- By:
- Clark, Cecilia N; Sica, Francescopaolo; Hughes, David C; McCarthy, Matthew J; Pacifici, Fabio
- Page Number:
- 9-38
- Book Title:
- GeoAI for Earth Observation Imagery: Fundamentals and Practical Applications
- Publication Date:
- June 23, 2026
- Publisher Location:
- Elsevier, Cambridge, Massachusetts, United States of America
- View DOI Listing:
- https://doi.org/10.1016/B978-0-44-343796-0.00008-5
Abstract
This chapter gives a thorough overview of radiometric correction techniques for optical, synthetic aperture radar, and thermal remote sensing data, emphasizing their role in supporting accurate and AI-ready geospatial analysis. The chapter begins by presenting the physical principles of electromagnetic radiation and subsequent interaction with the atmosphere. Topics covered include scattering, absorption, path radiance, and the relationship between radiance, reflectance, and emissivity. Empirical and physics-based correction methods are introduced, as well as radiative transfer models, such as those implemented through Py6S (which is a python interface to the second simulation of the satellite signal in the solar spectrum – 6S). Hybrid approaches and machine-learning techniques are also discussed. Radiometric correction for SAR data is defined separately, focusing on backscatter normalization and modality-specific considerations. Application examples demonstrate correction workflows for both optical and SAR imagery. The chapter concludes with best practices and existing challenges, emphasizing the importance of standardized and physically grounded preprocessing in modern GeoAI pipelines.
