Artificial Intelligence and Geomatic Technology
Description
This book presents the peer-reviewed proceedings of the International Conference on Artificial Intelligence and Geomatic Technology (ICAIGT 2026), bringing together contributions from researchers, engineers, and academics working at the intersection of artificial intelligence and geospatial sciences. Artificial Intelligence and Geomatic Technology are rapidly transforming the way environmental systems, natural resources, and spatial phenomena are monitored, analyzed, and managed. By integrating advances in GeoAI, remote sensing, machine learning, and geospatial analytics, researchers and practitioners are developing innovative solutions to address some of the world's most pressing challenges, including climate change, sustainable agriculture, disaster risk management, water scarcity, and smart environmental monitoring.
The book highlights recent advances in spatial machine learning, Earth observation analytics, hyperspectral data fusion, UAV-based monitoring, environmental modeling, and digital twin technologies.
The chapters provide both methodological innovations and real-world applications, with a particular focus on semi-arid and developing regions where geospatial intelligence and AI-driven decision support systems can significantly contribute to sustainable development and environmental resilience.
The book is organized into four thematic sections covering:
GeoAI and spatial machine learning.
Remote sensing and earth observation analytics.
Natural resource management and geospatial intelligence.
Digital twins and smart environment monitoring.
By combining theoretical foundations with practical case studies, this book serves as a valuable resource for researchers, graduate students, engineers, and professionals in artificial intelligence, remote sensing, geomatics, environmental sciences, and smart monitoring systems.
More details
Content
GeoAI and Spatial Machine Learning.- Spatio-Temporal Forecasting of PM2.5 Using Graph Neural Networks and Multi-Variate Transformers.- GeoAI-Based Cross-Sensor Fusion for Cloud-Free PRISMA and EnMAP Hyperspectral Reconstruction.- Flood Susceptibility Mapping Using Unsupervised Learning: A Case Study in Tata, Morocco.- Binary Classification of Forest Fire Images Through Deep Learning.- Machine Learning-Based Lithological Mapping from Sentinel-2 Imagery in the Moroccan High Atlas.- Rockfall and Landslide Susceptibility Mapping Using the Random Forest Model.- Temporal Deep Learning for Land Cover Dynamics: A 1D-CNN Approach.- Theoretical Roadmap for Building an Intelligent Geomorphological Knowledge Base Using LLMs.- Remote Sensing and Earth Observation Analytics.- Advanced Euphorbia resinifera Detection Using UAV Imagery and Deep Learning.- UAV-Based Semantic Segmentation of Plant Species in Mountainous Environments.