Armed conflicts can be prevented or reduced using Early Warning tools to analyze, track, and forecast fragility and conflict

Rajesh Uppal July 5, 2018 AI & IT, Threats Comments Off on Armed conflicts can be prevented or reduced using Early Warning tools to analyze, track, and forecast fragility and conflict 1,116 Views

In 2017, Deadly crisis zones have rightly been in the news: The crisis in Yemen, in which Saudi Arabia used equipment provided by the US and UK to bomb noncombatants and blockade supplies, has seen the civilian death toll climb above 5,000; civil conflict still rages in Afghanistan and Nigeria; Myanmar’s ethnic cleansing of the Rohingya has created a massive new refugee crisis, according to Vox.com.

But on the positive side of the ledger, ISIS has been militarily defeated in Syria and Iraq. The Syrian war, by far the most deadly conflict of this decade, has seen a lower death rate than previous years — estimated at 33,000 last year, compared with 50,000 in 2016. That suggests a continuation of the post-Cold War trend toward dramatically lower war deaths globally. Average battle deaths per 100,000 people worldwide were 5.7 a year between 1946 and 1989, compared with one per 100,000 each year between 1990 and 2010. We’re also continuing to see the almost-complete extinction of inter-state war.

An Early Warning and Response System (EWRS) is a tool whose primary objective is to prevent the escalation of violence that could jeopardize the integrity of individuals and democratic governance. The EWRS are mechanisms for preventing and addressing conflicts that focus on the systematic collection, processing and analysis of information (quantitative or qualitative) about conflict situations for the purpose of warning decision-makers so that they can take measures or implement actions that will avoid the emergence or escalation of conflict. These systems aim to: Identify the causes of a conflict, anticipate their outbreak, and mitigate their impact.

An initial version of the analytical tool called ViEWS (a political Violence Early-Warning System) was unveiled in June 2018. “ViEWS is a system that forecasts where in the world armed conflicts are going to occur. In a first stage we are focusing on Africa. Analyses cover the next 36 months and will be presented in the form of maps on which areas of conflict are marked with colours. Red signals high risk for conflict, while purple indicates low risk.”

Armed Conflicts and Causes

The ‘armed conflicts” are the most serious forms of conflicts, that involve organized military groups fighting against the government like the conflicts in Syria, Afghanistan, Sudan, and Israel/Palestine. Their causes are diverse, ranging from political, territorial, control of resources, social, religious, demands of “change of policies or governance” etc.

Some studies have explored the connections between climate change, migration, and social instability. Researchers led by Colin P Kelley have demonstrated that an extreme drought in Syria between 2006 and 2009 was closely linked to the emergence of the violent uprising that began in 2011, escalating the ‘Arab Spring’ movement across the region. A combination of “poor governance and unsustainable agricultural and environmental policies” led to a catalytic effect that contributed to unrest.

The researchers found that the drought exacerbated existing water and agricultural insecurity and caused massive agricultural failures and livestock mortality — the consequence of which was over 1.5 million people migrating from rural areas to urban centers. This, with other factors, catalyzed into the Arab Spring.

Early Warning of Conflict Predication

Modern technology enables us to predict the potential conflict events the world shall see in the future, it can also single out specific regions and countries for special attention. This allow organizations to perform early warning risk assessments for better planning and to target non-conflict interventions potentially limiting the break out or spread of conflict. The methodology also makes it possible to effectively evaluate the effects of peacekeeping operations, even making possible actual cost benefit analysis of such interventions.

ICT technology can help build a model which can eventually serve as an early-warning system for policy makers. It can allow to build statistical models to model the relationship between a set of structural factors such as education levels, infant mortality rates, population size, or a country’s history of armed conflict and the risk of the current armed conflict. Modern day tools like Machine learning and data mining can automate the processing and analysis of quantitative data.

The modern systems are based on information obtained directly in places of conflict, drawing on collaborative mechanisms for obtaining information via mobile data (crowdsourcing) or automated analysis of large volumes of data generated by open sources on the internet. The use of mobile phones enables speed in information collection (images, etc.) and in sharing information and alerts.

Conflict prediction systems

Many conflict prediction or forecasting have been developed over the years: The Political Instability Task Force (PITF) and the Worldwide Integrated Conflict Early Warning System (W-ICEWS) routinely update forecasts of various forms of political crisis for U.S. government customers. IARPA’s Open Source Indicators (OSI) and Aggregative Contingent Estimation (ACE) programs are simultaneously producing forecasts now and discovering ways to make future forecasts even better.

