GeoAI for Remote Sensing

From Algorithms to Real-World Applications
Erscheinungsjahr 2027
ISBN: 978-0-443-49320-1
Verlag: Elsevier Science & Technology

Buch, Englisch, Format (B × H): 152 mm x 229 mm

GeoAI for Remote Sensing: From Algorithms to Real-World Applications offers a structured, interdisciplinary resource bridging foundational GeoAI concepts with multisensor fusion and domain-specific applications. It targets advanced students, researchers, and professionals seeking scalable, platform-agnostic workflows and reproducible methods for agriculture, climate, hydrology, urbanism, and hazards. The book emphasizes practical pipelines, code, and case studies anchored in real-world problems, with an emphasis on transparency, ethics, and open science. The content is organized into four parts: Foundations and Methods (data ecosystems, cloud platforms, and basic AI techniques), GeoAI Algorithms and Data Analysis (multisensor fusion, transformer architectures, data-driven modeling), Real-World Applications (deforestation, water resources, urban monitoring, health and environment), and Challenges and Future Directions (ethics, governance, and open-source tooling). Each chapter blends theory with hands-on workflows, teaching objectives, practical implementations, and reproducible outputs, including a public companion repository with notebooks and data resources. Readers will gain a cohesive framework for translating GeoAI methods into actionable insights across sectors and scales, from local to global. They will leave equipped to design, evaluate, and deploy GeoAI solutions that support sustainable resource management, resilient infrastructure, and informed decision-making in policy and industry.

Autoren/Hrsg.

Singh, Sartajvir

Sood, Vishakha

Tiwari, Reet Kamal

Vyas, Narayan

Shoshany, Maxim

Fachgebiete

• Geowissenschaften Geologie GIS, Geoinformatik
• Geowissenschaften Geographie | Raumplanung Geodäsie, Kartographie, GIS, Fernerkundung

Inhaltsverzeichnis

Section 1: Core Concepts and Foundational Advances
1. Introduction to GeoAI and Foundations in Remote Sensing
2. Remote Sensing Data Sources in the AI Era: Optical, Hyperspectral, LiDAR, and SAR
3. Google Earth Engine and Cloud Platforms for Scalable GeoAI Applications in Earth Observation
4. XAI in Geospatial Applications: Building Trust and Interpretability in Remote Sensing Models
5. GeoAI for Smart Cities: Urban Analytics, Planning, and Resilience Using Remote Sensing

Section 2: GeoAI Algorithms and Data Analysis
6. IoT-Integrated GeoAI Framework for Monitoring and Predictions Analysis
7. GeoAI-Based Prediction Analysis: Insights from LiDAR 3D Point Clouds
8. GeoAI in Land Use and Land Cover Classification Using Remote Sensing Data
9. Cross-Modal GeoAI Transformer Network for Unified Tree Segmentation from Airborne, Mobile, and Terrestrial LiDAR
10. GeoAI with Machine/Deep Learning for Glacier Ice Volume Estimation
11. Data Fusion in GeoAI: Integrating Multispectral, Hyperspectral, and Multimodal Sources

Section 3: Real-world Applications/Case Studies of GeoAI
12. GeoAI-Based Polarimetric Scattering Signature Development for Sustainable Horticulture Monitoring in India
13. GeoAI-based Deep Learning in Snow Cover Estimation over the Western Himalayas
14. Improved Multimodal GeoAI Framework for Water Stress Detection and Irrigation Advisory with Satellite Observations
15. GeoAI-Driven Landslide Early Warning System for Improved Prediction Accuracy and Timeliness
16. GeoAI for Biomass Estimation and Sustainable Forest Fire Assessment Using Multisensory Remote Sensing
17. GeoAI-Enhanced Air Quality Forecasting in the Himalayas Using Machine Learning and Data Assimilation
18. GeoAI in Health Applications: Mapping Pollution, Disease Outbreaks, and Public Health with Earth Observation Data

Section 4: Challenges, Limitations and Future Directions
19. GeoAI for Integrated Hydrological Modeling: Recent Advances and Future Directions
20. Big Earth Data Challenges: Scalability, Cloud Computing, and Edge AI
21. Ethical, Legal, and Societal Implications of GeoAI in Remote Sensing
22. Open-Source Libraries and Cloud Computing for GeoAI
23. Challenges, Limitations, and Future Directions in GeoAI for achieving Sustainable Development Goals

Über Autor(innen)

