Progress Thus Far

Thus far we conducted a proof-of-concept case study in Syria. Our analysis showed that, within a given country at risk of sociopolitical instability and conflict such as Syria, it is possible to create models predicting risk of climate-induced migration, protest, and related violence more precisely, down to the city level, and with higher predictive power than enabled by most publicly available research.¹ Additionally, for hotspots where protest or political violence occurred, we were able to accurately determine whether direct climate impacts or resulting migration had played a causal role in sparking the violence. To do so, our study used a cluster analysis of available satellite data on environmental and demographic factors, followed by causal mediation analysis on the impact of climate-induced drought on protest, mediated by migration. Our study’s findings represent a significant positive step in conflict early prediction and prevention.

Comparison with Current Research and Early Warning Systems

For comparison, a handful of recent studies in various African countries have achieved results relating climatic factors to conflict with a similar level of granularity; our study achieved a higher spatial resolution than all but one of these analyses.¹³ If we are able to build on existing conflict research to predict climate related socio-political instability and violence at a global scale, we would be, to the best of our knowledge, the first to have done so. In the area of early warning systems, the Pentagon’s recently re-classified Worldwide Integrated Crisis Early Warning System (W-ICEWS) uses compilations of news reports to predict global conflict incidents with over 80% accuracy.¹⁴ Because of its reliance on news reports, however, the system does not appear to enable users to determine whether predicted conflicts are likely to be significantly sparked by climate impacts or to do so with enough lead time (on the order of 5-10 years) to determine in which locations targeted environmental peacebuilding work will be most critical.

According to a 2012 study by the UNEP, the types of early warning systems required to target environmental peacebuilding work, in particular, those for creeping hazards such as drought, are the least developed of all types of early warning systems, and only a few such national and regional systems exist worldwide.¹¹ The most reliable global early warning system around drought impacts is the UNFAO’s Global Information and Early Warning System on Food and Agriculture (GIEWS). This is the system that helped trigger investigations into the impact of drought in Syria; however, it was not able on its own to predict links between early drought and later unrest at the city or subdistrict level.¹

Proposed Intervention Strategies

In addition to predicting locations in which climate impacts are likely to lead to conflict, we have brought together research from other organizations that has helped to determine the most impactful and cost-effective interventions in the intersection of GHG mitigation and conflict prevention. Notable among these are several of the top ten most cost effective GHG mitigation methods described by the 2017 Drawdown report:⁵

• Regenerative agriculture and silvopasture sequester up to 60 tons of CO₂ per acre while improving soil quality and agricultural output, reducing the need for water, and combatting desertification. A case study involving similar methods in Afghanistan found that they reduced opium trade by enabling farmers to grow alternative low-water high-income crops, reduced terrorism, and ultimately enabled post-conflict resettlement of the areas in which they were implemented.
• In severely water-stressed and conflict-vulnerable locations, phasing out fossil fuel infrastructure and replacing it with distributed renewable energy generation saves critical water resources, reduces the vulnerability of energy infrastructure to conflict-related damages, and can contribute to income generation and community empowerment when accompanied by local skill training on construction and maintenance.
• Education of women and girls contributes both to conflict prevention through peacebuilding and climate change mitigation itself. Women with more years of education have fewer and healthier children, which reduces carbon emissions, water needs, and the population shocks that contribute to instability by stabilizing population growth. Educating girls and women enables their participation in peacebuilding processes, which during war-time increases the probability that conflict will end within a year by 24% and increases the likelihood of lasting peace.

Empowering local community organizers to implement these strategies and seek continued government funding and support for them is one of the most cost-effective methods NGOs and private foundations can use to leverage additional resources.¹⁵ This strategy has the additional benefit of strengthening democratic processes in conflict-vulnerable nations, while being available to smaller organizations that do not have the capacity to implement the above strategies directly. By determining the critical locations for this work, in time for community-based strategies to take place, and facilitating communication between larger and smaller organizations and funding sources, we hope to make an outsized impact in preventing climate-induced conflict.

Next Steps

We have divided our work into two distinct phases: Research and Implementation. During the first phase, we will construct a model to help us predict where environmental impacts are most likely to lead to sociopolitical instability and conflict globally, as well as build relationships with individual domain experts and organizations working in environmental conflict prediction and prevention. Once we have created a predictive model, we plan to use it as an action plan for the next stage of our work, in conjunction with the strategic advice we have received during the process.

