POST-PROCESSING AND VISUALIZATION
The EAGLE-Tools library provides various utilities for tasks such as executing certain modules, post processing or evaluating needs when running EAGLE ML models.
Output Formats and Tools
Credit to Tim Smith / NOAA Physical Sciences Laboratory
*Disclaimer: This package is pip-installable, but not yet fully documented and tested software.
Graphics & Forecasts Gallery
Postprocessing Figure 1
Performance of the fine-tuned Graphcast (red: similar to Global-Eagle-Ensemble) and GraphCast trained on the GDAS from scratch (green: similar to Global-EAGLE-Solo) compared to the operational GFS (blue). (a) Both versions of the GraphCast outperform forecasts of Tropical Cyclone (TC) track in the Atlantic basin.
Postprocessing Figure 2
Performance of the fine-tuned Graphcast (red: similar to Global-Eagle-Ensemble) and GraphCast trained on the GDAS from scratch (green: similar to Global-EAGLE-Solo) compared to the operational GFS (blue). (a) Both versions of the GraphCast outperform forecasts of Tropical Cyclone (TC) track in the Atlantic basin. (b) Both versions of the GraphCast models underpredict TC intensity compared to the GFS forecast. However, the version of the GraphCast used by the Global-EAGLE-Solo (green) is less biased than the version of the GraphCast used by the Global-EAGLE-Ensemble (red). (Tabas et al., 2025)
Postprocessing Figure 3
EAGLE-Global 2 meter temperature (visualized on the Dynamic Ensemble-based Scenarios for IDSS (DESI))
Postprocessing Figure 4
EAGLE-Global 2 wind direction (particles), visualized on DESI
