Explainable AI for Earth Observation Data Analysis

Applications, Opportunities, and Challenges
Herausgeber: Pv, Arun; Mohan, B Krishna; Chanussot, Jocelyn

• Gebundenes Buch

Produktbeschreibung

This book discusses the various advancements in Explainable AI and investigates their suitability for various EO data analyses offering best practices for implementing algorithms that facilitate big and efficient data processing. It lays the foundation of Explainable EO and helps readers build trustworthy, secure, and robust EO systems.

Produktdetails

• Verlag: CRC Press
• Seitenzahl: 300
• Erscheinungstermin: 4. November 2025
• Englisch
• Abmessung: 240mm x 161mm x 21mm
• Gewicht: 617g
• ISBN-13: 9781032980966
• ISBN-10: 1032980966
• Artikelnr.: 74264719

Autorenporträt

Arun PV is Assistant Professor at Indian Institute of Information Technology, Sricity, Chittoor, India. He leads the spatial data analytics and machine intelligence group. He has a PhD from IIT Bombay and has expertise in deep learning and remote sensing data analytics. He has over 15 years of research experience and has published over 70 publications in international journals and conference proceedings. Jocelyn Chanussot is Professor of Signal and Image Processing at the Grenoble Institute of Technology in Grenoble, France. Chanussot was nominated as a Fellow of the Institute of Electrical and Electronics Engineers (IEEE) in 2012 for his contributions to data fusion and image processing for remote sensing where he currently serves as an Editor-in-Chief B Krishna Mohan is Professor at the Indian Institute of Technology, Bombay, India. From 2016 to 2019 he was the Head of the Centre and Institute's Chair Professor. He has authored over 150 publications in journals, book chapters, and conference proceedings. He also has led over 45 national and international sponsored projects. Prof. Mohan is the recipient of the Indian Society of Remote Sensing National Geospatial Award for Excellence in 2012. D. Nagesh Kumar has been Professor in the Department of Civil Engineering, at the Indian Institute of Science, Bangalore, India since May 2002. He is a Fellow of the Indian Academy of Sciences, Bangalore. He is the co-author of 8 books and has published more than 220 papers including 131 in peer reviewed journals. He is the Editor-in-Chief of a journal on climate change and water and the Associate Editor for a journal on Hydraulic Engineering. Alok Porwal is Professor at the Indian Institute of Technology, Bombay, India. He specializes in Earth Observation data processing and analysis. From 2021-2024 he was the Head of the Centre and the Institute Chair Professor. He is currently an Editor of an academic journal and has authored over 200 publications in journals, book chapters, and conference proceedings. He has also led over 20 national and international sponsored projects. He is the recipient of SP Sukhatme Award for Excellence.

Inhaltsangabe

1. Towards Explainable Geospatial AI. 2. Explainable AI Methods: Challenges
and Opportunities for EO Data Analysis. 3. Explainable EO Data
Pre-processing: Challenges and Way Forward. 4. Explainable Feature
Engineering for EO Data Analysis. 5. Towards Explainable Discriminative
Models for EO Data Analysis. 6. Towards Explainable Generative Models for
EO Data Analysis. 7. Earth Observation Data Analytics: Explainable AI (XAI)
Strategies. 8. Towards Correlating Deep Learning Models with Physics-based
Models. 9. Explainable Ante-hoc Approaches for EO Data Analysis:
Opportunities and Challenges. 10. Explainable Post-hoc Approaches for EO
Data Analysis: Opportunities and Challenges. 11. Online Learning Strategies
for Explainability. 12. Explainability based Evaluation Metrics. 13.
Benchmark Datasets for EO Data Explainability. 14. Applications and Case
Studies of Explainable EO Data Analysis. 15. Future Trends in Explainable
AI for Geospatial Applications.