Lightweight Neural Network for Spatiotemporal Filling of Data Gaps in Sea Surface Temperature Images

Cloud coverage remains a key issue for researchers working with satellite data. Accurate reconstruction of measurements obstructed by cloud can enhance the usefulness of satellite databases for identifying trends and changes in various environments. In this work, we develop, train and test a bidirectional long short-term memory (BiLSTM) model with a custom temporal penalty layer for filling gaps in sea surface temperature (SST) images acquired by the Himawari- 8 satellite. The proposed model showed strong performance, achieving a per-image MAE of 0.1193◦C and per-image RMSE of 0.0985◦C. Our model is also shown to outperform previous state-of-the-art literature. Overall, this work shows that our BiLSTM algorithm is an effective tool for gapfilling cloud-affected SST data.


<b>Citation: </b>S. Baker, Z. Huang and B. Philippa, "Lightweight Neural Network for Spatiotemporal Filling of Data Gaps in Sea Surface Temperature Images," in <i>IEEE Transactions on Geoscience and Remote Sensing</i>, vol. 61, pp. 1-10, 2023, Art no. 4204310, doi: 10.1109/TGRS.2023.3273575

Simple

Identification info

Date (Creation)
2022-08-23T13:48:00
Date (Publication)
2023-11-01T05:47:54
Citation identifier
Geoscience Australia Persistent Identifier/https://pid.geoscience.gov.au/dataset/ga/147158

Identifier

Codespace

Digital Object Identifier

Cited responsible party
Role Organisation / Individual Name Details
Author

Baker, S.

 External Contact
Author

Huang, Z.

 Place and Communities Internal Contact
Author

Philippa, L.

 External Contact
Publisher

Elsevier B.V.

 External Contact
Name

IEEE Transactions on Geoscience and Remote Sensing

Issue identification

Volume 61

Page

1-10

Purpose

external publication

Status
Completed
Point of contact
Role Organisation / Individual Name Details
Point of contact

Commonwealth of Australia (Geoscience Australia)

 Voice
Resource provider

Place and Communities Division

 External Contact
Point of contact

Huang, Z.

 Place and Communities Internal Contact
Spatial representation type
Topic category
  • Geoscientific information
  • Oceans

Extent

Extent

N
S
E
W


Maintenance and update frequency
Not planned

Resource format

Title

Product data repository: Various Formats

Website

Data Store directory containing the digital product files

Data Store directory containing one or more files, possibly in a variety of formats, accessible to Geoscience Australia staff only for internal purposes

theme.ANZRC Fields of Research.rdf

  • EARTH SCIENCES

Keywords

  • Sea surface temperature - SST

Keywords

  • bidirectional long short-term memory - BiLSTM

Keywords

  • neural network

Keywords

  • spatiotemporal

Keywords

  • Published_External

Resource constraints

Title

Personal use is permitted, but republication/redistribution requires IEEE permission

Edition

4.0

Website

https://www.ieee.org/publications/rights/index.html

Access constraints
License
Use constraints
License
Other constraints

© 2023, IEEE

Resource constraints

Title

Australian Government Security ClassificationSystem

Edition date
2018-11-01T00:00:00
Website

https://www.protectivesecurity.gov.au/Pages/default.aspx

Classification
Unclassified
Language
English
Character encoding
UTF8

Distribution Information

Distributor contact
Role Organisation / Individual Name Details
Distributor

Commonwealth of Australia (Geoscience Australia)

 Voice facsimile
OnLine resource

Link to Journal

Link to Journal

Distribution format

Resource lineage

Statement

The is the results of a collaboration with two colleagues from JCU. The paper is published.

Baker, S., Huang, Z., Philippa, B., 2023. Lightweight Neural Network for Spatiotemporal Filling of Data Gaps in Sea Surface Temperature Images, IEEE Transactions on Geoscience and Remote Sensing, https://doi.org/10.1109/TGRS.2023.3273575.

Metadata constraints

Title

Australian Government Security Classification System

Edition date
2018-11-01T00:00:00
Website

https://www.protectivesecurity.gov.au/Pages/default.aspx

Classification
Unclassified

Metadata

Metadata identifier
urn:uuid/33d3e919-4597-4311-82a9-4f464ed2d118

Title

GeoNetwork UUID

Language
English
Character encoding
UTF8
Contact
Role Organisation / Individual Name Details
Point of contact

Commonwealth of Australia (Geoscience Australia)

 Voice
Owner

Huang, Z

 Geoscience Australia Internal Contact
Point of contact

Huang, Z.

 Place and Communities Internal Contact

Type of resource

Resource scope
Document
Name

Journal Articles and Conference Papers

Alternative metadata reference

Title

Geoscience Australia - short identifier for metadata record with

uuid

Citation identifier
eCatId/147158

Metadata linkage

https://ecat.ga.gov.au/geonetwork/srv/eng/catalog.search#/metadata/5167d912-6784-4371-9938-3931e84ca6f1

Metadata linkage

https://ecat.ga.gov.au/geonetwork/srv/eng/catalog.search#/metadata/33d3e919-4597-4311-82a9-4f464ed2d118

Metadata linkage

https://ecat.ga.gov.au/geonetwork/static/eng/catalog.search#/metadata/33d3e919-4597-4311-82a9-4f464ed2d118

Date info (Creation)
2019-04-08T01:55:29
Date info (Revision)
2019-04-08T01:55:29

Metadata standard

Title

AU/NZS ISO 19115-1:2014

Metadata standard

Title

ISO 19115-1:2014

Metadata standard

Title

ISO 19115-3

Title

Geoscience Australia Community Metadata Profile of ISO 19115-1:2014

Edition

Version 2.0, September 2018

Citation identifier
https://pid.geoscience.gov.au/dataset/ga/122551

 
 

Spatial extent

N
S
E
W


Keywords

Sea surface temperature - SST bidirectional long short-term memory - BiLSTM neural network spatiotemporal
theme.ANZRC Fields of Research.rdf
EARTH SCIENCES

Provided by

Access to the portal

Associated resources

Not available