WDC20 / DLWP
No estimate
No hardware requirements for this model
The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- University of Washington,Microsoft Research
- Organisation type
- Academia,Industry
- Country
- United States of America
- Published
- 15 March 2020
- Authors
- Jonathan A. Weyn, Dale R. Durran, Rich Caruana
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Earth science
- Task
- Weather forecasting
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Parameters
- 672.1K
- Training data
- tokens
- Epochs
- 100
Table 1
"we train for a minimum of 100 epochs followed by early stopping conditioned on the validation set loss"
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- Training compute
- 2.4 × 10¹⁸ FLOP
- How it was established
- Hardware
31330000000000 FLOP / GPU/ sec [Tesla V100] * 1 GPU * 72 hours * 3600 sec / hour * 0.3 [assumed utilization] = 2.4362208e+18 FLOP
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- NVIDIA Tesla V100 DGXS 32 GB
- Chips used
- 1
- Wall-clock time
- 72 hours
- Power draw
- 281 W
2–3 days for training on a single NVidia Tesla V100 GPU
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Closed — provider access only
- Model access
- Unreleased
- Training code
- Open source
GPL-3 https://github.com/jweyn/DLWP-CS
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- Improving data-driven global weather prediction using deep convolutional neural networks on a cubed sphere
- Last updated
- 28 November 2025
What the numbers mean
About this model
WDC20 / DLWP was published by University of Washington,Microsoft Research, in the country recorded as United States of America, during March 2020. It comes out of an organisation categorised as academia,Industry.
It works in the domain of Earth science, and is recorded as performing the task of weather forecasting.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
What went into building it
Training it took a computation budget of roughly 2.4 × 10¹⁸ FLOP, on hardware recorded as NVIDIA Tesla V100 DGXS 32 GB. That figure measures what producing the model cost, and has no bearing on how fast it answers.
Answers
WDC20 / DLWP — common questions
WDC20 / DLWP— when was it released?
It was published in March 2020. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
WDC20 / DLWP— what is it used for?
It works in the domain of Earth science, and is recorded as handling the task of weather forecasting. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.
WDC20 / DLWP— how much compute was used to train it?
Training consumed around 2.4 × 10¹⁸ FLOP, on hardware recorded as NVIDIA Tesla V100 DGXS 32 GB. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.
WDC20 / DLWP— what GPU do I need to run it?
None. This is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.
WDC20 / DLWP— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
WDC20 / DLWP— how many parameters does it have?
It has a parameter count of 672.1K. Table 1. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.
WDC20 / DLWP— who created it?
It was published by University of Washington,Microsoft Research, based in United States of America, an organisation categorised as academia,Industry.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.