Cultural ecosystem services (CES) are the nonmaterial benefits people obtain from nature. This tool maps CES flows, the places where people experience these benefits, using geotagged social media imagery. The maps presented here were generated using CLIP, a vision–language AI model that classified approximately 590,000 geotagged Flickr photographs from Florida’s natural and working lands (2014–2019) into 12 CES categories—such as outdoor recreation, wildlife viewing, and landscape aesthetics—while filtering out irrelevant content. By analyzing this multi-year image collection, the tool reveals spatial patterns of CES flows across the state and highlights areas where people most frequently interact with nature.

CES flows are summarized using two complementary metrics:

• Average annual Photo-User-Days (PUDs): total CES-related engagement in an area.
• Average annual PUDs per user: intensity of CES engagement per individual user.

Explore CES patterns at two spatial scales:

• 1-km grid cells, showing fine-resolution CES activity and CES bundles; and
• Census Block Groups (CBGs), which also include population and socioeconomic information.

Click any spatial unit to view a pop-up:

• All units display a CES bundle profile (radial chart).
• CBGs additionally include demographic information to contextualize CES engagement at the community level.

This tool supports researchers, planners, land managers, and the public in understanding how people engage with Florida’s diverse environments. It accompanies our research on AI-enabled CES mapping and will continue to expand as new data and capabilities are added.

Full methodological details are available in our EcoEvoRxiv manuscript: https://doi.org/10.32942/X29S8C

If you use this map or its data products, please cite:

Liao, H.-Y., Zhao, C.*, Koylu, C., Cao, H., Qiu, J., Callaghan, C. T., Song, J., & Shao, W. (2025). Mapping Cultural Ecosystem Service Flows from Social Media Imagery with Vision–Language Models: A Zero-Shot CLIP Framework. EcoEvoRxiv. https://doi.org/10.32942/X29S8C

Hao-Yu Liao, Chang Zhao, Jiayi Song, and Wei Shao. 2025. Mapping Cultural Ecosystem Services Using One-Shot In-Context Learning with Multimodal Large Language Models. In The 33rd ACM International Conference on Advances in Geographic Information Systems (SIGSPATIAL ’25), November 3–6, 2025, Minneapolis, MN, USA. ACM, New York, NY, USA, 4 pages. https://doi.org/10.1145/3748636.3764178