Advances in Machine Learning and Image Analysis for GeoAI

1st Edition - April 3, 2024
Imprint: Elsevier
Editors: Saurabh Prasad, Jocelyn Chanussot, Jun Li
Language: English
Paperback ISBN:
9 7 8 - 0 - 4 4 3 - 1 9 0 7 7 - 3
eBook ISBN:
9 7 8 - 0 - 4 4 3 - 1 9 0 7 8 - 0

Advances in Machine Learning and Image Analysis for GeoAI presents recent advances in applications and algorithms that are at the intersection of Geospatial imaging and Ar… Read more

Purchase options

World Book Day Celebration!

Save up to 30% on books and eBooks!

Shop now

Institutional subscription on ScienceDirect

Request a sales quote

Advances in Machine Learning and Image Analysis for GeoAI presents recent advances in applications and algorithms that are at the intersection of Geospatial imaging and Artificial Intelligence (GeoAI). The book covers algorithmic advances in geospatial image analysis, sensor fusion across modalities, few-shot open-set recognition, explainable AI for Earth Observations, self-supervised learning, image superresolution, Visual Question Answering, and spectral unmixing, among other topics.
This book offers a comprehensive resource for graduate students, researchers, and practitioners in the area of geospatial image analysis. It provides detailed descriptions of the latest techniques, best practices, and insights essential for implementing deep learning strategies in GeoAI research and applications.

Cover image
Title page
Table of Contents
Copyright
Contributors
Chapter 1: Introduction
Chapter 2: Deep learning for super-resolution in remote sensing
Abstract
2.1. Introduction
2.2. Tasks
2.3. Learning paradigms
2.4. Architecture
2.5. Loss
2.6. Data
2.7. Challenges and future directions
2.8. Conclusions
References
Chapter 3: Few-shot open-set recognition of hyperspectral images
Abstract
3.1. Introduction
3.2. Related works
3.3. Proposed methodology
3.4. Experimental analysis
3.5. Summary and future directions
3.6. Project code
References
Chapter 4: Deep semantic segmentation networks for GeoAI: Impact of design choices on segmentation performance
Abstract
Acknowledgements
4.1. Introduction
4.2. Semantic segmentation models – current state of the art
4.3. Datasets
4.4. Experimental results
4.5. Conclusions
References
Chapter 5: Estimation of class priors for improving classification accuracy during deployment
Abstract
5.1. Introduction
5.2. Estimation of class priors based on decision frequency
5.3. Method and results
5.4. Conclusions
References
Chapter 6: Benchmarking and end-to-end considerations for GeoAI-enabled decision-making
Abstract
Acknowledgements
6.1. Introduction
6.2. Algorithm benchmarking with remote sensing data
6.3. Guidelines and recommendations for application-oriented end-to-end GeoAI benchmarking
6.4. Conclusions
References
Chapter 7: Explainable AI for Earth observation: current methods, open challenges, and opportunities
Abstract
Acknowledgements
7.1. Introduction
7.2. Research methodology
7.3. Explainable artificial intelligence
7.4. Explainable AI in remote sensing
7.5. Discussion and conclusions
References
Chapter 8: Self-supervised contrastive learning for wildfire detection: utility and limitations
Abstract
Acknowledgements
8.1. Introduction
8.2. Overview of the analytic tools for wildfire detection
8.3. Overview of wildfire data
8.4. The self-supervised learning pipeline
8.5. Experimental results
8.6. Conclusions and discussion of future work
References
Chapter 9: Multimodal deep learning for GeoAI
Abstract
9.1. Introduction
9.2. Related technologies
9.3. Conclusion
References
Chapter 10: The power of voting
Abstract
10.1. What is ensemble learning?
10.2. Strength
10.3. Diversity
10.4. Fusion
10.5. Pruning
10.6. Implicit ensembles
10.7. Conclusions
References
Chapter 11: Visual question answering on remote sensing images
Abstract
Acknowledgements
11.1. Introduction
11.2. Datasets
11.3. VQA models for remote sensing
11.4. Conclusions
References
Chapter 12: Spectral unmixing for geospatial image analysis
Abstract
12.1. Introduction
12.2. Spectral–spatial hyperspectral unmixing using nonnegative matrix factorization
12.3. Hierarchical bilinear unmixing
12.4. Experiments and analysis: spectral–spatial unmixing
12.5. Experiments and analysis: deep learning-based unmixing
12.6. Conclusions
References
Chapter 13: Applying GeoAI for effective large-scale wetland monitoring
Abstract
Acknowledgements
13.1. Introduction
13.2. Wetland classification systems
13.3. Wetland classification using remote sensing data and machine learning algorithms
13.4. Large-extent wetland classification using advanced processing and computing tools
13.5. Case studies
13.6. Conclusions
References
Chapter 14: Leveraging ML approaches for scaling climate data in an atmospheric urban digital twin framework
Abstract
Acknowledgements
14.1. Introduction
14.2. Machine learning approaches
14.3. AUDT framework
14.4. Case studies
14.5. Future directions
14.6. Conclusions
References
Index

Saurabh Prasad

Saurabh Prasad (Senior IEEE Member) is an Associate Professor with the Department of Electrical and Computer Engineering, University of Houston, USA, where he directs the Machine Learning and Signal Processing Laboratory. His lab focuses on advancing state-of-the-art in machine learning and signal processing with applications to remote sensing and biomedicine. His work has been recognized by two student research awards during his Ph.D. study, a best student paper award at the 2008 IGARSS conference, top-10% papers at IEEE-ICIP conference, a NASA New Investigator (Early Career) award in 2014, and the junior faculty research excellence award at the University of Houston in 2017. He was the lead book editor on two Springer books on signal processing and machine learning for hyperspectral image analysis.

Affiliations and expertise

Associate Professor, Department of Electrical and Computer Engineering, University of Houston, USA

Jocelyn Chanussot

Jocelyn Chanussot (IEEE Fellow) has been with Grenoble INP since 1999, where he is currently a Professor of signal and image processing. His research interests include image analysis, hyperspectral remote sensing, data fusion, machine learning and artificial intelligence. He has been a visiting scholar at Stanford University (USA), KTH (Sweden) and NUS (Singapore) and is an Adjunct Professor of the University of Iceland. In 2015-2017, he was a visiting professor at the University of California, Los Angeles. He holds the AXA chair in remote sensing and is an Adjunct professor at the Chinese Academy of Sciences, Aerospace Information research Institute, Beijing. Dr. Chanussot is the founding President of IEEE Geoscience and Remote Sensing French chapter for which he which received the 2010 IEEE GRS-S Chapter Excellence Award. He was also the Vice-President of the IEEE Geoscience and Remote Sensing Society, in charge of meetings and symposia; the General Chair of the first IEEE GRSS Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote sensing; Chair and Cochair of the GRS Data Fusion Technical Committee.

Affiliations and expertise

Grenoble Institute of Technology, France

Jun Li

Jun Li (IEEE Fellow) is a Professor with the School of Geography and Planning, Sun Yat-sen University, Guangzhou, China. Since 2013, she has obtained several prestigious funding grants at the national and international level. Her research interests include remotely sensed hyperspectral image analysis, signal processing, supervised/semisupervised learning, and active learning. Dr. Li currently serves as the Editor-in-Chief for the IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

Affiliations and expertise

Sun Yat-sen University, China

Life Sciences

Physical Sciences & Engineering

Social Sciences & Humanities

Health

Advances in Machine Learning and Image Analysis for GeoAI

Purchase options

World Book Day Celebration!

Institutional subscription on ScienceDirect

Saurabh Prasad

Jocelyn Chanussot

Jun Li

Related books