Abstract
Migrant disappearances have become a critical humanitarian crisis on global scale. However, the lack of strong, consolidated data across irregular migration routes is a barrier to effective intervention. In this paper, we aim to employ a sociotechnical systems perspective to design an ethics-infused infrastructure. Our primary objective is to convert multimodal digital traces into actionable intelligence, thereby supporting search, identification, and policy accountability. To standardize the analysis of decentralized digital evidence, we define a typology of 32 trace types encompassing ten domains, categorized from geospatial markers to psychosocial signals. This classification is the basis for the modular architecture of five linked cores. We present a novel approach that combines entity resolution and spatiotemporal reconstruction with provenance tracking and explainable AI to support effective humanitarian action. These features enable robust early warning capabilities and provide decision support aligned with OCHA standards. The framework aims to facilitate compliance with FAIR data principles and international human rights standards through embedding cross-layer safeguards including dynamic consent, auditability and interoperability. This research provides a scalable, replicable method to validate digital evidence throughout the migration cycle. It bridges computational innovation and rights-based governance. Future work should focus on operational pilots to assess feasibility, triage efficiency, identification accuracy, and family notification protocols.
Funding Statement This work was developed within the framework of the COST Action (CA22106: Migrant Disaster Victim Identification (MDVI)). While no direct financial support for research or publishing costs was received, the study was supported by the networking opportunities and workshops provided by the Action.
The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Amendment
To enhance replication and technical soundness, the system architecture has been structured into an operational workflow matrix defining inputs, outputs, standards, and decision rules across four component tiers. A synthetic case-based application has been added to demonstrate exactly how data moves through the five system cores under human-in-the-loop supervision when resolving conflicting spatial information. Finally, this version introduces a comprehensive validation plan spanning 12 harm-aware and operational metrics, establishes explicit operational red lines within a new section on failure modes and non-deployment conditions, and appends a technical mapping matrix in a supplementary appendix. Throughout the text, deterministic language regarding system performance has been systematically softened to accurately reflect the current conceptual status of the infrastructure.
