Session LSTM and Other Time Series Machine Learning Methods for Time Series Prediction


Description:

With increasing advancements in time series machine learning research and models, this session will highlight research using time series specific models, such as LSTMs, in a variety of earth science applications. This includes but is not limited to topics in weather, climate, aerosol, and energy.


Papers:
Comparison of multivariate time series prediction techniques for emulating Noah-LSM soil moisture outputs.
Mitchell Dodson, MSFC, Huntsville, AL; University of Alabama in Huntsville, Huntsville, AL

A Fuel Moisture Model for WRF-SFIRE from HRRR and RAWS Data by a Physics-Initialized Recurrent Neural Network
Jan Mandel, Univ. of Colorado Denver, Denver, CO; and J. Hirschi, A. Kochanski, A. Farguell, D. V. Mallia, B. Shaddy, A. A. Oberai, K. A. Hilburn, and J. Haley

Submission Deadline: Thursday, 31 August 2023