AI and Multi-Source Geospatial Observation for Global Change, Ecological Sustainability and Land System Science

Dear Colleagues,

In recent decades, the rapid advancement of geospatial observation technologies—including hyperspectral remote sensing, SAR, GNSS-R, UAV-based sensing, and satellite constellations—has led to an exponential growth in geospatial data. These massive, multi-source, and multi-temporal datasets offer unprecedented opportunities to understand global environmental change, ecological sustainability, and land system dynamics. However, they also present significant challenges in terms of data integration, processing efficiency, and knowledge extraction. The emergence of Artificial Intelligence (AI), particularly geospatial AI approaches such as transformer networks, self-supervised learning, and spatiotemporal deep learning, has fundamentally transformed how we model and analyze complex Earth system processes. The integration of multi-source geospatial big data and cutting-edge AI techniques allows for deeper insights and more accurate predictions of ecological security, ecosystem services, and human–nature interactions. This Topic invites original research and review articles that leverage AI and multi-source geospatial big data to address pressing issues related to global environmental change, ecological security patterns, ecosystem services, land use conflicts, and sustainable development. We encourage submissions that operate across local, regional, and global scales, with a particular interest in studies that utilize long-term observations and high-resolution data. Research focusing on ecological security assessment, ecosystem service flow, land system simulation, and human–environment system coordination is especially welcome.

Topics of interest include, but are not limited to, the following:

• Multi-source geospatial big data fusion, assimilation, and mining (e.g., satellite constellations, SAR, hyperspectral, and IoT sensor networks);
• Development of novel AI algorithms and architectures for spatial-temporal prediction, anomaly detection, and pattern recognition;
• Retrieval and validation of essential environmental variables (e.g., evapotranspiration, carbon flux, urban heat island effect);
• Identification, optimization, and simulation of ecological security patterns at various scales;
• Quantification and mapping of ecosystem services (e.g., water retention, soil conservation, carbon sequestration, habitat quality);
• Monitoring and assessment of land use conflicts and human–nature interactions;
• Downscaling, super-resolution, and enhancement techniques for generated products;
• Automated information extraction (e.g., object detection, change tracking, semantic segmentation, and scene understanding);
• Disaster management and risk assessment (e.g., typhoons, heatwaves, glacial lake outbursts, coastal erosion, and forest degradation);
• Agricultural informatics (e.g., crop health monitoring, irrigation optimization, and food security forecasting);
• Urban sustainability (e.g., smart city analytics, green infrastructure, thermal environment mapping, and population mobility analysis);
• Applications supporting SDGs (e.g., renewable energy planning, water resource management, pollution control, and biodiversity conservation);
• Construction and evaluation of ecological networks based on multi-source remote sensing;
• Land system modeling and simulation under climate change scenarios;

Analysis of ecosystem service trade-offs and synergies across spatial and temporal scales.

Dr. Min Huang
Dr. Daoye Zhu
Prof. Dr. Nengcheng Chen
Dr. Tengping Jiang
Prof. Dr. Orhan Altan
Topic Editors