Nexma GeoEngine
Spatial analysis at the speed of asking
Nexma GeoEngine is AI-native spatial analysis. Ask a question in plain language and Jax becomes your GIS analyst — querying, joining, and analyzing every layer of the physical world, from a file you just uploaded to years of live history, and returning the answer as a map instead of a spreadsheet. There is no query language to learn and no analyst bottleneck to wait on.
Core concepts
Traditional GIS makes a human drive every step — wrangle projections, write the joins, stitch tools together — and the data sits in silos. GeoEngine collapses that into a question.
- Ask in language. Describe the question; Jax composes the SQL and spatial operations, runs them server-side, and explains the result.
- One query across every source. Joins span your uploads, the DataStore world model, live telemetry, and deep historical data in a single statement.
- Answers as maps. Results land as live, styled map layers with automatic statistics — ready to act on inside your project, never a static export.
- Typed when it can be. With an Ontology loaded, queries become typed and semantic — by entity, property, and unit. Without one, it works on raw uploads with no setup.
SQL is one of the things GeoEngine runs underneath. The engine is the analyst: it interprets the question, picks the right spatial methods, queries across every source, and returns a styled, sourced map. You only touch SQL if you want to.
How it works
GeoEngine runs a server-side spatial engine that executes the SQL, geometry, and statistics Jax composes. The loop is query, analyze, act.
1You: "Which substations have more than 200 customers within a 10-minute drive,
2 and how has that changed over the last year?"
3 1. Query Jax writes SQL across the world model + live telemetry + history
4 2. Analyze isochrone (10-min drive) → spatial join → aggregate by substation
5 3. Compare difference against the same window one year ago
6 4. Render a styled layer + summary statistics, in your projectEvery layer keeps its sources and method, so results are auditable and reproducible.
Spatial operations
Jax composes the right operations automatically for the question asked — you never name them.
| Category | Operations |
|---|---|
| Geometry | Buffers, spatial joins, nearest, distance matrices, clipping |
| Access | Isochrones and drive-time, reachability along the road network |
| Patterns | Density, clustering, hotspot detection across space and time |
| Aggregation | Roll-ups by geography, attribute, and time window |
| Optimization | Routing, allocation, and coverage handed off to the MathEngine |
Every source, one query
GeoEngine analyzes whatever you bring and whatever the platform already holds — together, in one statement.
- Your uploads. Drop in CSV, Parquet, GeoJSON, or a shapefile and analyze it immediately.
- The world model. Query the typed entities, relationships, and geometry in the DataStore.
- Live telemetry. Join current positions and readings streamed through the Event Broker.
- Deep history. Reach into the historical record behind the DataBase to see how things changed over time.
Join a dataset you dropped in five seconds ago to live telemetry and years of history — in a single question, without moving data between tools.
From question to map
Results are not files to export and email. They become live, styled layers in your project, with automatic color scales and summary statistics that make each answer legible at a glance. Anyone — not just a GIS specialist — can ask a rigorous spatial question and get a sourced answer back as a map, ready for the next decision.
Where to go next
- Jax — the agent that runs the analysis.
- Nexma MathEngine — the optimization GeoEngine hands routing and coverage to.
- DataBase — the time-aware backbone GeoEngine analyzes across history.
- Spatial analysis capability — what GeoEngine enables end to end.