Guest Editor(s)
Dr. Aqil Tariq
Email: at2139@msstate.edu
Affiliation: Mississippi State University, Mississippi, United States
Homepage:
Research Interests: wildfire and vegetation dynamics in temperate and tropical forest ecosystems, agricultural expansion, 3D geoinformation, urban analytics, spatial analysis to examine land use/land cover, geospatial data science, urban planning, crop identification /forest fire/land subsidence using synthetic aperture radar (SAR) and optical satellite imagery, agriculture monitoring, forest monitoring, forest cover dynamics, spatial statistics, multi-criteria algorithms, ecosystem sustainability, hazards risk reduction, statistical analysis and modeling, flash flood, flood prediction, flood forecasting, flood damage assessment, flood warning using machine learning, Python, R and MATLAB
Summary
Natural hazards, such as landslides, floods, avalanches, wildfires, and others, represent a significant global challenge, often resulting in substantial economic losses and human casualties. These hazards impact both developed and developing nations, often with consequences that are underestimated in scale and severity. Consequently, there is an urgent need for comprehensive monitoring frameworks that can effectively predict, assess, and mitigate these hazards. Early and accurate identification of active and impending natural hazards is critical for implementing monitoring systems, early warning mechanisms, hazard susceptibility mapping, and post-event recovery strategies.
Recent advancements in artificial intelligence (AI) and big data analytics have opened new frontiers in natural hazard monitoring. These technologies, enabled by rapid advances in computational capabilities, integrate vast datasets and diverse remote sensing technologies to support more effective hazard analysis. Emerging data sources, including optical, multispectral, synthetic aperture radar (SAR), and LiDAR datasets collected from satellites, UAVs, aircraft, and ground-based platforms, offer unprecedented opportunities to track surface changes and understand the dynamics of natural hazards.
This Special Issue aims to highlight innovative research that integrates AI methodologies with underutilized remote sensing sensors to monitor and manage natural hazards. We invite original research articles and comprehensive reviews that explore advanced AI approaches, geospatial analysis techniques, and the application of state-of-the-art remote sensing technologies. Studies leveraging multi-sensor data to analyze the mechanics, controlling factors, and spatiotemporal evolution of various hazards are particularly encouraged.
Topics of interest for this Special Issue include, but are not limited to:
· Landslide Modeling and Process Understanding: Development of advanced geospatial and AI-based methodologies for investigating submarine landslides, rockslides, slope failures, and post-fire debris flows, with a focus on process-based modeling, uncertainty quantification, and predictive analytics.
· Flood Dynamics and Predictive Modeling: Integration of remote sensing data and AI algorithms to develop robust hydrological and hydraulic models for riverine and flash flood prediction, including data assimilation techniques and spatiotemporal forecasting frameworks.
· Wildfire Modeling and Impact Assessment: AI-driven methodological frameworks for fire detection, spread simulation, and post-fire impact assessment, incorporating machine learning, deep learning architectures, and coupled atmosphere–land surface models.
· Avalanche Susceptibility and Risk Modeling: Development of geospatial and AI-based models for snow and debris avalanche prediction, focusing on terrain analysis, probabilistic modeling, and multi-factor susceptibility assessment.
· Hazard Mitigation and Risk Modeling Frameworks: Advancement of quantitative risk assessment models, multi-criteria decision analysis (MCDA), and resilience frameworks for hazard mitigation, emphasizing scalability, transferability, and policy integration.
· Innovative AI Algorithms for Geospatial Analysis: Design and implementation of novel machine learning and deep learning algorithms (e.g., CNNs, transformers, graph neural networks) for detecting land deformation, hydrological anomalies, and hazard precursors from multi-source geospatial datasets.
· Advanced Remote Sensing Methodologies: Development of new analytical techniques leveraging hyperspectral, multispectral, very high-resolution optical, SAR, and LiDAR data, with emphasis on feature extraction, data fusion, and inversion modeling.
· Multi-Sensor Data Fusion and Integration: Methodological advancements in integrating optical, radar, LiDAR, and UAV-based datasets using data fusion frameworks, ensemble modeling, and hybrid AI approaches for improved hazard detection and monitoring.
· Benchmark Dataset Development and Validation Frameworks: Creation of standardized, high-quality benchmark datasets and validation protocols to support reproducibility, model comparison, and generalization across different hazard types and geographic regions.
· UAV and Emerging Platform Methodologies: Development of scalable frameworks for integrating UAV/UAS, nano-satellite, InSAR, and GBInSAR data into geospatial modeling pipelines, including real-time processing and edge computing approaches.
· Early Warning Systems and Predictive Intelligence: Design of geospatially informed early warning systems incorporating real-time data streams, AI-based forecasting, and decision-support systems, with a focus on operational implementation and uncertainty handling.
We invite the global research community to contribute to this Special Issue, showcasing innovative work at the nexus of natural hazard monitoring, AI, and GIS-based geospatial analysis. By combining cutting-edge research, advanced methodologies, and interdisciplinary expertise, this Special Issue aims to drive progress in the field and foster effective management and mitigation of natural hazards.
Keywords
geospatial artificial intelligence (GeoAI), multi-sensor data fusion, remote sensing analytics, predictive hazard modeling, deep learning algorithms, spatiotemporal analysis, earth observation systems, InSAR and LiDAR integration, climate-driven natural hazards, early warning systems
Login
Register
Submit a Paper
Propose a Special lssue