// NATURE NEWS — SPAZIO & SCIENZA
Advancing conflict research and response through satellite-derived data
Nature
(2026) Cite this article
With armed conflicts at a historic high and attacks on civilians rising1, understanding the evolving nature of conflict is a critical research priority. The current paradigm in conflict research relies heavily on text-based data, using fatalities as the primary—and often sole—proxy for violence intensity. Although these data have expanded our ability to study armed conflict, they exhibit inherent limitations due to uneven human reporting2,3,4,5,6. War damage assessments based on satellite data7,8,9,10,11,12,13 offer a complementary perspective. Satellite-derived data have their own limitations, but these arise from different mechanisms, creating distinct, complementary strengths that can be leveraged through data integration. Here we propose three concrete approaches to integration: improvement, enrichment and fusion. Each bridges a different gap in the underlying data sources. We use case studies from Ukraine and Myanmar to illustrate how integration can be implemented in practice and the novel analytical insights that emerge. Prioritizing data integration enables a paradigm shift away from fatality-centric research towards a broader spectrum of violence, revealing the complexity of conflict dynamics.
We are witnessing a record number of armed conflicts, and attacks on civilians are increasing in number1. In conflicts such as those in Gaza, Ukraine, Sudan and Myanmar, the use of heavy weaponry, drone warfare and arson has caused widespread death, destruction and displacement, leaving lasting scars on entire countries. This makes understanding the evolving nature of armed conflicts and developing strategies to reduce violence a critical research priority.
Despite the urgency of studying armed conflict, there are important limitations in the available data. Over the past 15 years, conflict research has made substantial progress with the emergence of detailed conflict event datasets based primarily on media sources14,15,16. However, these datasets exhibit well-documented limitations and biases that reflect the uneven availability of human reporting2,3,4,5,6. Most notably, because media reporting is attention-driven, there is a lack of reliable data from places and periods that receive little media coverage, and from types of event that often go unreported or are reported only in unspecific terms17,18, such as the destruction of dwellings and crops or the displacement of populations. Accordingly, quantitative studies of conflict-related violence focus predominantly on fatalities and often leave other aspects of violence and their social and environmental effects unaddressed.
We propose an approach to broaden this focus through the integration of text-based conflict event data with satellite-derived data. Here we use the term satellite-derived data to refer to information generated through the analysis of satellite data (see Supplementary Information, section B). Advances in automated satellite analysis7,8,9,10,19,20,21,22 and increasingly available open-access satellite data make this a pivotal moment for such data integration. Prior work has highlighted the potential of satellite data for humanitarian action23,24,25 and provided remote-sensing-based perspectives on specific conflicts9,10,26,27,28,29. In this Analysis, we demonstrate how the fundamentally different data generation processes of text-based and satellite-derived data lead to unique strengths and limitations that can be overcome only through data integration. We propose three approaches to integration—improvement, enrichment and fusion—and use empirical examples from Ukraine and Myanmar to illustrate their feasibility and the novel empirical insights that they provide. We advocate for prioritizing this integration to enable a paradigm shift away from fatality-centric research towards a broader spectrum of violence, to reveal the complex, interactive dynamics that shape conflict landscapes.
To reduce im