Sood, Vishakha
Vishakha Sood is currently working as a Scientist at the Indian Institute of Technology, Ropar, Punjab, under the Women Scientist Scheme (WOS) of the Department of Science and Technology (DST), Government of India. She is also the founder of Aiotronics Automation Pvt. Ltd., supported under the Himachal Pradesh Chief Minister Startup Scheme. She received her Ph.D. in Electronics and Communication Engineering from Chitkara University, Punjab, in 2020. She earned her B.Tech. degree from Himachal Pradesh University in 2008 and her M.Tech. degree in Electronics and Communication Engineering from Punjab Technical University in 2011. She also completed an MBA in Human Resource Management in 2010. She has extensive academic and research experience and has authored research articles in SCI-indexed journals and SCOPUS-indexed book chapters and holds several inventions. Her research interests include satellite sensors, remote sensing, and digital image analysis. She is a Senior Member of IEEE and an active member of professional bodies including the Indian Society of Remote Sensing (ISRS), Indian Society for Technical Education (ISTE), Punjab Science Congress (Punjab Academy of Sciences), IEEE Sensors Council, IEEE Geoscience and Remote Sensing Society, IEEE Women in Engineering, and the European Geosciences Union (EGU).

Vyas, Narayan
Narayan Vyas is an Assistant Professor in the Department of Computer Science and Engineering at Vivekananda Global University, Jaipur, India, where he is actively involved in research and development in computer science. He qualified for the NTA UGC NET & JRF on his first attempt, showcasing his academic excellence. He has published numerous articles in reputed, peer-reviewed national and international Scopus-indexed conferences and journals. Additionally, he has served as a keynote speaker and resource person for several workshops and webinars conducted in India. His research areas include Remote Sensing, the Internet of Things, Machine Learning, Deep Learning, and Computer Vision. He is an IEEE member and an active member of various international and national societies, such as IEEE Young Professionals, the Indian Society of Remote Sensing (ISRS), the IEEE Geosciences and Remote Sensing Society (GRSS), the IEEE Sensors Council, and the International Society of Photogrammetry and Remote Sensing (ISPRS).

Singh, Sartajvir
Dr. Sartajvir Singh is currently serving as Chief Scientific Officer at the Center of Excellence in Socio-Environmental Sustainability for River Sand Mining (SENSRS) and Project Director (ICSSR Project) at Indian Institute of Technology Ropar, India. He is a digital image analyst with expertise in remote sensing and earned his PhD in Electronics & Communication Engineering (Outstanding Thesis Awardee, 2018) after completing his M. Tech (Gold Medalist) and B.Tech with Distinction. He is a Registered Indian Patent & Trademark Agent and a DGCA-approved drone operator, with 70+ innovations (35+ patents granted) and 90+ SCI/Scopus-indexed publications. He has secured over four Crore (INR) research funding, received multiple fellowships, held editorial positions, and is an IEEE Senior Member, advancing electronics, image processing, and geospatial intelligence.

Tiwari, Reet Kamal
Dr. Reet Kamal Tiwari received his M.Sc. degree in geology, M.Tech. degree in remote sensing and geographic information systems, and PhD degree in Earth sciences from the Indian Institute of Technology (IIT) Roorkee, India, in 2007, 2009, and 2015, respectively. In 2013, he joined the Centre for Glaciology, Wadia Institute of Himalayan Geology, India, as a scientist. Since March 2017, he has been an assistant professor with the Department of Civil Engineering, Indian Institute of Technology (IIT) Ropar, India. His research interests include geospatial technology applications in the fields of snow, ice and glaciers, climate change, natural resource management, environmental monitoring, and planetary sciences. He has secured over 15 Crore (INR) research funding, received multiple fellowships, held editorial positions, and is an IEEE Senior Member, advancing electronics, image processing, and geospatial intelligence. He is Senior IEEE member and an active member of various international and national societies, such as Indian Society of Remote Sensing (ISRS), IEEE Geosciences and Remote Sensing Society (GRSS), and the International Society of Photogrammetry and Remote Sensing (ISPRS).

Shoshany, Maxim
Maxim Shoshany is a distinguished geoinformation scientist at Technion Israel Institute of Technology. His research centers on Mediterranean and semi-arid environments, employing radar and multi-temporal optical data to study life-form compositions, soil–rock patterns, and their evolution across climatic gradients. He led Bar-Ilan University’s Geography Department (1997–2001), served as Academic Director of Technion International, and directed the Eco-Engineering Centre. He has been a visiting professor at King’s College London and Banaras Hindu University, contributing to remote sensing theory, methods, and applications throughout his career.