World Resources Institute - Water, Peace and Security - Global Early Warning Tool
Data category
- Social data
- Conflict
The data offers solutions for:
- Nature-based information: Water
- Social impact analysis and insight
- Conflict forecast;
Who are the data users?
- Government
- Water policymakers; Disaster risk reduction policymakers; Defence, development, diplomacy, and disaster relief actors
Brief description of the data offering
The Water, Peace, and Security (WPS) Partnership — a collaboration between the Netherlands Ministry of Foreign Affairs and a consortium of six partners: IHE Delft (lead partner), World Resources Institute, Deltares, The Hague Centre for Strategic Studies, Wetlands International and International Alert — was founded in 2018 to develop innovative tools that identify and address water-related security risks. WPS provides data, analyses risks, proposes solutions, and supports the prevention of conflicts over water by enabling policymakers and communities to take coordinated action at an early stage.
WPS’ Global Early Warning Tool enables actors from the global defence, development, diplomacy and disaster relief sectors, and national governments to identify conflict hotspots before violence erupts, begin to understand the local context and prioritise opportunities for water interventions. Based on this information, evidence-based actions can be taken to mitigate human security risks, which WPS facilitates through capacity development and dialogue support. While primarily used to predict water- and climate-related conflict, the Global Early Warning Tool is designed to forecast any type of violent conflict (and can therefore be used by a variety of users interested in conflict).
Where and how do you source your data?
The foundation of our forecasting is an expansive library of quantitative indicators potentially related to conflict. The indicators used in our model — predictor variables — are available for exploration as both interactive maps and time series. The selection of these indicators or predictor variables for the model is based on a feature-importance analysis. Out of the 80+ indicators tested, the most relevant indicators were used in the current model to produce the forecasts.
Like an initial medical screening, the long-term model is optimized to flag all concerning cases for further analysis. In other words, we would rather wrongly forecast the presence of conflict than incorrectly forecast its absence (i.e. ‘peace’, in the strictly negative sense). The downside to this decision is that the long-term forecast overestimates conflict. Users interested in the ongoing conflict forecasts can have high confidence in the forecast and may feel comfortable acting on this information immediately. For emerging conflicts, users can view these results as a ‘first screening’, feeling confident that our ‘net’ has caught most emerging conflicts, but acknowledging they are interspersed with many instances of peace.
What is the cost for your data offering?
Free.