elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Model and Data Uncertainty for Satellite Time Series Forecasting with Deep Recurrent Models

Rußwurm, Marc and Ali, Syed Mohsin and Zhu, Xiaoxiang and Gal, Yarin and Körner, Marco (2020) Model and Data Uncertainty for Satellite Time Series Forecasting with Deep Recurrent Models. In: 2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020, pp. 1-4. IGARSS 2020, 26.9.-2.10.2020, Virtual Symposium. doi: 10.1109/igarss39084.2020.9323890. ISBN 978-172816374-1. ISSN 2153-6996.

[img] PDF
604kB

Abstract

Deep Learning is often criticized as black-box method which often provides accurate predictions, but limited explanation of the underlying processes and no indication when to not trust those predictions. Equipping existing deep learning models with an (approximate) notion of uncertainty can help mitigate both these issues therefore their use should be known more broadly in the community. The Bayesian deep learning community has developed model-agnostic and easy to-implement methodology to estimate both data and model uncertainty within deep learning models which is hardly applied in the remote sensing community. In this work, we adopt this methodology for deep recurrent satellite time series forecasting, and test its assumptions on data and model uncertainty. We demonstrate its effectiveness on two applications on climate change, and event change detection and outline limitations.

Item URL in elib:https://elib.dlr.de/139306/
Document Type:Conference or Workshop Item (Speech)
Title:Model and Data Uncertainty for Satellite Time Series Forecasting with Deep Recurrent Models
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Rußwurm, MarcUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Ali, Syed MohsinUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Zhu, XiaoxiangUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Gal, YarinUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Körner, MarcoUNSPECIFIEDhttps://orcid.org/0000-0002-9186-4175UNSPECIFIED
Date:29 September 2020
Journal or Publication Title:2020 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2020
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:Yes
DOI:10.1109/igarss39084.2020.9323890
Page Range:pp. 1-4
ISSN:2153-6996
ISBN:978-172816374-1
Status:Published
Keywords:Remote Sensing, Deep Learning, Uncertainties, Time Series, Bayesian Neural Networks
Event Title:IGARSS 2020
Event Location:Virtual Symposium
Event Type:international Conference
Event Dates:26.9.-2.10.2020
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Earth Observation
DLR - Research theme (Project):R - Remote Sensing and Geo Research
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > EO Data Science
Deposited By: Ali, Syed Mohsin
Deposited On:10 Dec 2020 12:14
Last Modified:27 Mar 2024 15:07

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.