GeoAI for Earth Observation Imagery

Name: GeoAI for Earth Observation Imagery
Price: 175 USD
Availability: InStock
ISBN: 9780443437960

Fundamentals and Practical Applications

by Dalton Lunga, Ronny Hänsch

1st Edition

Publisher: Elsevier

(0 reviews)

Compare Prices

VitalSourceLifetime Access$175.00 AmazonKindle$140.00 Best PriceeTextShelfPDF$38.00

Book Details

Print ISBN	9780443437960
eText ISBN	9780443437977
Publisher	Elsevier
Publishing Year	2026
Edition	1st Edition
Language	English

GeoAI for Earth Observation Imagery, 1st Edition, presents modern artificial intelligence and machine learning methodologies designed for processing satellite and remote sensing datasets. Edited by Dalton Lunga and Ronny Hänsch, this publication addresses the limitations encountered by conventional processing tools when managing large volumes of Earth observation data.

The volume examines essential image enhancement and preparation approaches needed prior to advanced analytical modeling. Specialized topics explore atmospheric compensation, image deblurring, pansharpening, and satellite image denoising, together with superresolution techniques. Furthermore, concrete case studies demonstrate the practical deployment of geospatial machine learning workflows across real-world observational frameworks.

This work supports post-graduate students, university academics, and specialized researchers across Earth observation, GeoAI, remote sensing technologies, and environmental science. It offers a structured technical reference for professionals aiming to integrate machine learning solutions into complex planetary data systems and ongoing spatial research projects.

Chapter 1: Earth observation and GeoAI through the years: six decades of progress in image analysis
- • 1.1. Motivation and context
- • 1.2. About this book
Chapter 2: Radiometric correction
- • 2.1. Introduction
- • 2.2. Methodology
- • 2.3. State-of-the-art and current developments
- • 2.4. Application example
- • 2.5. Best practices and open issues
- • 2.6. Future implications
Chapter 3: Rectification
- • 3.1. Introduction
- • 3.2. Methodology
- • 3.3. State of the art and current developments
- • 3.4. Application example
- • 3.5. Best practices and open issues
- • 3.6. Future implications
Chapter 4: Georeferencing of remote sensing imagery
- • 4.1. Introduction
- • 4.2. Methodology
- • 4.3. State of the art and current developments
- • 4.4. Application example
- • 4.5. Best practices and open issues
- • 4.6. Future implications
Chapter 5: Image registration
- • 5.1. Introduction
- • 5.2. Methodology
- • 5.3. State-of-the-art and current developments
- • 5.4. Application example
- • 5.5. Best practices and open issues
- • 5.6. Future implications
Chapter 6: Mosaicking remote sensing data
- • 6.1. Introduction
- • 6.2. Methodology
- • 6.3. State of the art and current developments
- • 6.4. Future challenges and opportunities
- • 6.5. A practitioner’s guide to mosaicking
Chapter 7: Pansharpening
- • 7.1. Introduction
- • 7.2. Methodology
- • 7.3. State-of-the-art and current developments
- • 7.4. Application example
- • 7.5. Best practices and open issues
- • 7.6. Future implications
Chapter 8: Superresolution of satellite imagery
- • 8.1. Introduction
- • 8.2. Methodology
- • 8.3. State-of-the-art and current developments
- • 8.4. Application example
- • 8.5. Best practices and open issues
- • 8.6. Future implications
Chapter 9: Earth observation image denoising
- • 9.1. Introduction
- • 9.2. Methodology
- • 9.3. State-of-the-art and current developments
- • 9.4. Application example
- • 9.5. Best practices and open issues
- • 9.6. Future implications
Chapter 10: Semantic segmentation
- • 10.1. Introduction
- • 10.2. Methodology
- • 10.3. State-of-the-art and current developments
- • 10.4. Application example
- • 10.5. Best practices, challenges, future implications
- • 10.6. SpaceNet 8 — copyright and licensing
Chapter 11: Synthesis of Earth observation imagery
- • 11.1. Introduction
- • 11.2. Requirements for remote sensing
- • 11.3. Methodology
- • 11.4. State-of-the-art and current developments
- • 11.5. Application example
- • 11.6. Best practices and open issues
- • 11.7. Future implications
Chapter 12: Geospatial data visualization with Python
- • 12.1. Introduction
- • 12.2. Methodology
- • 12.3. State-of-the-art and current developments
- • 12.4. Application examples
- • 12.5. Best practices and open issues
- • 12.6. Future implications
Chapter 13: Multimodal data fusion
- • 13.1. Introduction
- • 13.2. Methodology
- • 13.3. State-of-the-art and current developments
- • 13.4. Application examples
- • 13.5. Best practices and open issues
- • 13.6. Future implications
Chapter 14: Self-supervised learning
- • 14.1. Introduction
- • 14.2. Methodology
- • 14.3. State-of-the-art and current developments
- • 14.4. Example
- • 14.5. Best practices and open issues
- • 14.6. Future implications
Chapter 15: Object detection
- • 15.1. Introduction
- • 15.2. Methodology
- • 15.3. State-of-the-art and current developments
- • 15.4. Application example
- • 15.5. Best practices and open issues
- • 15.6. Future implications
Chapter 16: Visual question answering
- • 16.1. Introduction
- • 16.2. Datasets
- • 16.3. Methods
- • 16.4. Conclusion
Chapter 17: Geospatial machine learning libraries
- • 17.1. Introduction
- • 17.2. Methodology
- • 17.3. State-of-the-art and current developments
- • 17.4. Application example
- • 17.5. Best practices and open issues
- • 17.6. Future implications
Chapter 18: High-performance computing
- • 18.1. Introduction
- • 18.2. Modern HPC
- • 18.3. Distributed computing
- • 18.4. State-of-the-art and current developments
- • 18.5. GeoAI applications
- • 18.6. Best practices and open issues
- • 18.7. Future implications
Chapter 19: Cloud infrastructure for EO imagery
- • 19.1. Introduction
- • 19.2. Methodology
- • 19.3. State-of-the-art and current developments
- • 19.4. Application examples
- • 19.5. Best practices
- • 19.6. Future implications
- • 19.7. Conclusion