Skip to content
Technology How it works Breeder — Hyperion Burner — Aegis Burner — MetroVolt AI-Native Architecture Magnets Fuel cycle Safety Roadmap
Solutions AI & Data Centers Defense & Government Grid & Baseload Neutron Detection Quantum
Learn Technical Library
Proof Publications Whitepapers Technical Library Open Science & Reproducibility The Honest Gates
Company About / Mission Leadership Environment Health & Safety Investors Careers Press Contact
3D Model
AI Architecture › L2 · Data Fabric
L2 · Data Fabric

Core Pressure Map

The 2-D plasma pressure distribution, reconstructed in flux coordinates from Thomson scattering, interferometry, and magnetics, is the fabric's richest engineered feature.

THE STACK · click to jumpL7Ecosystem & StrategyL6Experience & VisualizationL5Applications & CopilotsL4OrchestrationL3Twin Modeling & AIL2Data FabricL1Control PlaneL0Foundation▲tlmctl▼L2 · DATA FABRICTelemetry, validation, and the machine's memory.160+ Port Telemetrysensor bus2Signal Validationrange & sanity3Feature Engineeringderived signals4Time-Series Archivefull history5Feature Storetraining-ready6Vector DBembeddings for RAGMACHINE TIEIngests from diagnostics; serves the twin (L3) and copilots (L5).KRONOS FUSION ENERGYAI-NATIVE S.M.A.R.T. GENERATORDATA FABRICSHEET 04REV. 2026-08L2 · AI-NATIVE STACK
L2 · Data Fabric — its place in the stack (left, click any layer) and its internal components (right). Telemetry rises; control descends.

What the map is

The core pressure map is the plasma pressure p = n*(T_e+T_i) resolved across the cross-section, expressed in normalized flux coordinates. It is the feature that ties together density, temperature, and equilibrium, and it is what the twin's Power and MHD modules consume to judge stability and performance in the breeder (Hyperion).

The diagnostics that build it

Reconstruction, not interpolation

The map is a constrained inversion: profiles must be consistent with the equilibrium (pressure is a flux function to leading order) and with all measuring diagnostics simultaneously. This is why flux-coordinate normalization comes first. The result is a field that respects physics, so gradients at the negative-triangularity edge (delta -0.30) are physically placed rather than smeared.

Why it matters

Pressure gradient drives both performance and instability. The map feeds the instantaneous Q estimate, the MHD stability check that watches for pressure-driven modes, and the control that maintains the ELM-free negative-triangularity regime. A dropped Thomson channel is imputed over the sensor graph so the map stays continuous, with the imputed region carrying a reduced quality score.

The pressure-map pipeline is validated in simulation and is a design specification for the FOAK machine whose construction begins Q2 2027.

Content reviewed August 2026 · design-and-simulation stage