Includes contributions by international experts in remote sensing and artificial intelligence.

Includes bibliographical references and index.

Part I. Introduction to multi-sensor data and artificial intelligence -- Deep learning for multi-sensor Earth observation: introductory notes -- A basic introduction to deep learning -- Part II. Artificial intelligence for sensor-specific data analysis and fusion -- Deep learning processing of remotely sensed multispectral images -- Deep learning and hyperspectral images -- Synthetic aperture radar image analysis in era of deep learning -- Deep learning with LiDAR for Earth observation -- Several sensors and modalities -- Part III. Advanced concepts and architectures -- Self-supervised learning for multimodal Earth observation data -- Vision transformers and multi-sensor Earth observation -- Graph neural networks for multi-sensor Earth observation -- Uncertainty quantification in deep neural networks for multi-sensor Earth observation -- Part IV. Multi-sensor deep learning applications -- Multi-sensor deep learning for change detection -- Multi-sensor deep learning for glacier mapping -- Deep learning in multi-sensor agriculture and crop management -- Miscellaneous applications of deep learning-based multi-sensor Earth observation -- Multi-sensor Earth observation: outlook.

The book Deep Learning for Multi-Sensor Earth Observation presents state-of-the-art methods for integrating deep learning with multisensor remote sensing data. Covering multispectral, hyperspectral, SAR, and LiDAR imagery, it explains modern AI techniques—including self-supervised learning, vision transformers, graph neural networks, and uncertainty quantification—and demonstrates their application in change detection, glacier mapping, agriculture, and environmental monitoring. The book serves as a comprehensive reference for researchers, graduate students, and professionals in Earth observation and geospatial artificial intelligence.