Data for Multi-modal graph neural networks for localized off-grid weather forecasting

This repository contains the data for the paper "Multi-Modal Graph Neural Networks for Localized Off-Grid Weather Forecasting".

The paper presents a novel multi-modal graph neural network (GNN) that downscales gridded weather forecasts, such as ERA5, to provide accurate off-grid predictions. The model leverages both ERA5 data and local weather station observations from MADIS to make predictions that reflect both large-scale atmospheric dynamics and local weather patterns.

The model is evaluated on a surface wind prediction task and shows significant improvement over baseline methods, including ERA5 interpolation and a multi-layer perceptron.

Use the following citation when these data or model are used:> Yang, Q.; Giezendanner, J.; Civitarese, D. S.; Jakubik, J.; ,Schmitt E.; Chandra, A.; Vila, J.; Hohl, D.; Hill, C.; Watson, C.; Wang, S.; Multi-modal graph neural networks for localized off-grid weather forecasting. arXiv, October 2024. https://doi.org/10.48550/arXiv.2410.12938

The following data is available:- Shapefile of the Northeastern United States (NE-US, extracted from NWS)- Shapefile containing the location and number of observations (2019-2023) of the MADIS stations in NE-US- Processed hourly averaged MADIS data for the NE-US (2019-2023)- ERA5 data for the NE-US (2019-2023), gridded and interpolated

For MADIS and ERA5, the following variables are available:- u and v component of wind vector at 10 meters above ground- temperature at 2 meters above ground- dewpoint at 2 meters above ground- solar radiation