AI Foundationspredict · compress · act

concepts → Model

Model

Neural weather model

frontieras of 2026-094 connections

a learned forecast that distils decades of physics-based weather simulation

Where it sits

The prism has six jobs across and eight layers down. Its primary cell is no mode × L1. Hatched cells cannot exist — a GPU does not learn, an institution does not infer.

Runs at: datacenter. Evidence: benchmark.

What must come first — and what it unlocks

Left to right is reading order, derived from the prerequisite_of edges. Nothing here is hand-ordered: the diagram is the graph.

nothing comes first — this is a starting pointNeural weather modelnothing depends on it yet — a leaf in the reading order

What kind of thing it is — and what it is made of

Examples of it: GraphCast, GenCast.

Where to read it

The chapter that introduces it, and any chapter that uses it again.

64Simulating the Worldact XIV · AI for Science

Where it comes from

paperLearning Skillful Medium-Range Global Weather ForecastingLam et al., Google DeepMind · 2023
paperProbabilistic Weather Forecasting with Machine LearningPrice et al., Google DeepMind · 2024

Every connection

All 4 edges touching this node, grouped by relation family — the sections above are highlights from this list. Colours match the relation families inthe atlas.

Structure · 3
is an instance ofSurrogate modelMechanism
has as an instanceGraphCastSystem
has as an instanceGenCastSystem
Flow · 1
usesGraph neural networkArchitecture

This page is a projection of one node in src/data/concepts.ts. It has no prose file of its own — 521 declared edges produce all 340 of these pages. Edit an edge and both endpoints change.