Global Ocean Forecast Accuracy Improvement Due to Optimal Sensor Placement

The paper examines the impact of sensor placement on the accuracy of the Global ocean state forecasting. A comparison is made between various sensor placement methods, including the arrangement obtained by the Concrete Autoencoder method. To evaluate how sensor placement affects forecast accuracy, a...

Full description

Saved in:
Bibliographic Details
Main Authors: Turko Nikita, Lobashev Aleksandr, Ushakov Konstantin Viktorovich, Kaurkin Maksim Nikolaevich, Kal'nickiy Leonid Yur'evich, Semin Sergey, Ibraev Rashit
Format: Article
Language:English
Published: Russian Academy of Sciences, The Geophysical Center 2023-12-01
Series:Russian Journal of Earth Sciences
Subjects:
Online Access:http://doi.org/10.2205/2023ES000883
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849246100329857024
author Turko Nikita
Lobashev Aleksandr
Ushakov Konstantin Viktorovich
Kaurkin Maksim Nikolaevich
Kal'nickiy Leonid Yur'evich
Semin Sergey
Ibraev Rashit
author_facet Turko Nikita
Lobashev Aleksandr
Ushakov Konstantin Viktorovich
Kaurkin Maksim Nikolaevich
Kal'nickiy Leonid Yur'evich
Semin Sergey
Ibraev Rashit
author_sort Turko Nikita
collection DOAJ
description The paper examines the impact of sensor placement on the accuracy of the Global ocean state forecasting. A comparison is made between various sensor placement methods, including the arrangement obtained by the Concrete Autoencoder method. To evaluate how sensor placement affects forecast accuracy, a simulation was conducted that emulates a scenario where the initial state of the global ocean significantly deviates from the ground truth. In the experiment, initial conditions for the ocean and ice model were altered, while atmospheric forcing was retained from the control experiment. Subsequently, the model was integrated with the assimilation of data about the ground truth state at the sensor locations. The results showed that the sensor placement obtained using deep learning methods is superior in forecast accuracy to other considered arrays with a comparable number of sensors.
format Article
id doaj-art-5bf9bcbebd0045a8a3dd9ee059f134d5
institution Kabale University
issn 1681-1208
language English
publishDate 2023-12-01
publisher Russian Academy of Sciences, The Geophysical Center
record_format Article
series Russian Journal of Earth Sciences
spelling doaj-art-5bf9bcbebd0045a8a3dd9ee059f134d52025-08-20T03:58:36ZengRussian Academy of Sciences, The Geophysical CenterRussian Journal of Earth Sciences1681-12082023-12-0123612110.2205/2023ES000883Global Ocean Forecast Accuracy Improvement Due to Optimal Sensor PlacementTurko Nikita0https://orcid.org/0000-0002-8039-9087Lobashev Aleksandr1https://orcid.org/0000-0002-9522-9996Ushakov Konstantin Viktorovich2https://orcid.org/0000-0002-8454-9927Kaurkin Maksim Nikolaevich3https://orcid.org/0000-0002-0921-3630Kal'nickiy Leonid Yur'evich4https://orcid.org/0009-0005-4023-2257Semin Sergey5https://orcid.org/0000-0001-8079-168XIbraev Rashit6https://orcid.org/0000-0002-9099-4541Institut okeanologii im. P.P. Shirshova RANSkolkovskiy institut nauki i tehnologiyInstitut okeanologii im. P.P. Shirshova RANInstitut okeanologii im. P.P. Shirshova RANArkticheskiy i antarkticheskiy nauchno-issledovatel'skiy institutInstitut problem bezopasnogo razvitiya atomnoy energetiki RANInstitut vychislitel'noy matematiki im. G.I. Marchuka RANThe paper examines the impact of sensor placement on the accuracy of the Global ocean state forecasting. A comparison is made between various sensor placement methods, including the arrangement obtained by the Concrete Autoencoder method. To evaluate how sensor placement affects forecast accuracy, a simulation was conducted that emulates a scenario where the initial state of the global ocean significantly deviates from the ground truth. In the experiment, initial conditions for the ocean and ice model were altered, while atmospheric forcing was retained from the control experiment. Subsequently, the model was integrated with the assimilation of data about the ground truth state at the sensor locations. The results showed that the sensor placement obtained using deep learning methods is superior in forecast accuracy to other considered arrays with a comparable number of sensors.http://doi.org/10.2205/2023ES000883operational forecast Global ocean optimal sensor placement Concrete Autoencoder data assimilation
spellingShingle Turko Nikita
Lobashev Aleksandr
Ushakov Konstantin Viktorovich
Kaurkin Maksim Nikolaevich
Kal'nickiy Leonid Yur'evich
Semin Sergey
Ibraev Rashit
Global Ocean Forecast Accuracy Improvement Due to Optimal Sensor Placement
Russian Journal of Earth Sciences
operational forecast
Global ocean
optimal sensor placement
Concrete Autoencoder
data assimilation
title Global Ocean Forecast Accuracy Improvement Due to Optimal Sensor Placement
title_full Global Ocean Forecast Accuracy Improvement Due to Optimal Sensor Placement
title_fullStr Global Ocean Forecast Accuracy Improvement Due to Optimal Sensor Placement
title_full_unstemmed Global Ocean Forecast Accuracy Improvement Due to Optimal Sensor Placement
title_short Global Ocean Forecast Accuracy Improvement Due to Optimal Sensor Placement
title_sort global ocean forecast accuracy improvement due to optimal sensor placement
topic operational forecast
Global ocean
optimal sensor placement
Concrete Autoencoder
data assimilation
url http://doi.org/10.2205/2023ES000883
work_keys_str_mv AT turkonikita globaloceanforecastaccuracyimprovementduetooptimalsensorplacement
AT lobashevaleksandr globaloceanforecastaccuracyimprovementduetooptimalsensorplacement
AT ushakovkonstantinviktorovich globaloceanforecastaccuracyimprovementduetooptimalsensorplacement
AT kaurkinmaksimnikolaevich globaloceanforecastaccuracyimprovementduetooptimalsensorplacement
AT kalnickiyleonidyurevich globaloceanforecastaccuracyimprovementduetooptimalsensorplacement
AT seminsergey globaloceanforecastaccuracyimprovementduetooptimalsensorplacement
AT ibraevrashit globaloceanforecastaccuracyimprovementduetooptimalsensorplacement