Collaborative Research: NSF R2I2: Managing Invasive Caribbean Pine to Reduce Wildfire Risk in Puerto Rico

The U.S. Caribbean is becoming hotter and drier, and the spread of invasive Caribbean pine (Pinus caribaea) is amplifying wildfire danger, displacing native forests, and increasing hurricane damage. Partnering with local agencies and communities, this project will create the first high-resolution maps of pine invasion and burn scars, predict future risks, and package the results in user-friendly applications for Puerto Rico. The team will also engage with the community and citizen scientists, providing hands-on training in remote sensing and artificial intelligence (AI). Together, these efforts will launch a Regional Resilience Innovation Incubator that supports land managers, policymakers, and landowners in identifying mitigation resources, reducing wildfire risk, and protecting ecosystems, while expanding Science, Technology, Engineering, and Mathematics (STEM) skills and workforce capacity across Puerto Rico and other fire-prone island regions. The project tackles three related knowledge gaps: 1) fine-scale detection of invasive pine trees in rugged subtropical terrain; 2) mapping low-intensity fires that existing satellite fire products often miss; and 3) forecasting coupled vegetation–disturbance dynamics under future scenarios. Using very-high-resolution drone and satellite imagery, the project will deploy state-of-the-art AI models to locate individual Caribbean pine crowns and delineate burn scars, validating results with field plots and community photo transects. The resulting maps will feed spatially explicit machine learning models to forecast pine spread and fire risk. Phase 1 refines the methods in Maricao State Forest, a priority landscape with high wildfire exposure; Phase 2 would scale the workflow island-wide. Expected outcomes include multi-temporal invasion and burn maps, risk forecasts, and peer-reviewed algorithms that boost early-warning capacity and can be adopted across the Caribbean and other fire-prone island regions. This project advances Earth system science, applied ecology, and hazard-risk modeling, while filling key data gaps for island systems. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.