Evaluation

The competition involves a supervised learning task—participants will develop algorithms to identify flood pixels after training their algorithm against a training set of synthetic aperture radar (SAR) images. Participants are required to submit binary segmentation maps (256×256 pixels) in numpy array format with the byte (uint8) data type:

• 0: Not flood region
• 1: Flood region (Region of Interest)

The compeition consists of 2 phases:

• Phase 1 (Development phase): Participants are provided with training data (which includes reference data) and validation data (without reference data until phase 1 concludes) to train and validate their algorithms. Participants can submit prediction results for the validation set to the codalab competition website to get feedback on the performance from April 15 to May 14, 2021. The performance of the best submission from each account will be displayed on the leaderboard.
• Phase 2 (Test Phase):Participants receive the validation set reference data for model tuning and test data set (without the corresponding reference data) to generate predictions and submit their binary classification maps in numpy array format from May 15 to June 30, 2021. After evaluation of the results, three winners will be announced on July 16, 2021.

Performance is assessed using IOU score.

For details about the evaluation criteria and format: https://nasa-impact.github.io/etci2021/

Terms and Conditions

The data are provided for the purpose of participation in the 2021 ETCI competition. Any scientific publication using the data shall include a section “Acknowledgement”. This section shall include the following sentence: “The authors would like to thank the NASA Earth Science Data Systems Program, NASA Digital Transformation AI/ML thrust, and IEEE GRSS for organizing the ETCI competition”.

Acknowledgements

For details about the terms and conditions: https://nasa-impact.github.io/etci2021/