Resonant Nuclear

The software layer between
every neutron and its target

40,000 medical procedures happen in the US every day that depend on isotopes we can barely produce. The reactors that make them are aging. The waitlists are growing. And every facility on Earth wastes >95% of its neutrons at the wrong energy — because nobody has designed the spectrum.

Until now.

The Physics

A neutron at the right energy is worth ten thousand at the wrong one

Each target isotope captures neutrons only at specific, narrow energy windows — resonance peaks dictated by quantum mechanics. At these peaks, capture probability spikes by 10,000× over the baseline. Everywhere else, the neutron passes through as if the target isn't there.

The industry has always answered with brute force: bigger reactor, longer irradiation. The waste ratio stays the same. We took a different approach. We computationally design the neutron energy spectrum itself — a physical filter, AI-optimized, that reshapes the energy distribution to land on the resonances that matter.

R = ∫ N · φ(E) × σ(E) dE
NTarget atoms — fixed by your material
σ(E)Cross-section — fixed by quantum mechanics
φ(E)Neutron energy spectrum — the only variable we can design
5 material classes, 50 possible layers, arbitrary thicknesses — the design space is larger than the number of atoms in the universe. No human can navigate it. Our AI does.
People are dying on waitlists because we can't make isotopes fast enough. The bottleneck isn't reactors. It's physics.
How It Works

From target isotope to optimized filter geometry — in five steps

Where neutrons land today
Wrong energy — 95%
Industry response
Bigger reactor
$1B+
→
More beam
10× cost
→
Same waste
95%

Every facility wastes >95% of its neutrons

Reactors and accelerators produce neutrons across a broad energy spectrum. But each target isotope only reacts at specific, narrow energy windows. The rest? Absorbed, scattered, lost.

The industry's answer has always been brute force: build a bigger source, run it longer. The waste ratio stays the same.

40,000+daily US procedures $0spent designing spectra
Cross-section: Mo-98 → Mo-99
12 eV 39 eV 95 eV conventional Neutron energy (eV) →
Sharp peaks = quantum-mechanical. Dashed line = conventional flux. Almost zero overlap.

Every isotope has a resonance fingerprint

Quantum mechanics dictates that each nucleus absorbs neutrons at very specific energies — cross-section resonances. At these peaks, capture probability spikes by 10,000× or more.

Conventional sources produce a broad, unoptimized spectrum. The peaks and the flux barely touch.

10,000×peak-to-baseline <5%spectral overlap
AI design campaign
TargetMo-99 at 12, 39, 95 eV
↓
Monte Carlo10M+ neutron transport sims
↓
Surrogategeometry → spectrum in 2ms
↓
OptimizerBayesian + evolutionary search

Brute-force the physics, then learn from it

Millions of Monte Carlo simulations on GPU clusters. Each one a different combination of materials, thicknesses, ordering. The neural surrogate learns the nonlinear mapping. What took weeks now takes milliseconds.

Then optimizers search the combinatorial space — converging on designs no human could find by hand.

10M+simulations/campaign 2mssurrogate inference
Optimized filter assembly for Mo-99
SOURCE
Iron14cm
D₂O30cm
PE10cm
Bi3cm
LiF3cm
TARGET
Each material filters at different energies. The ordering and thicknesses are what the AI optimizes.

Not a cylinder. An AI-designed filter.

Iron strips fast neutrons. Heavy water moderates. Polyethylene thermalizes. Bismuth filters gammas. LiF absorbs the thermal tail. The optimizer finds the exact combination — and the output is complex, asymmetric, nothing a human would design by hand.

Additive manufacturing makes it buildable. We ship it to any neutron source on Earth.

5material classes ∞thickness combinations
Before & after: Mo-99 production
1×
Baseline yield
23×
AI-optimized yield
4.8%
Baseline overlap
61%
Optimized overlap
conventional AI-shaped
Gold flux peaks align with blue resonances. Same source — 23× more reactions.

Same source. Same neutrons. 23× more isotope.

The AI-designed filter reshapes the neutron energy spectrum to overlap with the target's cross-section peaks. No new reactor. No bigger beam. Just a physical insert — manufactured via 3D printing and shipped to the facility.

There's a second value axis: by concentrating flux at the target resonances, the filter also reduces unwanted activation of non-target isotopes. Higher yield and higher spectral purity — from the same source, at a fraction of the cost.

23×yield improvement 61%spectral overlap $0new infrastructure
1 / 5
You don't need massive flux
if you use the flux intelligently.
We don't build reactors.
We make every neutron source 10× more productive.

Medical isotopes. Fusion fuel. Semiconductor doping. Defense testing. Wherever neutrons meet target nuclei, the spectrum determines the outcome.

Applications → Get in Touch