Published July 21, 2023 | Version v1
Dataset Open

A multi-model ensemble of baseline and process-based models improves the predictive skill of near-term lake forecasts: data, forecasts, and scores

Authors/Creators

  • 1. Virginia Tech

Description

This data publication contains zipped parquet from the Falling Creek Reservoir multi-model ensemble (MME) forecasting work using the FLARE (Forecasting Lake And Reservoir Ecosystems) system and baseline models: drivers.zip contains NOAA driver forecast files, targets.zip contains in-situ water temperature observations, forecasts.zip contains forecast parquet files generated from the MME workflow (FLARE & baseline models), and scores.zip contains forecast skill metrics required for analysis.

Notes

In addition to the funding listed, this work was also supported by funding from the National Science Foundation (DEB-2320730).

Files

drivers.zip

Files (1.4 GB)

Name Size Download all
md5:990f74aa02c30f4434c6ad133c00c3fe
28.9 MB Preview Download
md5:2a41d1592d39e7d4f12553209c134b80
1.3 GB Preview Download
md5:00103909507b19fb68ad8460dd7eb12d
21.8 MB Preview Download
md5:ef4d41f9cbc8852acb08b4e15e191b2e
173.6 kB Preview Download

Additional details

Funding

U.S. National Science Foundation
Collaborative Research: CIBR: Cyberinfrastructure Enabling End-to-End Workflows for Aquatic Ecosystem Forecasting 1933102
U.S. National Science Foundation
NEON RCN: The Ecological Forecasting Initiative RCN: Using NEON-enabled near-term forecasting to synthesize our understanding of predictability across ecological systems and scales 1926388
U.S. National Science Foundation
Collaborative Research: CIBR: Cyberinfrastructure Enabling End-to-End Workflows for Aquatic Ecosystem Forecasting 1933016