sunspot-detection Object Detection Dataset and Pre-Trained Model by solarflarelabelling

Images

277 images

Explore Dataset

Sunspot detector using SDO/HMI

This model is being developed to classify suspots using the Zurich McIntosh classification.

Current Usage

Initial attempts to classifify the full 3 charachter McIntosh classification were deemed to difficult and therfore the approach to date is to limit the class to Zurich only.

Once a higher rate of success is achived this model will for a stacked layer to re-classifiy for the later McIntish parameters. The model success is improving and by setting the prediction rate to 20% the model is highly effective classification.

Therfore this is still very much in-progress.

Labelling

The labbelling is currently now at the stage where it's using the current model as the predictive first attempt. What has been cosnistent to date is the bounding boxes need to understand the seperate between sunspots and therefore the boxes look initial like they're including a lot of non-sunspot activity.

This however is useful how when the second stacked layer will coming into play, as this will re-classifiy within the p (Penumbra) and c (degreee of compatness)

Copyright

The images used in this project are downloaded from the NASA SDO website. See https://sdo.gsfc.nasa.gov/data/rules.php.

Therefore all images provided by SDO NASA are "Courtesy of NASA/SDO and the AIA, EVE, and HMI science teams."

Trained Model API

This project has a trained model available that you can try in your browser and use to get predictions via our Hosted Inference API and other deployment methods.

Cite This Project

If you use this dataset in a research paper, please cite it using the following BibTeX:

@misc{
                            sunspot-detection-uhgat_dataset,
                            title = { sunspot-detection Dataset },
                            type = { Open Source Dataset },
                            author = { solarflarelabelling },
                            howpublished = { \url{ https://universe.roboflow.com/solarflarelabelling/sunspot-detection-uhgat } },
                            url = { https://universe.roboflow.com/solarflarelabelling/sunspot-detection-uhgat },
                            journal = { Roboflow Universe },
                            publisher = { Roboflow },
                            year = { 2024 },
                            month = { jun },
                            note = { visited on 2024-06-23 },
                            }