Machine-learning data and model for autoconversion and accretion rates
- ORNL
This PI product includes two key components of a recently developed machine-learning model for predicting autoconversion and accretion rates. The training data set and the testing data set used to build our machine-learning model, containing sets of four input variables (cloud water content, cloud droplet number concentration, drizzle water content, and drizzle drop number concentration) and two output variables (autoconversion rate and accretion rate). The machine-learning model, containing information on the trained weights and biases, and the coefficients for scaling the inputs and outputs variables. The uncertainty in the new estimates of autoconversion and accretion rates is about 15% and 5%, respectively.
- Research Organization:
- Atmospheric Radiation Measurement (ARM) Archive, Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (US); ARM Data Center, Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), Biological and Environmental Research (BER)
- Contributing Organization:
- PNNL, BNL, ANL, ORNL
- DOE Contract Number:
- AC05-00OR22725
- OSTI ID:
- 1763390
- Availability:
- ORNL
- Country of Publication:
- United States
- Language:
- English