BENCHMARKING BAYESIAN DEEP LEARNING METHODS WITH MULTI-SPECTRAL SATELLITE IMAGERY

Download
Author
Marsh, Benjamin R.
Date
2021-09Advisor
Orescanin, Marko
Second Reader
Powell, Scott
Metadata
Show full item recordAbstract
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.
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
Related items
Showing items related by title, author, creator and subject.
-
A MACHINE LEARNING APPROACH TO NETWORK SECURITY CLASSIFICATION USING NETFLOW DATA
Watkins, John R. (Monterey, CA; Naval Postgraduate School, 2021-09);All computer network traffic can be associated with a specific signature based on a feature set within its metadata. There has been a significant effort in preprocessing data for machine learning for the purposes of ... -
FEDERATED LEARNING OF BAYESIAN NEURAL NETWORKS
Loomis, Justin M. (Monterey, CA; Naval Postgraduate School, 2023-03);Although federated learning and Bayesian neural networks have been researched, there are few implementations of the federated learning of Bayesian networks. In this thesis, a federated learning training environment for ... -
CONVOLUTIONAL NEURAL NETWORKS FOR DETECTION AND CLASSIFICATION OF MARITIME VESSELS IN ELECTRO-OPTICAL SATELLITE IMAGERY
Rice, Katherine (Monterey, CA; Naval Postgraduate School, 2018-12);The ability to locate and identify vessels of interest in satellite imagery plays a vital role in maintaining maritime security. Recent studies have demonstrated that convolutional neural networks can be used to automatically ...