DDM-Former: Global Ocean Wind Speed Retrieval with Transformer Networks

Daixin Zhao, Konrad Heidler, Milad Asgarimehr, Caroline Arnold, Tianqi Xiao, Jens Wickert, Xiao Xiang Zhu, Lichao Mou

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

As a novel remote sensing technique, GNSS reflectometry (GNSS-R) opens a new era of retrieving Earth surface parameters. Several studies employ the combination of deep learning and GNSS-R observable delay-Doppler maps (DDMs) to generate ocean wind speed estimation. Unlike these methods that often use convolutional neural networks (CNNs) with inductive bias, we proposed a Transformer-based model, named DDM-Former, to exploit fine-grained delay-Doppler correlation independently. Our model is evaluated on the Cyclone GNSS (CYGNSS) version 3.0 dataset and shown to outperform the other retrieval methods.

Original languageEnglish
Title of host publicationIGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1182-1185
Number of pages4
ISBN (Electronic)9798350320107
DOIs
StatePublished - 2023
Event2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023 - Pasadena, United States
Duration: 16 Jul 202321 Jul 2023

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)
Volume2023-July

Conference

Conference2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023
Country/TerritoryUnited States
CityPasadena
Period16/07/2321/07/23

Keywords

  • Cyclone GNSS
  • deep learning
  • GNSS reflectometry
  • ocean wind speed
  • Transformer network

Fingerprint

Dive into the research topics of 'DDM-Former: Global Ocean Wind Speed Retrieval with Transformer Networks'. Together they form a unique fingerprint.

Cite this