A new report from the University of Liverpool and the United Nations Migration Agency – International Organization for Migration (IOM) demonstrates how harnessing digital data collected from mobile phone applications and social media platforms can transform the way humanitarian agencies track and respond to population displacement during crises.
Co-authored by researchers from the University of Liverpool and the IOM Displacement Tracking Matrix (DTM), the report Dynamic Estimates of Displacement in Disaster Regions: A Policy-driven Framework Triangulating Data sets out a cutting-edge framework that combines the complementary expertise of academic researchers, humanitarian practitioners and technology partners through digital trace data, geographic data science and traditional humanitarian data.
By integrating multiple data sources, this framework delivers faster, more spatially fine-grained estimates of population movement. This currently scarce information is crucial for delivering timely humanitarian assistance when and where it is needed most.
Cloud-based data storage company Snowflake supported this work through its End Data Disparity initiative, which is helping break down data silos, enable better decisions and drive real-world impact.
The report was launched at a special webinar held on Tuesday 25th November, which featured expert speakers from the University of Liverpool, IOM’s DTM and Snowflake.
Drawing on expertise from Dr Elisabetta Pietrostefani and Professor Francisco Rowe of the University’s Geographic Data Science Lab, the report includes two in-depth case studies: the ongoing war in Ukraine and the devastating Pakistan floods in 2022. These examples showcase how the framework can support rapid, evidence-based decision-making across different types of emergencies.
With an estimated 123.2 million people forcibly displaced globally in 2024, the authors highlight an urgent need for accessible, spatially detailed data to guide policy and humanitarian action.
The publication offers practical guidance for governments, NGOs and international agencies on integrating multiple streams of data to enhance preparedness and response to crises triggered by conflict, climate change and public health emergencies.
Dr Elisabetta Pietrostefani, Lecturer in Geographic Data Science, said: “Accurate, real-time, and spatially detailed data are essential for effective humanitarian action, yet they are often the hardest to obtain during crises. This report shows how new forms of digital data, combined with traditional sources, can provide clearer and more responsive insights. Just as importantly, it demonstrates the value of strong partnerships between academia, humanitarian organisations, and the private sector—working together to turn complex data into meaningful support for people affected by disasters.”
Professor Francisco Rowe, Professor of Population Data Science, added: “These case studies demonstrate how data triangulation can improve crisis response across different contexts—from war to climate-driven events. By bringing together diverse data sources, we can provide humanitarian actors with faster, more reliable and actionable information. Such data triangulation approaches have the potential to significantly strengthen decision-making during emergencies.”
Robert Trigwell, Senior DTM Coordination Officer, IOM added: “Displacement does not necessarily indicate vulnerability or special needs. Instead, displacement data is essential for complementing operations and response efforts. This is where traditional datasets such as the IOM-DTM do an excellent job.”
Find out more: https://publications.iom.int/books/dynamic-estimates-displacement-disaster-regions-policy-driven-framework-triangulating-data
This project and accompanying video were funded through the Research England Policy Support Fund.
Publication of the fundamental research unpinning the report: https://doi.org/10.1057/s41599-025-06137-4
The Geographic Data Science Lab is a centre of excellence for research and teaching within this emerging area, drawing expertise from the intersection of social sciences and computational sciences.