The European Union has recently developed its own Global Conflict Risk Index (GCRI), and the Early Warning Project now assesses risks of mass atrocities in countries worldwide.

Violence Early-Warning System (ViEWS )

“The system is based on data in the Uppsala University Conflict Database (UCDP), which collects information about conflicts in the world on an continual basis. This information is supplemented with data on, among other things, terrain conditions and demographics. Conflicts arise where there are people, of course, and the main indicator for predicting where future conflicts will occur is what the situation looks like right now.

“Because the system is under construction, it will be supplemented by additional sources, such as data on peacekeeping efforts, presidential elections and military coups. We also want to look at how we can analyse large amounts of text from news sources to pick up information that points to conflict.”

“It is a matter of searching for specific words and phrases to try to identify triggers that in theory could cause tensions, such as various forms of protest and how governments are acting in such situations. The analyses are updated every month, and we will also be following up on how well our prognoses reflect the reality on the ground.”

All the data that is used for analysis is freely available for anyone to see. Why have you chosen to work that way?
“The principle of full transparency is very important to us. There are already analytical tools based on intelligence information and used by bodies such as the United Nations. We have chosen to maximise transparency and just use open data to see how far it can take us. This means that we may not necessarily have the best warning system, but it will be the most open. That will be our contribution.”

Worldwide Integrated Crisis Early Warning System (W-ICEWS)

The Integrated Crisis Early Warning System (ICEWS) program is a comprehensive, integrated, automated, generalizable, and validated system to monitor, assess, and forecast national, sub-national, and internal crises. To that end, ICEWS supports decisions on how to allocate resources to mitigate crisis. Using ICEWS, Combatant Commanders (COCOMs) have a powerful capability to anticipate and respond to stability challenges, allocate resources in accordance to the risks they are designed to mitigate, and track and measure in real time the effectiveness of resource allocations toward end-state stability objectives.

There are four primary elements to ICEWS: iDATA, iTRACE, iCAST and iSENT

iDATA: The process that allows the provisioning of the models in near real-time from a variety of international, regional, national and local new sources (over 6000). More than 38 million multilingual news stories over the past 25 years are processed to extract [who, did-what, to-whom, when, and where] from each sentence in these stories creating a right 25-year “history of the world”.

iTRACE: provides situation understanding through analysis and visualization of the news event history trends and patterns generated by iDATA. Time series, map-based views, trends and pattern analytics, relationship matrices, and other visualizations are provided with drill-down to underlying events and news stories.

iCAST: mixed methods modeling approach leveraging over 80 heterogeneous model types to forecasting major instability events of interest (EOI) worldwide with greater than 80% accuracy and recall.

iSENT: Measures population attitudes and perception on issues, people, and events from social media through sentiment analysis from blogs, tweets, and Facebook. Sentiment propagation across the internet and identification of key sites and people in shaping opinion dynamics is also provided. iSENT capabilities are currently in transition discussions.

PeaceTech Data Networks Lab

US Institute of Peace has created PeaceTech Data Networks Lab to advance the institute’s work at the intersection of technology, media and data with the aiming of reducing violent conflict around the world. Dickover heads up the recently-launched Open Situation Room eXchange project, which is a collaboration and data sharing platform for peacebuilders in conflict zones. PeaceTech Lab has started using big data tools to investigate climate change-related data sources that could help detect early warning signs of social unrest and conflict.

“Data can come from the event reports of protests and violent incidents, conversations about those events on social media, and from a variety of other structured and unstructured sources. By aggregating disparate information sources, the hope is that we can find better insights on tensions arising from inter-communal violence, ethnic and religious tensions, poor governance or gender issues. The PeaceTech Lab’s Open Situation Room Exchange provides an early attempt to use this information to provide a baseline view of conflict across the globe,” explains Dickover.

CEWARN

CEWARN – IGAD’s Conflict Early Warning and Response Mechanism – was established in 2002 on the basis of a protocol signed by IGAD Member States. IGAD Member States in establishing CEWARN made a major strategic decision to utilize early warning and early response to prevent violent conflict so as to serve the aspirations of their people for shared prosperity and a sustained just peace.

CEWARN’s mandate is to receive and share information concerning potentially violent conflicts as well as their outbreak and escalation in the IGAD region; undertake and share analyses of that information; develop case scenarios and formulate options for response; share and communicate information analyses and response options; carry out studies on specific types and areas of conflict in the IGAD region.

