County Intelligence Platform
A database can tell you Terrebonne Parish's flood risk score.
A knowledge graph can tell you why that score alone isn't enough.
Independent Research · Not an official Red Cross application

County Intelligence Platform

3,232 county documents. Every hazard. Every risk index. Queryable with plain English.
3,232
County docs
18
Hazard types
5
Risk indices
All
Counties
Hazards
Indices
Click · Zoom · Drag
· connections

A knowledge graph of every US county — queryable with plain English

Every US county has been encoded into a graph database connecting hazard risks, social vulnerability, economic hardship, health outcomes, and disaster declaration history. Instead of searching spreadsheets, you ask a question and get a synthesized answer grounded in that data.

Layer 1 — Raw data

Source Documents

FEMA NRI, CDC SVI, CDC PLACES, Census ACS, FEMA Disaster Declarations — one structured document per county

Layer 1 — Raw data

Hazard Coverage

18 hazard types per county: wildfire, hurricane, flood, tornado, earthquake, drought, hail, ice storm, strong wind, and more

Layer 2 — Intelligence engine

LightRAG on Railway

Extracts entities and relationships. Builds the graph: county → hazard → risk index → health indicator → declaration history. Running live at explorer.jbf.com

Layer 3 — Query interface

AI Query Layer

Plain English question → graph traversal + vector search → synthesized answer with citations. Any app can call the API.

Try the live app →

The technology stack, layer by layer

01
Document Ingestion
3,232 county profiles loaded into LightRAG

Each county document contains structured data from five federal sources: FEMA National Risk Index (risk scores for 18 hazard types), CDC Social Vulnerability Index, CDC PLACES health outcomes, Census ACS socioeconomic indicators, and FEMA Major Disaster Declaration history. LightRAG ingests these as text and extracts entities and relationships automatically using an LLM.

02
Graph Construction
Entities and relationships extracted and indexed

LightRAG reads each document and extracts named entities (county names, hazard types, index names) and the relationships between them. These become nodes and edges in a graph database. When you see Terrebonne → Hurricane in the graph, that's a stored relationship with associated risk data. "Degree 19" means a county has 19 direct connections — one for each hazard type and risk index it's linked to.

03
Hybrid Retrieval
Graph traversal + vector similarity search combined

When you ask a question, LightRAG runs two searches simultaneously: (1) traverses the graph to find relevant entities and their neighbors, and (2) runs vector similarity search over the raw document chunks. Combining both results is what allows it to answer specific factual questions ("what is Terrebonne Parish's hurricane risk?") and complex comparative questions ("which Louisiana parishes have both high flood risk and low healthcare access?").

04
AI Synthesis
Claude generates grounded answers from retrieved context

The retrieved graph context is passed to Claude with your question. The model synthesizes a natural language answer from the graph data — not from general training knowledge. This is Retrieval Augmented Generation (RAG): the AI is grounded in your specific dataset. Answers include citations back to source counties and federal datasets.

05
API + Spatial RAG
Any app can query the graph — including ArcGIS maps

LightRAG exposes a REST API. Any application can send a natural language question and receive a structured answer. The next evolution is Spatial RAG: connecting this graph to ArcGIS maps so a disaster planner can click a county on a map and ask "what's this county's compounded risk profile?" — answered in seconds by the knowledge graph, displayed directly in the map interface.

Try the live app →