Description:
This dataset supports the research article "Globally Scalable, QGIS-Integrated Workflow for Solar Photovoltaic System Segmentation and Capacity Estimation: A Case Study in Algeria." It provides geospatial data of segmented solar photovoltaic (PV) systems located in the Piat region of Algeria. The data was generated using a deep learning-based segmentation approach (DeepLabV3+ with a ResNet backbone) and applied through the Deepness plugin integrated into the QGIS environment.
Each identified PV system is represented as a polygon geometry in GeoJSON format, reflecting the segmented outlines of the PV installations. Estimated installed capacities are included, calculated based on a regionally adapted power density factor of 73.5 MWp/km². Additionally, the dataset contains official capacity values reported by operators and the corresponding relative error between the estimated and official values. The dataset is intended for use in renewable energy studies, remote sensing validation, geospatial analysis, and energy infrastructure planning.
Contents:
File: piat_pv.geojson
Contents: Polygon geometries representing the segmented outlines of individual photovoltaic (PV) systems.
Format: GeoJSON
Attributes:
id: Unique identifier for each PV system
layer: Name of the PV system or location (e.g., project name)
area_km2: Surface area in square kilometers
capacity_MWp: Estimated installed capacity in megawatt-peak (MWp) based on area
capacity_official_MWp: Official installed capacity reported by the operator
relative_error_percent: Relative estimation error compared to the official capacity (in %)
Coordinate Reference System (CRS): EPSG:4326 (WGS 84)
Usage License:
The dataset is published under the Creative Commons Attribution 4.0 International (CC BY 4.0) license.Users are free to share and adapt the material provided appropriate credit is given.
Suggested Citation:
Maximilian Kleebauer, Dataset: Piat Solar Photovoltaic Systems, Algeria, 2025, Zenodo, DOI: [10.5281/zenodo.15294535].