Send sample site data
Share drone imagery, orthomosaic tiles, as-built CAD, asset lists, or a small representative site area.
Solar digital twin pilots — built on an inspectable facility schema
Start with a sample site. Lock the asset schema and QA rules. Extract panels, inverters, combiner boxes, cable runs, and exceptions into a reviewable geospatial twin — every feature tied to an ID, an attribute set, and a validation state.
For existing imagery or draft asset layers outside this solar workflow, see geospatial annotation and GIS QA services.
Open the live editorScoped pilot
timing confirmed after source and acceptance review
185+ fields
managed attributes across the solar asset schema
QA trail
exceptions, confidence, and reviewer notes kept visible
Sample first
Test one representative site or area before scaling the twin across the portfolio.
Schema & QA locked
Classes, attributes, geometry, confidence, and acceptance rules are fixed before production.
Inspectable handoff
You leave with a site model, a QA log, and a scoped quote for full-site production.
The solar asset schema
The digital twin is not a pretty model — it is a structured asset inventory. Browse the demonstration schema below: pick a category, choose a feature class, and see the exact attributes, geometry, and value sources we capture. Field names and domains remap to your existing GIS or CMMS naming conventions.
Site & Field
Boundaries, fencing, gates, and access drives that frame the site.
PV Array
Panels, racking, and tracker hardware that generate the power.
Collection & Wiring
Combiner boxes, cable, conduit, and trench routing the current.
Power Conversion
Inverters, transformers, and power stations stepping power up.
Monitoring & Data
Weather stations and data acquisition feeding performance models.
Protection & Switching
Switchgear and disconnects that isolate and protect circuits.
PV Panel
PV Array · Polygon feature
12
fields
| Field | Source | Editable |
|---|---|---|
Location location Panel location | user input | |
String Number string_number String the panel belongs to | template default | |
Combiner Box combiner_box_id Associated combiner box identifier | template default | |
Date Cleaned date_cleaned Last cleaning date | user input | |
Owner Funded owner_funded Whether owner-funded | user input | |
SHAPE_Length shape_length Panel perimeter | calculated | — |
SHAPE_Area shape_area Panel area | calculated | — |
Install Status install_status Installation lifecycle ProposedIn DesignApprovedInstalled+1 | template default | |
Notes notes Free-text notes | user input |
Source: derived from a representative utility-scale solar facility schema. It is operational, not illustrative — and every field name, domain, and geometry type can be remapped to your conventions with no proprietary lock-in.
The working environment
The same schema powers the Solar Utility Network Editor — a web-based workspace where panels, inverters, nodes, collection lines, switches, and transformers carry live attributes, connectivity, and validation state over satellite imagery.
Pilot workflow
Great drone hardware hands you 10,000+ images. The value is in turning that capture into a structured, validated twin. Here is how the pilot runs.
Share drone imagery, orthomosaic tiles, as-built CAD, asset lists, or a small representative site area.
Confirm feature classes, IDs, attributes, geometry types, acceptance criteria, review stages, and output format.
Map assets, attach attributes, flag uncertain cases, and reconcile imagery against available records.
Review the sample twin, QA log, exception list, and a scoped quote for full-site production.
Pilot output
The first deliverable proves model quality on real data and defines what it takes to scale across a site or portfolio.
Panel, inverter, and access layers tied to asset IDs
QA log with exceptions, uncertainty, and reviewer notes
Pilot quote for full-site digital twin production
Pilot package
Bring one representative site or asset area. Leave with the schema, the QA approach, and your first production scope.
Implementation stack
We choose the stack around the job: browser maps for decision surfaces, spatial databases for reliable data, Python and GIS libraries for analysis, and annotation tools when imagery needs reviewer-ready labels.
QGIS
GIS Software
ESRI ArcGIS
GIS Platform
PostgreSQL
Database
PostGIS
Spatial Database
AWS
Cloud Platform
Google Cloud
Cloud Platform
DuckDB
Analytics Database
OpenAI
AI Platform
Claude AI
AI Assistant
CVAT
Annotation Tool
Python
Programming
React
Frontend
Node.js
Backend
Docker
Containerization
Kubernetes
Orchestration
Azure
Cloud Platform
TensorFlow
Machine Learning
Pandas
Data Analysis
NumPy
Scientific Computing
Jupyter
Data Science
Git
Version Control
Linux
Operating System
Ubuntu
Operating System
Mapbox
Mapping Platform
Leaflet
Web Mapping
Fastapi
API Framework
GeoPandas
Geospatial Analysis
GDAL
Geospatial Library