// EDGION LTD · UK COMPANY 17095794

AI weather intelligence. built for real decisions.

// weather intelligence · climate risk · decision systems

// UK-registered technology company · Reading

> scroll to read
// THE METHOD · ENGAGED

we model uncertainty.
you make the call.

// the first question ends. the model can be re-run.

// new data comes in. the decision can be tested again.

geo N51°30'26" W00°07'40"
wind 12kt @ 240°
vis 3.2km · ceil 230m
press 1014 hPa · rising
link edgion · reading · · 42ms
[ MACHINE READY ] edgion@reading:~ > explore the work
// 01 · COMPANY

registered //
and building.

// Edgion Ltd is an active UK private limited company.

// company identity, products, and contact details are available here.

company Edgion Ltd · Company number 17095794 · incorporated 16 March 2026.
office Davidson House, The Forbury, Reading RG1 3EU, United Kingdom.
focus AI weather intelligence, climate risk modelling, and model-driven decision systems.
founder Founded and led by Dr Yue Zheng, director and person with significant control.
read the company profile
// 02 · WHAT WE BUILD

the machine //
for your decision.

// we work across domains.

// what stays constant is the engine.

Climate Atlas
Climate hazard product work that turns 3 km PGW typhoon simulation data into report structures, hazard cards, and decision-ready workflows.
Weather Edge
Forecast-revision intelligence for weather-sensitive operators and planning teams, built around model updates, uncertainty ranges, and timing signals.
Climate Futures
Research-backed climate scenario workflows for places, assets, and extreme events where the assumptions need to be explicit and repeatable.
Decision Systems
Reusable risk engines, scoring systems, and model-driven decision pipelines. The infrastructure you own and operate.
// 03 · METHOD

three rules //
we never break.

// three practices that make the work repeatable.

// all of them load-bearing.

RULE.001

engineer‑built.

the work is built as a runnable system.

pipelines, models, and platforms can be examined and repeated.

re-run it whenever the question comes back.

RULE.002

calibrated.

every output ships with its confidence bounds.

a narrow interval: act. a wide one: gather more data first.

the uncertainty is the information.

RULE.003

first‑principles.

we derive models from physics and economics.

every assumption is explicit and auditable.

built to work where the data runs out.

// 04 · EVIDENCE

two examples //
of the build pattern.

// representative build examples.

// examples from the current product work.

EXAMPLE.001 · CLIMATE ATLAS

How does a future typhoon scenario become a usable design brief?

Built: 3 km PGW typhoon simulations linked to report sections, structured hazard cards, and methodology notes.
→ climate hazard workflow for infrastructure and engineering decisions.
EXAMPLE.002 · WEATHER EDGE

When a forecast changes before delivery, how much decision value is carried by the revision itself?

Built: research pipeline comparing consecutive AI and numerical-weather model updates for the same delivery window.
→ forecast-to-decision workflow for weather-linked planning.
// 05 · START

tell us //
the decision.

// we read every company and product brief directly.

officeDavidson House, The Forbury, Reading RG1 3EU, United Kingdom