Next Day Wildfire Spread: A Machine Learning Data Set to Predict Wildfire Spreading from Remote-Sensing Data

Image | Wildfire | Preparedness

Next Day Wildfire Spread is a dataset for wildfire spread prediction. It contains images for 18,545 fire events with snapshots at time t and t+1 day. It is introduced for image segmentation.

  • ML task type: Image segmentation
  • Data Source: Earth Observation Data and GeoSpatial Imagery (Remote sensing); Sensor network data; Official data (Research institutes)
  • Size: 18,545 fire events with two image snapshots at time t and t+1 day
  • Timespan: 2012 - 2020
  • Geographical Coverage: Contiguous US
  • Baseline Information
  • Evaluated on: Convolutional autoencoder
  • Metrics used: AUC, Precision, Recall
  • Results as reported in original paper: AUC: 28.4%; Precision: 33.6%; Recall: 43.1%

Fantine Huot, R Lily Hu, Nita Goyal, Tharun Sankar, Matthias Ihme, and Yi-Fan Chen. Next day wildfire spread: A machine learning data set to predict wildfire spreading from remote-sensing data. arXiv preprint arXiv:2112.02447, 2021.