Radiant MLHub

Tropical Cyclone Wind Estimation Model

Tropical Cyclone Wind Estimation Model
ml-model
resnet18
regression
supervised

This is a PyTorch model trained on the Tropical Cyclone Wind Estimation Competition dataset with v0.1 of the TorchGeo package. The model is a resnet18 model pretrained on ImageNet then trained with a MSE loss. The data were randomly split 80/20 by storm ID and an early stop was used based on performance.

Model ID

model-cyclone-wind-estimation-torchgeo-v1

DOI

10.5281/zenodo.5773331browse DOI

Creator

Microsoft AI for Good Research Lab (Caleb Robinson)

Contact

caleb.robinson@microsoft.com

License

MIT

Applicable Temporal Extent

2000-01-01 / present

Publications

  • Stewart, A., Robinson, C. and Corley, I., 2021. TorchGeo: deep learning with geospatial data. arXiv preprint arXiv:2111.08872, [online] (11). Available at: https://arxiv.org/abs/2111.08872 [Date Accessed].

Citation

Caleb Robinson. (2021). Tropical Cyclone Wind Estimation model (2.0). Zenodo. https://doi.org/10.5281/zenodo.5773331.

Inferencing Image Example

docker pull docker.io/radiantearth/cyclone-model-torchgeo:1

Assets and Links

Inference RuntimeModel inferencing runtime
CheckpointFinal model checkpoint
Training DataTraining Data Source, Training Data Labels
Inferencing Image
docker.io/radiantearth/cyclone-model-torchgeo:1
Related MLHub DatasetTropical Cyclone Wind Estimation Competition Dataset

Radiant Earth Foundation

© Radiant Earth Foundation