TimesFM-3Google
|
WeatherNextGoogle DeepMind
|
|||||
Related Products
|
||||||
About
TimesFM-3 is a state-of-the-art time series foundation model designed for highly accurate multivariate forecasting in a single forward pass. The 330 million parameter model is pre-trained on a real-world and synthetic time-series corpus comprising more than 1 trillion time points, building on the efficiency and zero-shot generalization of earlier TimesFM models. It can jointly predict multiple coevolving time series and capture dependencies that improve accuracy without task-specific fine-tuning. The model supports multiple targets with point and quantile forecasts, past covariates that are known only historically, and past-future dynamic covariates such as planned promotions, holidays, or weather forecasts. TimesFM-3 uses a decoder-only transformer architecture, processes contiguous data in patches of 32 time steps, and applies alternating causal temporal attention and full variate attention to combine patterns across time and related series.
|
About
WeatherNext is a family of AI models from Google DeepMind and Google Research that produces state-of-the-art weather forecasts. These models are faster and more efficient than traditional physics-based weather models and yield superior forecast reliability. The gains in forecast performance could enable better preparation to help save lives in the face of extreme weather events and enhance the reliability of sustainable energy and supply chains. WeatherNext Graph offers more accurate and efficient deterministic forecasts compared to the best deterministic systems in use today, providing a single weather forecast per time and location with a temporal resolution of 6 hours and a lead time of 10 days. WeatherNext Gen accurately generates an ensemble forecast, better than the current ensemble models most widely used today, helping decision-makers better understand weather uncertainties and risks of extreme conditions.
|
|||||
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
Platforms Supported
Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook
|
|||||
Audience
Data scientists, researchers, and developers wanting to forecast multiple related time series and incorporate historical and known future signals
|
Audience
Meteorologists and climate researchers searching for a tool to enhance disaster preparedness and sustainability planning
|
|||||
Support
Phone Support
24/7 Live Support
Online
|
Support
Phone Support
24/7 Live Support
Online
|
|||||
API
Offers API
|
API
Offers API
|
|||||
Screenshots and Videos |
Screenshots and Videos |
|||||
Pricing
No information available.
Free Version
Free Trial
|
Pricing
No information available.
Free Version
Free Trial
|
|||||
Reviews/
|
Reviews/
|
|||||
Training
Documentation
Webinars
Live Online
In Person
|
Training
Documentation
Webinars
Live Online
In Person
|
|||||
Company InformationGoogle
Founded: 1998
United States
research.google/blog/timesfm-3-a-zero-shot-foundation-model-for-multivariate-forecasting/
|
Company InformationGoogle DeepMind
Founded: 2010
United Kingdom
deepmind.google/science/weathernext/
|
|||||
Alternatives |
Alternatives |
|||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
Categories |
Categories |
|||||
Integrations
AlphaCode
AlphaEvolve
AlphaFold
Chinchilla
Gemini
Gemini Deep Research
Gemini Diffusion
Gemini Enterprise
Gemini Enterprise Agent Platform
Gemini Robotics
|
Integrations
AlphaCode
AlphaEvolve
AlphaFold
Chinchilla
Gemini
Gemini Deep Research
Gemini Diffusion
Gemini Enterprise
Gemini Enterprise Agent Platform
Gemini Robotics
|
|||||
|
|
|