Inclusion of data uncertainty in machine learning and its application in geodetic data science
METADATA ONLY
Loading...
Author / Producer
Date
2021-06
Publication Type
Other Conference Item
ETH Bibliography
yes
Citations
Altmetric
METADATA ONLY
Data
Rights / License
Abstract
Data uncertainty plays an important role in the field of geodesy. We
propose to include the uncertainty of data in deep neural network
architectures to achieve better generalization, even in small data sets.
Inspired by weighted and total least squares, we formulate the problem
for both input and target uncertainties, and combine it with the Bayesian
learning method. This results in a new form of the loss function in
machine learning. Additionally, we consider the error propagation by
using data uncertainty as features. As benchmark, we use models
without the consideration of data uncertainty. The choice of the model is
arbitrary. However, in this study the benchmark model is a single-layer
LSTM neural network, which can represent and predict sequential data.
We use input uncertainties either as auxiliary features or in a total least
squares manner, and output uncertainties as weights in the L2 classical
loss function.
To show the efficacy of the proposed method, we use real data of Earth
Orientation Parameters (EOP) and various GNSS station position time
series across the globe. Prediction of EOP is important for many
applications such as spacecraft navigation. For the two polar motion
components, dUT1, and GNSS station position time series, we
demonstrate that the least-squares-inspired method can outperform both
the benchmark (by 45%, 52%, 1%, and 8%, respectively) and the
feature-inspired method (65%, 55%, 77%, and 6%). In the case of the
LOD time series, the feature-inspired method shows a better
performance by 10% and 39% with regard to the benchmark and the
least-squares-inspired method, respectively.
Permanent link
Publication status
published
External links
Editor
Book title
IAG 2021 Abstract Book: Geodesy for a Sustainable Earth
Journal / series
Volume
Pages / Article No.
636 - 636
Publisher
IAG 2021
Event
Scientific Assembly of the International Association of Geodesy (IAG 2021)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Data uncertainty; Machine learning; Geodetic data science; EOP and GNSS time series
Organisational unit
09707 - Soja, Benedikt / Soja, Benedikt
Notes
Conference lecture held on July 1, 2021