BigQuery ML now offers a built-in TimesFM univariate time series forecasting model that implements Google Research's open source TimesFM model

## Feature BigQuery ML now offers a built-in [TimesFM univariate time series forecasting model](https://cloud.google.com/bigquery/docs/timesfm-model) that implements Google Research's open source TimesFM model. You can use BigQuery ML's built-in TimesFM model with the [AI.FORECAST function](https://cloud.google.com/bigquery/docs/reference/standard-sql/bigqueryml-syntax-ai-forecast) to perform forecasting without having to create and train your own model. This lets you avoid the need for model management. To try using a TimesFM model with the `AI.FORECAST` function, see [Forecast a time series with a TimesFM univariate model](https://cloud.google.com/bigquery/docs/timesfm-time-series-forecasting-tutorial). This feature is in [preview](https://cloud.google.com/products/#product-launch-stages). ## Feature You can now [create, view, modify, and delete Apache Iceberg resources in BigQuery metastore](https://cloud.google.com/bigquery/docs/bqms-manage-resources). This feature is [generally available](https://cloud.google.com/products#product-launch-stages) (GA). ## Feature You can now [connect BigQuery metastore to Apache Flink](https://cloud.google.com/bigquery/docs/bqms-use-dataproc#connect-bigquery-flink). This feature is [generally available](https://cloud.google.com/products#product-launch-stages) (GA).