DisasterScope: A Multi-Source Multimodal Dataset and Benchmark for Disaster Response and Severity Assessment

Jieli Chen; Kah Phooi Seng; Chee Shen Lim; Jeremy Smith; Li-Minn Ang

doi:10.3390/electronics15174050

Back

DisasterScope: A Multi-Source Multimodal Dataset and Benchmark for Disaster Response and Severity Assessment

Journal article

Open access

Peer reviewed

DisasterScope: A Multi-Source Multimodal Dataset and Benchmark for Disaster Response and Severity Assessment

Jieli Chen, Kah Phooi Seng, Chee Shen Lim, Jeremy Smith and Li-Minn Ang

Electronics, Vol.15(17), pp.1-27

2026

DOI: https://doi.org/10.3390/electronics15174050

Files and links (1)

pdf

DisasterScope: A Multi-Source Multimodal Dataset and Benchmark for Disaster Response and Severity Assessment6.27 MBDownload View

Published Version Open Access CC BY V4.0

Abstract

disaster response

multimodal dataset

satellite imagery

severity assessment

evidence retrieval

Disaster response often requires evidence from several sources, including satellite imagery, social media, news reports, audio and video recordings, and event metadata. Existing disaster datasets, however, usually focus on one source, a limited set of modalities or a single task. This separation makes it difficult to evaluate models that must combine regional observations with ground-level evidence for the same disaster context. We introduce DisasterScope, an event-centric multimodal dataset and benchmark for disaster-type recognition, severity assessment and evidence retrieval. DisasterScope organizes satellite observations, social images, synchronized audio–video segments, observation text, report passages, and provenance metadata around canonical events. Its primary benchmark contains 12,159 fixed event-context bundles from 24 events and nine disaster classes. The dynamic-media inventory includes 273 source videos, 628 curated audio–video segments, 9.02 h of material and 5473 temporal windows. Labels are harmonized through source-label inheritance, taxonomy mapping, teacher assistance and partition-specific human review. Validation and test annotations were reviewed in full, while training annotations were sampled for review and accepted through a threshold gate. The benchmark evaluates full-input and unavailable-view conditions on the same bundle identities, allowing direct measurement of how each view affects a model without changing the evaluated sample population. DisasterScope therefore provides a traceable setting for studying multimodal disaster assessment across different disasters, evidence sources and input-availability conditions.

Details

Title: DisasterScope: A Multi-Source Multimodal Dataset and Benchmark for Disaster Response and Severity Assessment
Authors: Jieli Chen - University of Liverpool
Kah Phooi Seng (Corresponding Author) - University of the Sunshine Coast
Chee Shen Lim - Xi’an Jiaotong-Liverpool University
Jeremy Smith - University of Liverpool
Li-Minn Ang - University of the Sunshine Coast
Publication details: Electronics, Vol.15(17), pp.1-27
Publisher: MDPI AG
Date published: 2026
DOI: 10.3390/electronics15174050
ISSN: 2079-9292
Copyright note: © 2026 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license.
Data Availability: The data used in this study is publicly available.
Organisation Unit: School of Science, Technology and Engineering; Engage Research Lab
Language: English
Record Identifier: 991259327402621
Output Type: Journal article

Metrics

1 Record Views