forecasting, estimating missing locations, and capturing peak concentrations. The resulting dataset is of particular interest to a diverse range of stakeholders engaged in downstream assessments supported by outdoor air pollution concentration data for nitrogen dioxide (NO2), Ozone (O3), particulate matter with a diameter of 10 μm or less (PM10), particulate matter with a diameter of 2.5 μm or less PM2.5, and sulphur dioxide (SO2), at a higher resolution than was previously possible.

Forests play a crucial role in the Earth’s system processes and provide a suite of social and economic ecosystem services, but are significantly impacted by human activities, leading to a pronounced disruption of the equilibrium within ecosystems. Advancing forest monitoring worldwide offers advantages in mitigating human impacts and enhancing our comprehension of forest composition, alongside the effects of climate change. While statistical modeling has traditionally found applications in forest biology, recent strides in machine learning and computer vision have reached important milestones using remote sensing data, such as tree species identification, tree crown segmentation, and forest biomass assessments. For this, the significance of open-access data remains essential in enhancing such data-driven algorithms and methodologies. Here, we provide a comprehensive and extensive overview of 86 open-access forest datasets across spatial scales, encompassing inventories, ground-based, aerial-based, satellite-based recordings, and country or world maps. These datasets are grouped in OpenForest, a dynamic catalog open to contributions that strives to reference all available open-access forest datasets. Moreover, in the context of these datasets, we aim to inspire research in machine learning applied to forest biology by establishing connections between contemporary topics, perspectives, and challenges inherent in both domains. We hope to encourage collaborations among scientists, fostering the sharing and exploration of diverse datasets through the application of machine learning methods for large-scale forest monitoring. OpenForest is available at the following url: https://github.com/RolnickLab/OpenForest.

Central banks have increased their official communications. Previous literature measures complexity, clarity, tone and sentiment. Less explored is the use of fact versus emotion in central bank communication. We test a new method for classifying factual versus emotional language, applying a pretrained transfer learning model, fine-tuned with manually coded, task-specific and domain-specific data sets. We find that the large language models outperform traditional models on some occasions; however, the results depend on a number of choices. We therefore caution researchers from depending solely on such models even for tasks that appear similar. Our findings suggest that central bank communications are not only technically but also subjectively difficult to understand.

Novel methods of data collection and analysis can enhance traditional risk management practices that rely on expert engineering judgment and established safety records, specifically when key conditions are met: Analysis is linked to the decisions it is intended to support, standards and competencies remain up to date, and assurance and verification activities are performed. This article elaborates on these conditions. The reason engineers are required to perform calculations is to support decision-making. Since humans are famously weak natural statisticians, rather than ask stakeholders to implicitly assimilate data, and arrive at a decision, we can instead rely on subject matter experts to explicitly define risk management decision problems. The results of engineering calculation can then also communicate which interventions (if any) are considered to be risk-optimal. It is also proposed that the next generation of engineering standards should learn from the success of open source software development in community building. Interacting with open datasets and code can promote engagement, identification (and resolution) of errors, training and ultimately competence. Finally, the profession’s tradition of independent verification should also be applied to the complex models that will increasingly contribute to the safety of the built environment. Model assurance will be required to keep pace with model development to identify suitable use cases as adequately safe. These are considered to be increasingly important components in ensuring that methods of data-centric engineering can be safely and appropriately adopted in industry.

Efficient tools for predicting the drag of rough walls in turbulent flows would have a tremendous impact. However, accurate methods for drag prediction rely on experiments or numerical simulations which are costly and time consuming. Data-driven regression methods have the potential to provide a prediction that is accurate and fast. We assess the performance and limitations of linear regression, kernel methods and neural networks for drag prediction using a database of 1000 homogeneous rough surfaces. Model performance is evaluated using the roughness function obtained at a friction Reynolds number $Re_\tau$ of 500. With two trainable parameters, the kernel method can fully account for nonlinear relations between the roughness function $\Delta U^+$ and surface statistics (roughness height, effective slope, skewness, etc.). In contrast, linear regression cannot account for nonlinear correlations and displays large errors and high uncertainty. Multilayer perceptron and convolutional neural networks demonstrate performance on par with the kernel method but have orders of magnitude more trainable parameters. For the current database size, the networks’ capacity cannot be fully exploited, resulting in reduced generalizability and reliability. Our study provides insight into the appropriateness of different regression models for drag prediction. We also discuss the remaining steps before data-driven methods emerge as useful tools in applications.

With developing technology, the usage areas of aircraft are constantly expanded. In aircraft designed for different missions, it is an important issue to evaluate many design possibilities and make optimum designs by taking into account many parameters that are not directly connected to each other with equal importance. In this context, issues such as safety and performance come to the fore in aircraft designs. One of the critical situations affecting flight safety is the takeoff and landing phases of the aircraft. The speed changes that occur in these stages are an important issue. In this study, takeoff speed was predicted with different machine learning algorithms using takeoff speed data of the Boeing B-737-300 type aircraft. Linear regression, support vector regression, classification and regression trees, random forest regression, Extreme Gradient Boosting algorithms were selected from machine learning algorithms for takeoff speed prediction. Base models were created with these selected algorithms and the takeoff speed was predicted by training the data. Considering the obtained results, feature engineered was applied to minimise the error values of the proposed base models. In models developed by applying feature engineered, error values were reduced and better performance was observed in takeoff speed prediction. Takeoff speed values obtained with the developed models and actual flight speed values are presented comparatively for the first time in the literature. The simulation results emphasise that the developed models can be used as an effective and alternative method for takeoff speed prediction.

Shifting to cycling in urban areas reduces greenhouse gas emissions and improves public health. Access to street-level data on bicycle traffic would assist cities in planning targeted infrastructure improvements to encourage cycling and provide civil society with evidence to advocate for cyclists’ needs. Yet, the data currently available to cities and citizens often only comes from sparsely located counting stations. This paper extrapolates bicycle volume beyond these few locations to estimate street-level bicycle counts for the entire city of Berlin. We predict daily and average annual daily street-level bicycle volumes using machine-learning techniques and various data sources. These include app-based crowdsourced data, infrastructure, bike-sharing, motorized traffic, socioeconomic indicators, weather, holiday data, and centrality measures. Our analysis reveals that crowdsourced cycling flow data from Strava in the area around the point of interest are most important for the prediction. To provide guidance for future data collection, we analyze how including short-term counts at predicted locations enhances model performance. By incorporating just 10 days of sample counts for each predicted location, we are able to almost halve the error and greatly reduce the variability in performance among predicted locations.