Time Series & Scientific AI

Pretrained foundation models for time-series forecasting.

Probabilistic time series modeling with deep learning. Powers Amazon SageMaker forecasting with PyTorch and MXNet backends. Apache 2.0 licensed.

Automated time series forecasting with broad model selection, ensembling, anomaly detection, and holiday effects. Designed for production deployment with minimal setup.

Pretrained decoder-only foundation model developed by Google Research for time-series forecasting, supporting up to 16k context length, covariate support, and Flax / PyTorch backends. Apache 2.0 licensed.