BENCHMARKING BAYESIAN DEEP LEARNING METHODS WITH MULTI-SPECTRAL SATELLITE IMAGERY

Loading...
Thumbnail Image
Authors
Marsh, Benjamin R.
Subjects
artificial intelligence
machine learning
deep learning
image classification
Bayesian deep learning
uncertainty quantification
convolutional neural networks
deep neural networks
atmospheric science
convective type classification
meteorology
passive microwave satellite images
estimating uncertainty
aleatoric uncertainty
epistemic uncertainty
data science
statistics
deep convolutional neural network
DCNN
National Aeronautics and Space Administration
NASA
Advisors
Orescanin, Marko
Date of Issue
2021-09
Date
September 2021
Publisher
Monterey, California. Naval Postgraduate School
Language
Abstract
The deep convolutional neural network (DCNN) is the current state-of-the-art approach for automatic image classification tasks. Historically, Bayesian deep learning methods have been applied to these models in narrow scopes. This thesis has created and tested several Bayesian deep learning models to perform classification on operational meteorological multi-spectral satellite data while quantifying the uncertainty in the model predictions. This large-scale dataset is used to compare the performance of Bayesian models against a DCNN and the current algorithm used by the National Aeronautics and Space Administration (NASA) to perform precipitation classification on the dataset. The use of a large-scale, operational dataset to benchmark Bayesian deep learning methods is the first application of its kind and represents a novel contribution to the fields of Bayesian deep learning and computer science. Several novel benchmarks were developed for use in this work. The best performing Bayesian model achieved 92 percent classification accuracy with demonstrated calibrated uncertainty on test data. All Bayesian models are shown to outperform current state-of-the-art DCNNs and the current operational algorithm. Furthermore, it is demonstrated that Bayesian model uncertainties can be used to screen uncertain predictions, and these uncertainties can be mapped spatially to identify specific regions of data that can be used to further improve the model performance.
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.
Collections