Soyoma provides freelance consulting that combines GIS, satellite imagery, computer vision, and AI‑generated synthetic data to create decision‑ready maps, datasets, and automated workflows for municipal energy planning. The service extracts building‑level attributes, estimates heat demand, and evaluates rooftop solar potential at city scale, delivering outputs in standard GIS formats that can be directly integrated into planning tools and dashboards.
Funding
Funding not disclosed
Founders
Product
Problem
Municipal planners and energy companies often work with fragmented geospatial datasets, making it difficult to assess building energy demand, rooftop solar potential, and heat planning at city scale. Traditional GIS workflows can be time‑consuming and require specialized expertise, leading to delays in actionable decision‑making.
Solution
Soyoma offers freelance consulting that integrates GIS, satellite imagery, computer vision, and AI‑generated synthetic data to produce decision‑ready maps, datasets, and automated workflows for energy planning. By applying remote sensing and machine‑learning techniques, the service extracts building‑level attributes, estimates heat demand, and evaluates rooftop solar suitability across entire municipalities. The resulting outputs are delivered in standard GIS formats and can be directly incorporated into existing planning tools or municipal dashboards. This approach streamlines data preparation, reduces manual effort, and enables faster, data‑driven energy strategy development.
Target Audience
Primary customers are municipal planning departments, city‑scale energy utilities, and consulting firms that require accurate geospatial intelligence for building energy and solar deployment projects.
Features
- End‑to‑end GIS analysis pipelines that combine QGIS, GeoPandas, and custom Python scripts for spatial data integration
- Satellite‑based computer‑vision models (built with PyTorch) to detect building footprints, roof types, and solar‑friendly surfaces
- AI‑generated synthetic datasets to fill gaps in data‑scarce regions, improving model robustness for heat demand estimation
- Automated generation of ready‑to‑use maps and datasets (e.g., solar rooftop potential, municipal heat demand) in industry‑standard formats
- MLOps‑enabled workflow automation for repeatable, scalable analyses across multiple cities or districts