Human health and well-being are tied to ecosystem services—from food and water security to climate regulation and cultural benefits. In response to global initiatives such as UNEP TEEB, IPBES, the SDGs, and the 2050 Vision for Biodiversity, there is a growing need for integrated, data-driven assessments that make nature’s benefits more visible. This session invites interdisciplinary contributions that leverage Geospatial Artificial Intelligence (GeoAI) for advancing biodiversity and ecosystem services research. We welcome studies on: (1) applications of GeoAI to quantify the supply, demand, and flows of ecosystem services using multimodal data sources, including but not limited to remote sensing, citizen science, mobile, and other crowdsourced data; (2) advancements in GeoAI methods (e.g., multimodal learning, foundation models, knowledge-informed machine learning); (3) model-data integration to evaluate and forecast spatio-temporal dynamics and interactions among multiple ecosystem services and biodiversity across scales; and (4) interpretation, quantification, and communication of uncertainties in GeoAI model predictions.
-
● Filling the Gaps: Expert-Informed Multimodal Species Distribution Modeling for Data-Sparse Regions
-
● Mapping Cultural Ecosystem Service Flows from Crowdsourced Imagery: A Zero-Shot Learning Approach with the Vision–Language Model CLIP
-
● Fire and Recreation in the U.S. West: Modeling Impacts of Wildfire and Prescribed Fire on Non-Material Contributions of Nature
-
● GeoAI-Enhanced Decision Support System For Sustainable Natural-Resource Management.
-
● FoundationSoil: A GeoAI Framework for Mapping Soil Organic Carbon Stocks Using Foundation Models and Explainable Machine Learning
-
● Calibrated Multi-Model Ensemble with Dynamic Thresholding and Weighted Box Fusion for Robust Object Detection in Noisy Remote Sensing Datasets
-
● Advancing Scalable Biodiversity Monitoring with Partnerships and Edge Computing: NASA and California’s 30x30 Mission
-
● Toward 30x30: How Effective Is Egypt’s Protected Area Coverage from a GeoAI Perspective?
-
● Machine Learning Estimation of Soil Microbial Diversity Using Remote Sensing Data
-
● Monitoring Forest Loss and Biodiversity in the Context of Large-Scale Land Acquisitions in Ethiopia: Integrating Remote Sensing, Ecological Field Data, and Household Perspectives
-
● Do forest management strategies in the U.S. optimize ecosystem service supply?
-
● MODELING FUTURE PLANT SPECIES OCCURRENCE USING MACHINE LEARNING TRAINED ON PALEO-CLIMATE TRENDS, eDNA, AND POLLEN DATA
-
● SAV Detection Across Diverse Aquatic Systems Using Low-Cost Sonar and AI Image Segmentation
-
● EO4Biodiversity: Applying GeoAI to Improve Habitat Mapping for Biodiversity Net Gain