Research

Our goal over the next few months is to create a global model predicting future sociopolitical instability and related violence at the city level, as well as in which locations environmental peacebuilding work is likely to make the greatest difference in preventing this conflict. To do so, we plan to improve upon our existing approach in the following ways.

Scale and Scope of Data

We will expand from an analysis of Syria to a global scale. For this reason, all satellite and events data we use will be global in context. Our next analysis will include our original data sources on rainfall, drought severity, NDVI, cropland percentage, population density and population growth rates.¹ To this, we will add the following:

• National and subnational governance data on regime type and stability, as well as indicators of well-being including infant mortality, GDP and GDP growth;¹⁶
• Environmental data including temperature, soil moisture content, and predicted climate impacts such as rainfall variability and flood and drought occurrence;
• Known conflict risk factors including ethic composition and fractionalization, presence of petroleum and high value mineral resources, and past incidence of conflict;¹⁶ and
• Events and media reports from the GDELT Project indicating occurrence of violent events, media tone, and keyword mentions of political and environmental concerns.¹⁷

Algorithms and Approach

Because standard regression models are often poor at predicting conflict compared to more recently developed machine learning algorithms,¹⁸ we plan to improve our forecasting ability through application and comparative testing of three to four machine learning models. To do so, we will select the random forest and similar supervised learning models, train them on a subset of available data related to past conflicts, and then cross-validate them using the remaining available past conflict data. After fine-tuning each model, we will select the one with the highest predictive accuracy. This approach has advantages over typical regression models in that, with sufficient data, it allows for very high accuracy.¹⁸ We believe decision tree based approaches like the random forest model will be especially helpful because they can provide some indication of the potential causal role each of our variables played in spurring conflict, and can be trained using a smaller set of data points.^19,20 These last two characteristics are particularly helpful to our study both because conflicts are relatively rare events²¹ and because we plan to investigate what role environmental factors played in each conflict.

Domain Expertise

In order to construct the best possible model and ensure thoroughness in providing input data, we plan to consult practitioners with expertise in the following domains:

• Conflict prediction and prevention,
• Disaster and conflict early warning systems,
• Climate change impacts and adaptation in developing nations,
• Environmental peacebuilding methods and impact evaluation,
• International governance and state stability, and
• Machine learning in social science contexts.

These experts will be able to provide practical insights from their past experience, help us refine the questions we are posing, guide our analytics in the right direction, and help evaluate the effectiveness of our results.²² With the help of our team members and advisers, we expect to have this process completed within 4-6 months. Once our algorithm has been validated, we plan to begin the application phase of our work while iterating our research process to further improve our model.

We plan to engage in a cyclical research process (illustrated above) beginning with data gathering and process validation through interviews and discussions with practitioners. We will use this step to refine our questions and ensure we have acquired all available related data. After feeding this data into a multiple test models, we will select and refine our top performing model, interpret the results, and review them in collaboration with practitioners. A few iterations of this research process over the course of 4-6 months will provide a solid foundation for the application phase of our work and continue to support our intervention-focused work thereafter.

Application

As a delay often exists between advances in research and their application, we hope to speed along this process by developing organizational partnerships that will allow us to ensure our research benefits local communities as soon as possible. We are looking at options ranging from advocacy within larger organizations, to launching a pilot study to better determine the impact of this work in climate and conflict vulnerable locations, to raising funding and support for local advocates and organizers in vulnerable locations. Because the UNEP has identified impact assessment as a major gap to be filled for targeted environmental peacebuilding work to gain widespread institutional support, we believe launching a pilot study in partnership with a larger organization and assessing its impact will be our most important next step.¹¹ This pilot study would likely include a subset of the intervention strategies proposed above, tailored to the local context and centered around empowerment of local community organizers. We expect our long-term strategy, however, to involve a multi-faceted approach shaped by the relationships we build and the advice we are able to obtain during our research-focused phase over the next few months. Our ultimate goal is to help individuals and organizations working to address climate change and conflict focus their efforts as effectively as possible, and to ensure that those in vulnerable locations are able to receive the funding and resources they need.