IMPACT OF STOCHASTIC DEPTH ON DETERMINISTIC AND PROBABILISTIC RESNET MODELS FOR WEATHER MODELING
Loading...
Authors
Woods, Cameron P.
Subjects
stochastic depth
SD
residual networks
ResNet
deep neural networks
deterministic models
probabilistic models
Advanced Baseline Imager
ABI
Global Precipitation Measurement
GPM
SD
residual networks
ResNet
deep neural networks
deterministic models
probabilistic models
Advanced Baseline Imager
ABI
Global Precipitation Measurement
GPM
Advisors
Orescanin, Marko
Date of Issue
2022-03
Date
Publisher
Monterey, CA; Naval Postgraduate School
Language
Abstract
This thesis builds on the research that uses Bayesian neural networks to generate Global Precipitation Measurement Microwave Imager data collected by LEO satellites from Advanced Baseline Imager data collected by GEO satellites for the purposes of weather modeling. Specifically, this thesis investigates the efficacy of a stochastic depth (SD) implementation in residual networks (ResNet), both deterministic and probabilistic, to reduce long training times associated with Bayesian neural networks while maintaining model accuracy. We show that overall, ResNets fail to perform better with the implementation of SD with the exception of SD ResNet56 S25, utilizing a survivability probability of 0.25. This resulted in an RMSE of 2.863, a 6.83% increase in performance. In our evaluations, SD models did not train faster, with the fastest average time per epoch of 973.69 seconds compared to 960.42 seconds for the base ResNet56. We conclude that SD was unable to provide the expected performance benefits on realistic large-scale satellite data as found in research on smaller datasets.
Type
Thesis
Description
Series/Report No
Department
Computer Science (CS)
Organization
Identifiers
NPS Report Number
Sponsors
Funder
Format
Citation
Distribution Statement
Approved for public release. Distribution is unlimited.
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.