The mechanism aspires to become “A network of excellence that works to advance an IGAD region in which reducing the risks of violent conflict through structured and consistent early warning and early response is central to local, national and regional governance in its priority areas of intervention”.

At the heart of the functionality of the CEWARN Mechanism is data collection, analysis and the timely dissemination of information and knowledge to the right people and institutions.

CEWARN’s operations have been credited with a significant reduction of violent conflict particularly along Kenya-Uganda as well as Ethiopia-Kenya-Somalia borders.

Other Systems

DARPA’s was first to develop a computerized approach to automated conflict prediction system to answer a simple question: Will this country’s government face an acute existential threat in the next six months? . Their Integrated Conflict Early Warning System, or ICEWS, is claimed to have 80% accuracy. The tools like ICES classified or proprietary and very expensive. Recently, many efforts to create open source tools to forecast violent conflicts, are being made with many teams of researchers.Different groups are experimenting with different approaches.

Researchers at Georgetown University are cataloging every significant political event of the past century into a single database called GDELT. It is also constructing a network diagram, a graph over the entire world, including not only what’s happening, but what its context is, who’s involved, and how the world is feeling about it, updated every single day. The database is open for public research; projects have already used it to map the Syrian civil war.

Ward Lab, releases a new sheet of predictions every six months. This project uses machine-coded data that is available in near-real time, as well as a variety of features such as population size and economic performance, that are updated on an annual basis. The current models are able to provide true forecasts for the month after the data observation period ends. Five countries are identified with the highest probabilities of experiencing a given event.

Neil Johnson, a physicist at the University of Miami, and his team are developing a theory of human conflict and apply it to various confrontations. Their findings provide quantitative predictions concerning future attacks; a tool to help detect common perpetrators and abnormal behaviors. Johnson and his colleagues have developed a single equation that they say describes how any two-sided asymmetric conflicts will escalate using which Johnson and his colleagues can predict how a conflict will develop based on the frequency of clashes early on.

Ramakrishnan, a professor at Virginia Tech, and his team, have developed a computer program EMBERS that try to derive meaning from tweets, news articles, satellite images and Google searches to accurately forecast civil unrest, epidemics, and elections around the world. The program correctly forecasted mass protests in Brazil last summer and those that turned violent in Venezuela earlier this year.

US Quadrennial Diplomacy and Development Review (QDDR) 2015

The U.S. Department of State ‘s Quadrennial Diplomacy and Development Review, or QDDR, lays out the department’s big-picture concerns and objectives so that—in theory—they can guide planning and shape day-to-day decision-making. One of the focus areas is enhancing the use of data, diagnostics, and technology. In a world of information saturation, effective diplomacy and development require smart investments in the technology, knowledge management, and diagnostics that allow us to leverage data. The steps outlined in this report focus on everything from better application of data for crisis prevention and inclusive growth to greater accountability for strategic planning and programs.

The QDDR establishes four main goals, one of which is to “strengthen our ability to prevent and respond to internal conflict, atrocities, and fragility.” To help do that, the State Department plans to “increase [its] use of early warning analysis to drive early action on fragility and conflict.” Specifically, State says it will:

Improve our use of tools for analyzing, tracking, and forecasting fragility and conflict, leveraging improvements in analytical capabilities;
Provide more timely and accurate assessments to chiefs of mission and senior decision-makers;
Increase use of early warning data and conflict and fragility assessments in our strategic planning and programming;
Ensure that significant early warning shifts trigger senior-level review of the mission’s strategy and, if necessary, adjustments; and
Train and deploy conflict-specific diplomatic expertise to support countries at risk of conflict or atrocities, including conflict negotiation and mediation expertise for use at posts.

Conclusion

Future developments in ICT are likely to facilitate even better data collection, more sophisticated forecasting models and more accurate automatic prediction programs.

“Early warning and response systems (EWRS) are just one of the many existing tools to prevent and resolve potential social conflicts and should be part of a comprehensive prevention strategy with other approaches, such as conciliation, mediation or dialogue, as well as the inter-institutional coordination of actors responsible for the adoption and promotion of a culture of peace among public officials and citizens,” writes Jessica Faieta UN Assistant Secretary-General Regional Director for Latin American and the Caribbean United Nations Development and Luis Almagro.