Enter Note Done
Go to previous page in this tab
Session
  • Presentation | H11L: Advances in Machine Learning for Earth Science: Observation, Modeling, and Applications I Poster
  • Poster
  • Bookmark Icon
  • H11L-1039: Transfer Learning with Recurrent Neural Networks of Fuel Moisture Content: Extending from 10h fuels to 1h and 100h
  • Schedule
    Notes
  • Board 1039‚ Hall EFG (Poster Hall)
    NOLA CC
    Set Timezone

Generic 'disconnected' Message
Author(s):
Jonathon Hirschi, University of Colorado Denver (First Author, Presenting Author)
Jan Mandel, University of Colorado Denver
Angel Farguell, University of Colorado Denver


Fuel moisture content (FMC) is crucial for understanding wildfire risk and active wildfire rate of spread. Almost all available FMC data is from a type of standardized sensor intended to represent smaller dead sticks. Using models trained to accurately predict the FMC of this standard stick size, we evaluate methods to adapt the model for use in predicting the FMC of other sizes of fuels.



Scientific Discipline
Suggested Itineraries
Neighborhood
Type
Main Session
Discussion