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.

Machine learning (ML) techniques have emerged as a powerful tool for predicting weather and climate systems. However, much of the progress to date focuses on predicting the short-term evolution of the atmosphere. Here, we look at the potential for ML methodology to predict the evolution of the ocean. The presence of land in the domain is a key difference between ocean modeling and previous work looking at atmospheric modeling. Here, we look to train a convolutional neural network (CNN) to emulate a process-based General Circulation Model (GCM) of the ocean, in a configuration which contains land. We assess performance on predictions over the entire domain and near to the land (coastal points). Our results show that the CNN replicates the underlying GCM well when assessed over the entire domain. RMS errors over the test dataset are low in comparison to the signal being predicted, and the CNN model gives an order of magnitude improvement over a persistence forecast. When we partition the domain into near land and the ocean interior and assess performance over these two regions, we see that the model performs notably worse over the near land region. Near land, RMS scores are comparable to those from a simple persistence forecast. Our results indicate that ocean interaction with land is something the network struggles with and highlight that this is may be an area where advanced ML techniques specifically designed for, or adapted for, the geosciences could bring further benefits.

Originating from a unique partnership between data scientists (datavaluepeople) and peacebuilders (Build Up), this commentary explores an innovative methodology to overcome key challenges in social media analysis by developing customized text classifiers through a participatory design approach, engaging both peace practitioners and data scientists. It advocates for researchers to focus on developing frameworks that prioritize being usable and participatory in field settings, rather than perfect in simulation. Focusing on a case study investigating the polarization within online Christian communities in the United States, we outline a testing process with a dataset consisting of 8954 tweets and 10,034 Facebook posts to experiment with active learning methodologies aimed at enhancing the efficiency and accuracy of text classification. This commentary demonstrates that the inclusion of domain expertise from peace practitioners significantly refines the design and performance of text classifiers, enabling a deeper comprehension of digital conflicts. This collaborative framework seeks to transition from a data-rich, analysis-poor scenario to one where data-driven insights robustly inform peacebuilding interventions.

The application of data analytics to product usage data has the potential to enhance engineering and decision-making in product planning. To achieve this effectively for cyber-physical systems (CPS), it is necessary to possess specialized expertise in technical products, innovation processes, and data analytics. An understanding of the process from domain knowledge to data analysis is of critical importance for the successful completion of projects, even for those without expertise in these areas. In this paper, we set out the foundation for a toolbox for data analytics, which will enable the creation of domain-specific pipelines for product planning. The toolbox includes a morphological box that covers the necessary pipeline components, based on a thorough analysis of literature and practitioner surveys. This comprehensive overview is unique. The toolbox based on it promises to support and enable domain experts and citizen data scientists, enhancing efficiency in product design, speeding up time to market, and shortening innovation cycles.

This commentary discusses opportunities for advancing the field of developmental psychopathology through the integration of data science and neuroscience approaches. We first review elements of our research program investigating how early life adversity shapes neurodevelopment and may convey risk for psychopathology. We then illustrate three ways that data science techniques (e.g., machine learning) can support developmental psychopathology research, such as by distinguishing between common and diverse developmental outcomes after stress exposure. Finally, we discuss logistical and conceptual refinements that may aid the field moving forward. Throughout the piece, we underscore the profound impact of Dr Dante Cicchetti, reflecting on how his work influenced our own, and gave rise to the field of developmental psychopathology.

Cyber-Physical-Systems provide extensive data gathering opportunities along the lifecycle, enabling data-driven design to improve the design process. However, its implementation faces challenges, particularly in the initial data capturing stage. To identify those, a comprehensive approach combining a systematic literature review and an industry survey was applied. Four groups of interrelated challenges were identified as most relevant to practitioners: data selection, data availability in systems, knowledge about data science processes and tools, and guiding users in targeted data capturing.

In “How Can Spin, Ply, and Knot Direction Contribute to Understanding the Quipu Code?” (2005), mathematician Marcia Ascher referenced new data on 59 Andean khipus to assess the significance of their variable twists and knots. However, this aggregative, comparative impulse arose late in Ascher's khipu research; the mathematical relations she had identified among 200+ previously cataloged khipus were specified only at the level of individual specimens. This article pursues a new scale of analysis, generalizing the “Ascher relations” to recognize meaningful patterns in a 650-khipu corpus, the largest yet subjected to computational study. We find that Ascher formulae characterize at least 74% of khipus, which exhibit meaningful arrangements of internal sums. Top cords are shown to register a minority of sum relationships and are newly identified as markers of low-level, “working” khipus. We reunite two fragments of a broken khipu using arithmetic properties discovered between the strings. Finally, this analysis suggests a new khipu convention—the use of white pendant cords as boundary markers for clusters of sum cords. In their synthesis, exhaustive search, confirmatory study, mathematical rejoining, and hypothesis generation emerge as distinct contributions to khipu description, typology, and decipherment.

