| title | emoji | colorFrom | colorTo | sdk | sdk_version | app_file | pinned | license |
|---|---|---|---|---|---|---|---|---|
TPL |
🌳 |
indigo |
blue |
streamlit |
1.45.1 |
app/app.py |
false |
apache-2.0 |
This repository contains the source code for the LLM Decision-Support Prototype using Trust for Public Land Data which is hosted on Hugging Face.
An interactive conservation decision-support tool that integrates protected areas, conservation finance, climate, biodiversity, and social vulnerability data into a unified exploratory interface. The application combines geospatial visualization with a natural-language chatbot that generates SQL queries over H3-indexed spatial datasets, enabling real-time spatial joins across conservation investments, ballot measures, irrecoverable carbon, species richness, legislative districts, and environmental justice indicators to support rapid analysis of conservation patterns, gaps, and opportunities. Users can explore protected lands, funding flows, and socio-ecological priorities while dynamically intersecting datasets at multiple scales through on-the-fly H3 indexing and model-generated queries. The tool draws on public datasets including Trust for Public Land’s Conservation Almanac and LandVote, the U.S. Climate and Economic Justice Screening Tool (Justice40), and the CDC Social Vulnerability Index, supporting multiple open-weights language models for reproducible, extensible conservation analytics and decision support.
