GeoAI for Environmental Monitoring, Natural Hazards, Public Health, and Urban Resilience

The field of geospatial artificial intelligence (GeoAI) is rapidly redefining both environmental science and urban studies by leveraging the analytical power of machine learning, deep learning, and advanced spatial analytics. As global challenges such as climate change, urban expansion, and the increasing frequency of natural disasters become more acute, GeoAI combined with next-generation remote sensing provides unprecedented capabilities for extracting actionable insight from massive and diverse data sources, including satellite imagery, UAV platforms, and ground-based sensors. Recent years have seen significant advancements in the processing and interpretation of multisource geospatial data, leading to improved predictive modeling, near real-time environmental monitoring, and deeper understanding of socio-ecological processes in both rural and urban landscapes. Despite this progress, the field remains fragmented, with many studies focused on specific applications, single data modalities, or geographically limited case studies, posing obstacles to synthesis, standardization, and broader impact.



This Research Topic aims to establish a cohesive and scalable framework for employing GeoAI and remote sensing as integrated tools for tackling the most intricate environmental and urban challenges. The key objective is to address the gap between innovative, isolated research outputs and the development of generalizable, reproducible solutions suitable for diverse contexts. The initiative seeks to bridge methodological divides, foster meaningful interdisciplinary collaboration, and guide the co-development of GeoAI protocols that are robust, transparent, and transferable across different geographic, climatic, and socio-economic settings. Essential questions include evaluating the comparative efficacy of emerging AI models, uncovering best practices for multi-source data integration, and exploring pathways for translating geospatial intelligence into practical solutions supporting resilience and sustainable development.



The scope of this Research Topic is oriented towards original research, reviews, case studies, and methodological advances that demonstrate rigorous, reproducible application of GeoAI and remote sensing methodologies addressing environmental and urban system challenges. Submissions are expected to link technical innovation with policy and societal relevance while emphasizing data transparency. To gather further insights in these areas, we welcome articles addressing, but not limited to, the following themes:



Advanced AI and machine learning methods for multi-sensor remote sensing data fusion

Climate change impact modeling on agriculture, soil, water, and coupled human-natural systems

Urban analytics including assessment of heat islands, flood vulnerability, pollution, and public health dynamics

GeoAI-powered disaster risk reduction and early warning systems

Biomass estimation, land degradation, and ecosystem monitoring using remote sensing

Development of open-source tools, geospatial data cubes, and reproducible analytical workflows

Policy-relevant studies and frameworks for climate resilience and adaptation