This article presents ViEWS – a political violence early-warning system that seeks to be maximally transparent, publicly available, and have uniform coverage, and sketches the methodological innovations required to achieve these objectives. ViEWS produces monthly forecasts at the country and subnational level for 36 months into the future and all three UCDP types of organized violence: state-based conflict, non-state conflict, and one-sided violence in Africa. The article presents the methodology and data behind these forecasts, evaluates their predictive performance, provides selected forecasts for October 2018 through October 2021, and indicates future extensions. ViEWS is built as an ensemble of constituent models designed to optimize its predictions. Each of these represents a theme that the conflict research literature suggests is relevant, or implements a specific statistical/machine-learning approach. Current forecasts indicate a persistence of conflict in regions in Africa with a recent history of political violence but also alert to new conflicts such as in Southern Cameroon and Northern Mozambique. The subsequent evaluation additionally shows that ViEWS is able to accurately capture the long-term behavior of established political violence, as well as diffusion processes such as the spread of violence in Cameroon. The performance demonstrated here indicates that ViEWS can be a useful complement to non-public conflict-warning systems, and also serves as a reference against which future improvements can be evaluated.

Recent research suggests that climate variability and change significantly affect forced migration, within and across borders. Yet, migration is also informed by a range of non-climatic factors, and current assessments are impeded by a poor understanding of the relative importance of these determinants. Here, we evaluate the eligibility of climatic conditions relative to economic, political, and contextual factors for predicting bilateral asylum migration to the European Union—form of forced migration that has been causally linked to climate variability. Results from a machine-learning prediction framework reveal that drought and temperature anomalies are weak predictors of asylum migration, challenging simplistic notions of climate-driven refugee flows. Instead, core contextual characteristics shape latent migration potential whereas political violence and repression are the most powerful predictors of time-varying migration flows. Future asylum migration flows are likely to respond much more to political changes in vulnerable societies than to climate change.

No abstract

The recently developed Shared Socioeconomic Pathways (SSPs) have enabled researchers to explore coupled human–nature dynamics in new and more complex ways. Despite their wide applicability and unquestionable advantage over earlier scenarios, the utility of the SSPs for conducting societal impact assessments is impaired by shortcomings in the underlying economic growth projections. In particular, the assumed economic convergence and absence of major growth disruptions break with historical growth trajectories in the developing world. The consequence is that the SSP portfolio becomes too narrow, with an overly optimistic lower band of growth projections. This is not a trivial concern, since resulting impact assessments are likely to underestimate the full human and material costs of climate change, especially for the poorest and most vulnerable societies. In response, we propose that future quantifications of the SSPs should incorporate the likelihood of growth disruptions, informed by scenarios of the relevant political contexts that historically have been important in curbing growth.

How can we secure an accessible and open democratic debate about police use of predictive analytics when the technology itself is a specialized area of expertise? Police utilize technologies of prediction and automation where the underlying technology is often a machine learning (ML) model. The article argues that important issues concerning ML decision models can be unveiled without detailed knowledge about the learning algorithm, empowering non-ML experts and stakeholders in debates over if, and how to, include them, for example, in the form of predictive policing. Non-ML experts can, and should, review ML models. We provide a ‘toolbox’ of questions about three elements of a decision model that can be fruitfully scrutinized by non-ML experts: the learning data, the learning goal, and constructivism. Showing this room for fruitful criticism can empower non-ML experts and improve democratic accountability when using ML models in policing.