Hacktoberfest 2026: los issues que los mantenedores marcaron para octubre, abiertos y aptos para principiantes. Explorar issues de Hacktoberfest

[Data Source Proposal]: Farm dams of Western Australia (DPIRD-083)

Abierto
  • ¿Algo no está bien?
#581 0 comentarios 0 reacciones 0 asignados Ver en GitHub

Nadie ha tomado este issue todavía.

Evaluación

Dificultad
5/5
Tiempo estimado
Más de una semana
Aptitud para principiantes
35/100
Tipo de issue
Nueva funcionalidad
Claridad
Bastante claro
Estado de actividad
Activo
Stack tecnológico
python
Área
data

Línea de trabajo

Start with the proposal’s dataset catalogue page and the related issue #580, which contains the imagery review and full list of suspected building footprints. Assess whether the proposed dam polygons can be incorporated into the water theme and the existing building filter, including licensing, data quality, and update considerations. Done means a decision on the proposal and, if accepted, an agreed integration approach.

Escrito por el modelo de indexación a partir del texto del issue.

Descripción

data-sources external
Dataset name

Farm dams of Western Australia (DPIRD-083)

Source URL

https://catalogue.data.wa.gov.au/dataset/farm-dams-of-the-south-west-agricultural-region-of-wa

Your relationship to this data

I publish or maintain it

Overture theme

Base, Buildings

Geographic coverage

Western Australia, concentrated in the South West agricultural region (99% of features are south of 29°S)

What the data would add

175,143 farm dam polygons, which would help Overture in two places:

  1. Base / water. Farm dams in WA are almost entirely missing from the water theme. Of 15,282 buildings found sitting on DPIRD dams, only 289 (1.9%) have their centre inside any polygon in base/water (release 2026-09-23.1).
  2. Buildings. As an input to the existing filter that excludes ML buildings crossing water. About 15,000 Microsoft ML footprints in WA are farm dams mistaken for buildings. A 100-hit imagery review found 99 not buildings. Details and the full list: #580

The dams are small: median 0.24 ha, and 97.6% under 1 ha. Most are too small for 30 m products like DEA Waterbodies to capture, which is the gap this fills.

License

CC-BY-4.0

Other license details

Requested attribution: © State of Western Australia, Department of Primary Industries and Regional Development.

Is this data already in OpenStreetMap?

No

Format, updates, and other details

Format: File Geodatabase, GeoPackage, GeoJSON and Shapefile downloads (SLIP account login), plus anonymous ArcGIS REST, WMS and WFS services, all linked from the catalogue page. Polygons with an objectid and no other attributes.
Updated: As required
Collection method: Deep-learning image segmentation of Vivid 2.0 satellite imagery, mostly captured 2018–2019, with each feature filtered by a second deep-learning classifier. Sites were preselected from the earlier South West farm dams dataset, DEA Waterbodies and Landgate's Medium Scale Topo Water polygons.
Known quality issues: within the South West agricultural region, the metadata estimates about 24,000 farm dams are missing and about 1,800 features are not farm dams. A subset was manually reviewed in QGIS. Some dams have been filled in or built over since the 2018–19 imagery.

Before submitting
  • I searched existing proposals and didn't find this dataset.
  • I understand that submitting a proposal doesn't guarantee Overture will add the data.
Lenguaje dominante
Python
Estrellas
1.2k
Forks
48
Merge medio
56 min
PR fusionados (30 d)
2

Preparar el entorno

Primeros pasos

  1. Lee el issue completo y luego la guía de contribución del proyecto.
  2. Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
  3. Haz un fork del repositorio y trabaja en una rama.
  4. Abre un pull request que haga referencia al número del issue.

Más de OvertureMaps/data

Todos los issues de OvertureMaps/data

Issues similares

Más issues de Python

Recibe los nuevos issues en tu correo

Un resumen breve de issues de GitHub para principiantes.