Like every other field, the field of remote sensing is undergoing one of the most transformative shifts in its history in this era of artificial intelligence (AI). The convergence of massively large volumes of Earth observation (EO) data from multiple sensor systems (spaceborne, airborne), cloud scale computing, and rapid advances in AI has ushered in a new era, in which global natural resources management and environmental processes can be mapped, modeled, monitored, and understood with unprecedented precision, speed, and scale. This research topic welcomes contributions that define, expand, and exemplify this revolution.

Over the past decade, AI has evolved from a promising analytical tool to a foundational engine powering next generation EO science. Deep learning architectures, transformer based models, and emerging EO foundation models (e.g., Prithvi 2.0 from IBM and NASA) now enable automated interpretation of petabyte scale satellite archives, fusion of data from multiple sensors (e.g., spaceborne, airborne), multi-resolution, multi-platform datasets, and discovery of complex spatial–temporal patterns seamlessly cross sensors and platforms by computing on the cloud that were previously inaccessible. These advances are reshaping how scientists monitor agriculture, forests, water resources, urbanization, biodiversity, extreme weather events, disasters, and the Earth system as a whole.

This research topic seeks to capture the breadth and depth of this transformation. Submissions may include, but are not limited to:

1. Foundations of AI in Remote Sensing

• Conceptual and historical perspectives on AI in EO
• Reviews of machine learning, deep learning, and generative AI for geospatial analysis
• Emerging paradigms such as self supervised learning and multimodal EO foundation models

2. Remote Sensing Data Types and AI Workflows

• Applications using optical, thermal, LiDAR, SAR, hyperspectral, and multisensor fusion
• AI for analysis of high resolution commercial imagery, UAV data, and in situ–EO integration
• Cloud native geospatial computing and scalable AI pipelines

3. Algorithms, Architectures, and Models

• Convolutional neural networks, transformers, graph neural networks, and hybrid models
• Foundation models trained on global EO archives
• Physics informed AI and interpretable machine learning for EO science

4. Applications Across Planetary Systems

• Agriculture, food security, and cropping intensity mapping
• Water resources, drought, and hydrological modeling
• Forest monitoring, carbon accounting, and biodiversity assessment
• Urbanization, infrastructure, and disaster response
• Climate extremes, long term environmental change, and global sustainability metrics

5. Computing, Coding, and Reproducibility

• Open source tools, workflows, and benchmark datasets
• Cloud computing platforms (e.g., HPC, GEE, AWS, NASA Cumulus)
• Reproducible AI pipelines and FAIR data principles

6. Vision for the Future

• Opportunities and challenges in scaling AI for global EO
• Ethical, societal, and policy implications of AI driven Earth monitoring
• The path toward real time, planetary scale environmental intelligence

Confirm your expert contribution

The Artificial Intelligence (AI) Revolution in Remote Sensing: A New Era of Earth Observation Science