Connectionists: Special Issue on “Advancing Visual Data Analytics for Disaster Management”.

[Efi P]

*CALL FOR PAPERS*


*Special Issue on “Advancing Visual Data Analytics for Disaster Management”
IMAGE AND VISION COMPUTING*



*Visit the **Website*
<https://www.sciencedirect.com/special-issue/322678/advancing-visual-data-analytics-for-disaster-management>



>From torrents of satellite imagery to drone video streams and
citizen-generated footage, visual data now shapes how we forecast, respond
to, and recover from catastrophes. This Special Issue of *Image and Vision
Computing* journal seeks state-of-the-art research that converts these
heterogeneous visual streams into trustworthy, real-time intelligence for
natural- and human-made disaster management. We welcome breakthroughs
in *computer
vision*, *machine learning*, *multimodal fusion*, *privacy-preserving
analytics*, *explainability*, *high-performance/edge computing*, and
*generative
simulation*. Join us in building a cross-disciplinary forum where novel
algorithms meet operational challenges, advancing resilience and saving
lives through *smarter visual data analytics*.



With the increasing frequency and severity of natural and man-made
disasters, effective disaster management is a global priority. Visual data
from any source play a vital role in disaster preparedness, response, and
recovery. Efficient and accurate analysis of this visual data is crucial
for understanding disaster scale and impact, while having significant
implications for broader challenges in visual data analytics.



This *Special Issue* on “*Advancing Visual Data Analytics for Disaster
Management*” seeks to present cutting-edge methodologies, emerging
applications, and core challenges in deriving actionable insights from
visual data in disaster contexts. Emphasis is placed on advanced computer
vision, machine learning, and data science methods for processing visual
data streams in real-time or near-real-time, supporting *disaster
prediction*, *detection*, *monitoring*, and *assessment*.



The Special Issue offers a forum for discussing challenges in visual data
analytics with a primary focus on *disaster management*. Potential
applications include, not exhaustively, flood monitoring, wildfire
tracking, earthquake damage assessment, and urban disaster response. The
aim is to foster collaboration across disciplines – computer vision,
machine learning, data science – and identify future research directions.



We welcome submissions on novel *algorithms*, *methods*, and *systems* for
visual data analytics with direct relevance to disaster management or
similarly *critical real-world scenarios*.



*Topics of interest* include, but are not limited to:

   - Advanced *deep learning* models for understanding complex visual data
   in critical scenarios.
   - *Real-time analytics* of visual data from UAVs, satellites, and social
   media for disaster response and similar applications.
   - *Visual data summarization* and feature extraction for rapid disaster
   assessment.
   - *Human-centered visual recognition* methods for disaster scenarios.
   - *Multimodal visual data analysis* integrating sources like
   hyperspectral imaging, LIDAR, and thermal imaging.
   - *Generative models* for visual data: simulation of disaster scenarios,
   in-painting, and handling incomplete data.
   - *Explainable and interpretable models* to support decision-making in
   high-stakes environments.
   - *Privacy-preserving visual* analytics using methods like differential
   privacy and federated learning.
   - *Scalable algorithms and architectures* for large-scale visual data
   processing in disasters.
   - *High-performance and parallel computing* approaches for visual data
   analytics.
   - *Domain-specific analytics* for remote sensing, wildfire detection,
   flood mapping, earthquake damage, etc.
   - *Ethical considerations* in visual analytics for disaster management.



*Submission Guidelines:*

The Journal's submission system (Editorial Manager
<https://www.editorialmanager.com/imavis/default.aspx>) will be open for
submissions to our Special Issue from July 1st, 2025. Please refer to the
Guide for Authors to prepare your manuscript and select the article type of
“*VSI: Visual Data for DM*” when submitting your manuscript online. Both
the Guide for Authors and the submission portal could be found on the
Journal Homepage: Guide for authors - Image and Vision Computing - ISSN
0262-8856 (elsevier.com)
<https://www.elsevier.com/journals/image-and-vision-computing/0262-8856/guide-for-authors>
.

Submissions must follow the IMAGE AND VISION COMPUTING journal’s formatting
and submission requirements. All manuscripts will undergo rigorous peer
review. Contributions must be original and unpublished, focusing on visual
data analytics methods and their applications in disaster management.



*Important Dates:*

   - Manuscript Submission Open Date: *July 1st, 2025*
   - Manuscript Submission Deadline: *October 31st, 2025*
   - Editorial Acceptance Deadline: *February 28th, 2026*



*Guest Editors:*

   1. Prof. Ioannis Pitas (Department of Informatics, Aristotle University
   of Thessaloniki, Greece)

*e-mail address: **pitas at csd.auth.gr* <pitas at csd.auth.gr>

   2. Prof. Jose Ramiro Martinez de Dios (Robotics, Vision and Control
   Group, University of Seville, Spain)

*e-mail address: **jdedios at us.es* <jdedios at us.es>

   3. Prof. Stefano Berretti (Media Integration and Communication Center,
   University of Florence, Italy)

*e-mail address: **stefano.berretti at unifi.it* <stefano.berretti at unifi.it>

   4. Dr. Ioannis Mademlis (Department of Informatics, Aristotle University
   of Thessaloniki, Greece)

*e-mail address: **imademlis at csd.auth.gr* <imademlis at csd.auth.gr>



We look forward to your contributions to this Special Issue on advancing
visual data analytics for more effective disaster management and similar
real-world applications.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20250618/d1e3bd0d/attachment.html>