Notices

Notices required by the training data's licenses

Each training dataset of the Simons models keeps its own license and terms; the data were cleaned, resampled and cut into training windows.

ERA5: Contains modified Copernicus Climate Change Service information 2026. Neither the European Commission nor ECMWF is responsible for any use that may be made of the Copernicus information or data it contains.
CAMS European air-quality forecasts: Contains modified Copernicus Atmosphere Monitoring Service information 2026. Neither the European Commission nor ECMWF is responsible for any use that may be made of the Copernicus information or data it contains.
ECMWF IFS weather forecasts, retrieved through the Open-Meteo archive: Weather data by Open-Meteo.com (https://open-meteo.com/), CC BY 4.0. Based on data and products of the European Centre for Medium-Range Weather Forecasts (ECMWF, https://www.ecmwf.int/), CC BY 4.0.
NASA POWER: Weather data were obtained from the NASA Langley Research Center POWER Project funded through the NASA Earth Science Directorate Applied Science Program.
NCEP/CPC L3 Half Hourly 4km Global Merged IR (GPM_MERGIR): NASA is the source of these data (https://disc.gsfc.nasa.gov/datasets/GPM_MERGIR_1/summary).
National Highways WebTRIS: Contains public sector information licensed under the Open Government Licence v3.0.
NESO Data Portal: Supported by National Energy SO Open Data.
EirGrid: Supported by EirGrid Group Data.
Retrosheet: The information used here was obtained free of charge from and is copyrighted by Retrosheet. Interested parties may contact Retrosheet at "www.retrosheet.org".
WorldTrace: Contains information from WorldTrace (UniTraj), which is made available under the Open Database License (ODbL) 1.0. Map matching uses data © OpenStreetMap contributors. The WorldTrace-derived training data are offered under the ODbL 1.0 in Simons-Pretrain (univariate/worldtrace/).
Banco Central do Brasil Focus survey: Contains information from the Expectativas de Mercado dataset (Focus survey) of Banco Central do Brasil, which is made available under the Open Database License (ODbL) 1.0. Fonte: Banco Central do Brasil, Sistema de Expectativas de Mercado. The derived data are offered under the ODbL 1.0 in Simons-Pretrain (covariates/bcb_focus_inflation/).
opentransportdata.swiss: Source of the raw data: opentransportdata.swiss.
RTE eCO2mix: Data from RTE éCO2mix (https://odre.opendatasoft.com/), Licence Ouverte 2.0.
CausalRivers: Data from CausalRivers (https://causalrivers.github.io/), licensed under dl-de/by-2-0 (https://www.govdata.de/dl-de/by-2-0).
AEMO: Contains data from the Australian Energy Market Operator (AEMO), used under AEMO's copyright permissions.
Elia: Contains data from Elia Open Data (https://opendata.elia.be/).
LargeAQ: from CauAir (https://github.com/PoorOtterBob/CauAir), CC BY 4.0. Ma et al., "Causal Learning Meet Covariates: Empowering Lightweight and Effective Nationwide Air Quality Forecasting", IJCAI 2025 (https://www.ijcai.org/proceedings/2025/353).
CC BY-SA 4.0: training data from Building Data Genome Project 2, Open D1NAMO, NMT Scalp EEG Dataset (Khan et al. 2022), the HAI industrial control system dataset and Wikipedia club-season, episode-list and team-season articles (Wikipedia contributors; the team-season articles give the NBA, NHL and WNBA event dates in nyc_subway_events), licensed under CC BY-SA 4.0; the redistributed copies are in Simons-Pretrain.
The datasets in Simons-Pretrain are credited, with their licenses and links to their sources, in its NOTICE.md.