Multimodal GeoAI for Spatial Fusion: Multi-Source Geotagged Images, Video and Sound

Dear Colleagues,

In recent years, the rapid evolution of Geospatial Artificial Intelligence (GeoAI) has profoundly reshaped the landscape of geospatial analysis. Technologies such as deep learning (e.g., transformer architectures) and generative models have enabled unprecedented capabilities in image understanding, pattern recognition, and spatial reasoning. However, single-source, single-view, and single-modal data are often not sufficient to fully deal with the complexity of real-world geospatial phenomena. The integration of multimodal spatial data, such as multi-source imagery (e.g., remote sensing, UAV, and street-level imagery), geotagged video, and geotagged sounds, presents both a critical challenge and a transformative opportunity.

This Special Issue aims to explore the convergence of GeoAI and multimodal fusion, fostering innovative methodologies and applications that leverage complementary information across sensors, perspectives, and modalities. Specifically, it aims to explore the roles and significance of integrating multimodal data—such as multi-source imagery (e.g., remote sensing images, UAV images, ground-level street view images), geotagged videos, and sound—into the modeling of urban built environments, urban development, urban green spaces, urban mobility, and urban health, as well as socio-economic development. Therefore, this Special Issue aligns well with the aims and scope of the journal Remote Sensing.

We invite the submission of high-quality original research articles in areas including, but not limited to, the following:

• Multimodal Geospatial Data Fusion: Novel architectures and models for the cross-view, cross-resolution, and cross-modal alignment and fusion of multi-source imagery (e.g., remote sensing, UAV, and street-level imagery), geotagged video and sounds, as well as other new types of geospatial data.
• GeoAI Foundation Models: Development of pre-trained or self-supervised models capable of processing and representing multimodal geospatial data at scale.
• Vision Language Models (VLMs): Development and fine-tuning of VLMs for multimodal geospatial data fusion.
• Cross-Domain Learning and Transfer: Techniques for model transfer and domain adaptation between different geospatial data sources and geographic contexts.
• Urban Governance and Management: Applications in urban planning, 3D city modeling, traffic monitoring, land use classification, and smart city governance.
• Urban Health and Wellbeing: Applications in environmental exposure, urban health, quality of life, wellbeing, and lifestyles.
• Disaster Response and Environmental Monitoring: Technologies for rapid damage assessment, flood mapping, landslide detection, and ecological analysis using multi-source geospatial data.
• Infrastructure Inspection and Change Detection: Automated systems for monitoring roads, bridges, buildings, and utilities through fused aerial and ground imagery.
• Real-Time and Edge Computing for Geospatial Fusion: Lightweight models and system designs enabling onboard or real-time processing for multimodal geospatial data.

Prof. Dr. Haosheng Huang
Dr. Fangli Guan
Prof. Dr. Zhixiang Fang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.