WIND-Bench: A Benchmark Dataset for In-Situ Near-Surface Wind Speed Observations Across the Conterminous United States
Abstract
Accurate wind forecasts are essential for operational decision-making and public safety, yet forecasts tend to miss near-surface high wind speeds in complex terrain. In response, advances in machine learning (ML) weather prediction methods have demonstrated the ability to improve forecast skill beyond traditional numerical weather prediction (NWP) models. However, the absence of a benchmark dataset to evaluate NWP and ML models with sufficient, quality-controlled wind speed observations in complex terrain poses challenges to the development and intercomparison of high-quality surface wind forecasts across the Conterminous United States (CONUS). We develop the Wind IN-situ Data Benchmark (WIND-Bench), a benchmark dataset from in-situ observations in the Meteorological Assimilation Data Ingest System (MADIS) observational network. WIND-Bench integrates multiple sensor networks with quality control that distinguishes sensor failures from high-wind conditions, using a framework that validates observations against forecasts from the National Oceanic and Atmospheric Administration (NOAA) High-Resolution Rapid Refresh (HRRR) model. WIND-Bench provides a standardized benchmark for evaluating ML and NWP models and for quantifying forecast skill, accelerating the development, evaluation, and operational deployment of skilled near-surface wind forecasts.
Related
- Evaluating the performance of the surface water and ocean topography (SWOT) mission for monitoring reservoirs across the conterminous United States
- A Sentinel-2 benchmark dataset for deep-learning active-fire segmentation across 25 California wildfires, July 2020-August 2026
- A Canadian Benchmark LiDAR Dataset for Urban Infrastructure and 3D Scene Understanding
- The Hyperspectral Bio-Optical Observations Sailing on Tara (HyperBOOST) dataset
- The UWO dataset – long-term observations from a full-scale field laboratory to better understand urban hydrology at small spatio-temporal scales
BibTeX
@misc{bazlen2026windbench,
title = {{WIND-Bench: A Benchmark Dataset for In-Situ Near-Surface Wind Speed Observations Across the Conterminous United States}},
author = {Kyla Bazlen and Grant Buster and Brandon Benton and Lauren North and Ansley Baring and David D. Turner and Emily Wells and Laura Vimmerstedt},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.12228},
eprint = {2609.12228},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.12228},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - WIND-Bench: A Benchmark Dataset for In-Situ Near-Surface Wind Speed Observations Across the Conterminous United States
AU - Kyla Bazlen
AU - Grant Buster
AU - Brandon Benton
AU - Lauren North
AU - Ansley Baring
AU - David D. Turner
AU - Emily Wells
AU - Laura Vimmerstedt
PY - 2026
DA - 2026/09/10
PB - arXiv
DO - 10.48550/arxiv.2609.12228
UR - https://arxiv.org/abs/2609.12228
AB - Accurate wind forecasts are essential for operational decision-making and public safety, yet forecasts tend to miss near-surface high wind speeds in complex terrain. In response, advances in machine learning (ML) weather prediction methods have demonstrated the ability to improve forecast skill beyond traditional numerical weather prediction (NWP) models. However, the absence of a benchmark dataset to evaluate NWP and ML models with sufficient, quality-controlled wind speed observations in complex terrain poses challenges to the development and intercomparison of high-quality surface wind forecasts across the Conterminous United States (CONUS). We develop the Wind IN-situ Data Benchmark (WIND-Bench), a benchmark dataset from in-situ observations in the Meteorological Assimilation Data Ingest System (MADIS) observational network. WIND-Bench integrates multiple sensor networks with quality control that distinguishes sensor failures from high-wind conditions, using a framework that validates observations against forecasts from the National Oceanic and Atmospheric Administration (NOAA) High-Resolution Rapid Refresh (HRRR) model. WIND-Bench provides a standardized benchmark for evaluating ML and NWP models and for quantifying forecast skill, accelerating the development, evaluation, and operational deployment of skilled near-surface wind forecasts.
ER -