Caraballo‐Vega et al. (2025) Optical imagery and digital spaces in the era of machine learning for better geospatial information and services

Identification

• Journal: Elsevier eBooks
• Year: 2025
• Date: 2025-11-28
• Authors: Jordan A. Caraballo‐Vega, Mariana Blanco-Rojas, Paul Montesano, Mark Carroll, Matthew Frost, Andrew Burke, Caleb S. Spradlin, Jian Li, R.L. Gill, Margaret Wooten, C. S. R. Neigh, W.G. Alemu
• DOI: 10.1016/b978-0-443-29216-3.00008-4

Research Groups

• Data Science Group, Computational and Information Science and Technology Office, NASA Goddard Space Flight Center, Greenbelt, MD, United States
• Biospheric Sciences Laboratory, NASA Goddard Space Flight Center, Greenbelt, MD, United States

Short Summary

This chapter introduces the challenges and opportunities presented by the vast amount of Earth observation satellite data, emphasizing the critical role of machine learning methods for accurate processing and analysis to generate geospatial information and services. It highlights the need for guidance in selecting appropriate methods for remote sensing applications.

Objective

• To address the increasing need for developing accurate techniques for processing and analyzing remotely sensed imagery, particularly by providing guidance on choosing appropriate machine learning methods given the proliferation of data and rapid evolution of processing techniques.

Study Configuration

• Spatial Scale: Applications cover local to global scales, leveraging Earth observation satellites.
• Temporal Scale: Not specified for a particular study, but the context covers applications benefiting from increasing temporal resolution of satellite imagery.

Methodology and Data

• Models used: Machine learning methods (general discussion; specific models not detailed in this introductory section).
• Data sources: Earth observation satellites, remotely sensed imagery.

Main Results

• Not applicable; this text is an introductory section of a chapter and does not present specific study results. It sets the context for the subsequent content of the chapter.

Contributions

• Identifies the critical need for proper guidance in selecting and applying machine learning methods for the accurate processing and analysis of the growing volume of Earth observation satellite data.
• Emphasizes the importance of advanced techniques for generating updated land use/land cover maps and other geospatial information and services.

Funding

• Not specified in the provided text.

Citation

@article{CaraballoVega2025Optical,
  author = {Caraballo‐Vega, Jordan A. and Blanco-Rojas, Mariana and Montesano, Paul and Carroll, Mark and Frost, Matthew and Burke, Andrew and Spradlin, Caleb S. and Li, Jian and Gill, R.L. and Wooten, Margaret and Neigh, C. S. R. and Alemu, W.G.},
  title = {Optical imagery and digital spaces in the era of machine learning for better geospatial information and services},
  journal = {Elsevier eBooks},
  year = {2025},
  doi = {10.1016/b978-0-443-29216-3.00008-4},
  url = {https://doi.org/10.1016/b978-0-443-29216-3.00008-4}
}