Geocarto International

Multimodal Artificial Intelligence for Remote Sensing and Geospatial Intelligence

Geocarto International is pleased to welcome you to submit your research to the Article Collection "Multimodal Artificial Intelligence for Remote Sensing and Geospatial Intelligence"

Remote sensing and geospatial science increasingly rely on heterogeneous data acquired from multiple platforms and sensors. Such data include those from optical and hyperspectral imagery, synthetic aperture radar, LiDAR and 3D point clouds, UAVs, and the Internet of Things. Artificial intelligence provides powerful tools for learning complementary representations across these modalities and for extracting spatial, spectral, temporal, and semantic information at scale. Recent advances in deep learning, transformers, self-supervised learning, foundation models, and vision-language models are creating new opportunities to move beyond single-sensor analysis towards integrated multimodal geospatial intelligence.

Multimodal artificial intelligence (MAI) is important because no single sensing modality can fully capture the complexity of natural and built environments. Combining and using various data from complementary sources becomes essential for researchers and practitioners to improve robustness to cloud cover, illumination changes, sparse observations, sensor noise, and domain shifts, while supporting a more complete understanding of three-dimensional structure and environmental dynamics. However, effective MAI and especially multimodal learning remain challenging because geospatial datasets differ in resolution, geometry, acquisition time, coordinate systems, and data availability. Progress in alignment, fusion, representation learning, uncertainty estimation, and generalisation can enable more reliable Earth observation and support such applications as environmental monitoring, urban mapping, agriculture, forestry, infrastructure assessment, disaster management, and change detection.

This Article Collection welcomes original research and review articles on MAI for remote sensing and geospatial intelligence. Topics include:

• Multimodal and cross-modal learning;
• Fusion of optical, hyperspectral, SAR, LiDAR, UAV, GIS and other geospatial data;
• AI for LiDAR and 3D point cloud understanding;
• Semantic segmentation, object detection, classification and change detection;
• Spatial temporal learning;
• Self-supervised/weakly-supervised/few-shot learning;
• Open-world-learning;
• Transformers, foundation models, vision-language models and generative AI;
• Domain adaptation and generalisation;
• Explainable, trustworthy and uncertainty-aware AI;
• Efficient learning for large-scale geospatial data;
• Multimodal benchmark datasets and evaluation protocols;
• Innovative applications in Earth observation, geoscience and environmental analysis.

Meet the Guest Advisors

Dr. Dongxu Gao is a Senior Lecturer in the School of Computing, Mathematics & Physics at the University of Portsmouth. His research interests include artificial intelligence, deep learning, computer vision, multimodal learning, and 3D point cloud understanding, with applications in medical imaging, robotics and geospatial analysis. He has published research in Geocarto International and has experience in funded research projects and academic editorial activities.

Dr. Qing Gao is an Associate Professor at the School of Electronics and Communication Engineering, Sun Yat-sen University, China. His research interests include artificial intelligence, computer vision, robotics, human–robot interaction, and intelligent perception. He has published extensively in the areas of deep learning, visual perception, and intelligent systems. He has also served in editorial roles for international journals and conferences.

Prof. MengChu Zhou is a Distinguished Professor of Electrical and Computer Engineering at the New Jersey Institute of Technology (NJIT), USA. He is the founding Editor of the IEEE Press Book Series on Systems Science and Engineering and Editor-in-Chief of the IEEE/CAA Journal of Automatica Sinica. He currently serves as Vice President for Conferences and Meetings of the IEEE Systems, Man, and Cybernetics Society and is a Fellow of IEEE, IFAC, AAAS, and CAA.

The Guest Advisors declare no conflict of interest regarding this work.