Global Urban Analytics for Resilient Defence

Post Views: 835

Understanding the mechanics that cause conflict and identifying multi-scale population areas that are at risk of conflict

Research areas

Mathematical physics || Information Theory (Applied Mathematics) || Graph Theory

Introduction

The defence and security sector is increasingly facing a myriad of trans-national and trans-genre conflicts on a global scale, where the patterns in violence and underlying relationships are shifting rapidly. The directly- and indirectly-related data concerning these conflicts is overwhelming. By utilising network theory this project aims to leverage this data into identifying multi-scale population areas that are at risk of conflict.

Explaining the science

Conflict, or the threat of it, is often caused by contentious interactions between groups. This project’s research utilises the latest developments in complex networks and spatial interaction theory by Sir Alan Wilson to model the effect of multiplexed regional-global interactions.

*Interaction network between cities in the Middle East. Weak or ‘fuzzy’ community boundaries at choke points in the network correspond to instability and violence*.

**GUARD Project Example Output: Predicting Global Stability at City/Town Scale (Jan 2019)**. Each city/town is represented by a triangle (orientation – local stability, size – strategic importance, colour – level of political violence). Each link represents a multi-dimensional interaction (thickness – cultural similarity, colour – economic/political affiliation) – Credit: Gerardo Aquino (GUARD project).

Project aims

Of immediate interest to defence and security operations is the ability to automate the identification of future conflict areas (from a region to within a city) for high fidelity analysis and policy/action advice. Of long-term interest is the ability to understand the dominant interaction forces that give rise to conflict.

This work will complement existing defence and security intelligent data systems to:

Automate identification of future conflict areas to improve consistency and reduce expenditure
Improve understanding of causal mechanisms by quantifying interaction effects
Transform network theory into military actionable tasks.

Applications

This work has potential for application across a wide range of defence and security contexts in forecasting conflict and determining their geographic relations.

Recent updates

February 2019

BBC video interview with Dr Weisi Guo, ‘How AI could unlock world peace’

October 2018

Dr Weisi Guo and Sir Alan Wilson wrote a comment piece for Nature, explaining how using artificial intelligence to predict outbursts of violence and probe their causes could save lives.

The piece details existing research being conducted into the forecasting of conflict, including this project. The piece identifies three things that will improve conflict forecasting: new machine-learning techniques; more information about the wider causes of conflicts and their resolution; and theoretical models that better reflect the complexity of social interactions and human decision-making. The piece goes on to propose that an international consortium be set up to develop formal methods to model the steps society takes to wage war.

Read the full Nature comment piece