Political opposition to fiscal climate policy, such as a carbon tax, typically appeals to fiscal conservative ideology. Here, we ask to what extent public opposition to the carbon tax in Canada is, in fact, ideological in origin. As an object of study, ideology is a latent belief structure over a set of issue topics—and in particular their relationships—as revealed through stated opinions. Ideology is thus amenable to a generative modeling approach within the text-as-data paradigm. We use the Structural Topic Model, which generates word content from a set of latent topics and mixture weights placed on them. We fit the model to open-ended survey responses of Canadians elaborating on their support of or opposition to a carbon tax, then use it to infer the set of mixture weights used by each response. We demonstrate this set, moreso than the observed word use, serves efficient discrimination of opposition from support, with near-perfect accuracy on held-out data. We then operationalize ideology as the empirical distribution of inferred topic mixture weights. We propose and use an evaluation of ideology-driven beliefs based on four statistics of this distribution capturing the specificity, variability, expressivity, and alignment of the underlying ideology. We find that the ideology behind responses from respondents who opposed the carbon tax is more specific and aligned, much less expressive, and of similar variability as compared with those who support the tax. We discuss the implications of our results for climate policy and of broad application of our approach in social science.

This study aimed to identify and understand the major topics of discussion under the #sustainability hashtag on Twitter (now known as “X”) and understand user engagement. The sharp increase in social media usage combined with a rise in climate anomalies in recent years makes the area of sustainability with respect to social media a critical topic. Python was used to gather Twitter posts between January 1, 2023, and March 1, 2023. User engagement metrics were analyzed using a variety of statistical analysis methods, including keyword-frequency analysis and Latent Dirichlet Allocation (LDA), which were used to identify significant topics of discussion under the #sustainability hashtag. Additionally, histograms and scatter plots were used to visualize user engagement. LDA analysis was conducted with 7 topics after trials were run with various topics and results were analyzed to determine which number of topics best fit the dataset. The frequency analysis provided a basic overview of the discourse surrounding #sustainability with the topics of technology, business and industry, environmental awareness, and discussion of the future. The LDA model provided a more comprehensive view, including additional topics such as Environmental, Social, and Governance (ESG) and infrastructure, investing, collaboration, and education. These findings have implications for researchers, businesses, organizations, and politicians seeking to align their strategies and actions with the major topics surrounding sustainability on Twitter to have a greater impact on their audience. Researchers can use the results of this study to guide further research on the topic or contextualize their study with existing literature within the field of sustainability.

There are now an estimated 114 million forcibly displaced people worldwide, some 88% of whom are in low- and middle-income countries. For governments and international organizations to design effective policies and responses, they require comparable and accessible socioeconomic data on those affected by forced displacement, including host communities. Such data is required to understand needs, as well as interactions between complex drivers of displacement and barriers to durable solutions. However, high-quality data of this kind takes time to collect and is costly. Can the ever-increasing volume of open data and evolving innovative techniques accelerate and enhance its generation? Are there applications of alternative data sources, advanced statistics, and machine-learning that could be adapted for forced displacement settings, considering their specific legal and ethical dimensions? As a catalytic bridge between the World Bank and UNHCR, the Joint Data Center on Forced Displacement convened a workshop to answer these questions. This paper summarizes the emergent messages from the workshop and recommendations for future areas of focus and ways forward for the community of practice on socioeconomic data on forced displacement. Three recommended areas of future focus are: enhancing and optimizing household survey sampling approaches; estimating forced displacement socioeconomic indicators from alternative data sources; and amplifying data accessibility and discoverability. Three key features of the recommended approach are: strong complementarity with the existing data-collection-to-use-pipeline; data responsibility built-in and tailored to forced displacement contexts; and iterative assessment of operational relevance to ensure continuous focus on improving outcomes for those affected by forced displacement.

Statistical profiling of job seekers is an attractive option to guide the activities of public employment services. Many hope that algorithms will improve both efficiency and effectiveness of employment services’ activities that are so far often based on human judgment. Against this backdrop, we evaluate regression and machine-learning models for predicting job-seekers’ risk of becoming long-term unemployed using German administrative labor market data. While our models achieve competitive predictive performance, we show that training an accurate prediction model is just one element in a series of design and modeling decisions, each having notable effects that span beyond predictive accuracy. We observe considerable variation in the cases flagged as high risk across models, highlighting the need for systematic evaluation and transparency of the full prediction pipeline if statistical profiling techniques are to be implemented by employment agencies.