# Domain Model

## Project

A project represents a GeoAI investigation. It is not just a folder. It defines the purpose, spatial areas, datasets, analysis runs, and outputs.

Fields:

- id
- name
- description
- region
- status
- created_at
- updated_at

Relationships:

- has many areas
- has many datasets
- has many analysis_runs
- has many exports

## Area

An area is a selected geometry, usually a polygon. It may represent a municipality, manually drawn polygon, bounding box, or uploaded GeoJSON geometry.

Rules:

- Must have valid geometry.
- Must have a calculated area in square meters.
- Must keep original input geometry if uploaded.
- Must be convertible to GeoJSON.

## Dataset

A dataset is any input or derived geospatial artifact.

Dataset types:

- raster
- vector
- reference
- detection_output
- segmentation_output
- mask
- tile_set
- export

Dataset statuses:

- registered
- uploaded
- metadata_extracted
- processed
- failed

## AnalysisRun

Tracks execution of a pipeline.

Analysis types:

- raster_metadata
- raster_clip
- raster_tile
- vector_import
- object_detection
- segmentation
- qaqc
- change_detection
- export

## Detection

A model-detected object. V1 supports bounding boxes converted into geospatial polygons.

Important fields:

- class_name
- confidence
- geometry
- bbox_pixel
- bbox_geo
- source_tile
- model_id

## QualityCheck

A measured comparison between predicted features and reference features.

Core metrics:

- precision
- recall
- f1
- mean_iou
- matched_count
- false_positive_count
- false_negative_count