Vertical Velocity Diagnosed From Surface Data With Machine Learning

Abstract Submesoscale vertical velocities, w, are important for the oceanic transport of heat and biogeochemical properties, but observing w is challenging. New remote sensing technologies of horizontal surface velocity at O(1) km resolution can resolve surface submesoscale dynamics and offer promis...

Full description

Saved in:
Bibliographic Details
Main Authors: Jing He, Amala Mahadevan
Format: Article
Language:English
Published: Wiley 2024-03-01
Series:Geophysical Research Letters
Online Access:https://doi.org/10.1029/2023GL104835
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849321881507725312
author Jing He
Amala Mahadevan
author_facet Jing He
Amala Mahadevan
author_sort Jing He
collection DOAJ
description Abstract Submesoscale vertical velocities, w, are important for the oceanic transport of heat and biogeochemical properties, but observing w is challenging. New remote sensing technologies of horizontal surface velocity at O(1) km resolution can resolve surface submesoscale dynamics and offer promise for diagnosing w subsurface. Using machine learning models, we examine relationships between the three‐dimensional w field and remotely observable surface variables such as horizontal velocity, density, and their horizontal gradients. We evaluate the machine learning models' sensitivities to different inputs, spatial resolution of surface fields, the addition of noise, and information about the subsurface density. We find that surface data is sufficient for reconstructing w, and having high resolution horizontal velocities with minimal errors is crucial for accurate w predictions. This highlights the importance of finer scale surface velocity measurements and suggests that data‐driven methods may be effective tools for linking surface observations with vertical velocity and transport subsurface.
format Article
id doaj-art-7f8dd74a2b4141e69d5aa45e3a78ab36
institution Kabale University
issn 0094-8276
1944-8007
language English
publishDate 2024-03-01
publisher Wiley
record_format Article
series Geophysical Research Letters
spelling doaj-art-7f8dd74a2b4141e69d5aa45e3a78ab362025-08-20T03:49:37ZengWileyGeophysical Research Letters0094-82761944-80072024-03-01516n/an/a10.1029/2023GL104835Vertical Velocity Diagnosed From Surface Data With Machine LearningJing He0Amala Mahadevan1MIT/WHOI Joint Program in Oceanography Cambridge MA USAWoods Hole Oceanographic Institution Woods Hole MA USAAbstract Submesoscale vertical velocities, w, are important for the oceanic transport of heat and biogeochemical properties, but observing w is challenging. New remote sensing technologies of horizontal surface velocity at O(1) km resolution can resolve surface submesoscale dynamics and offer promise for diagnosing w subsurface. Using machine learning models, we examine relationships between the three‐dimensional w field and remotely observable surface variables such as horizontal velocity, density, and their horizontal gradients. We evaluate the machine learning models' sensitivities to different inputs, spatial resolution of surface fields, the addition of noise, and information about the subsurface density. We find that surface data is sufficient for reconstructing w, and having high resolution horizontal velocities with minimal errors is crucial for accurate w predictions. This highlights the importance of finer scale surface velocity measurements and suggests that data‐driven methods may be effective tools for linking surface observations with vertical velocity and transport subsurface.https://doi.org/10.1029/2023GL104835
spellingShingle Jing He
Amala Mahadevan
Vertical Velocity Diagnosed From Surface Data With Machine Learning
Geophysical Research Letters
title Vertical Velocity Diagnosed From Surface Data With Machine Learning
title_full Vertical Velocity Diagnosed From Surface Data With Machine Learning
title_fullStr Vertical Velocity Diagnosed From Surface Data With Machine Learning
title_full_unstemmed Vertical Velocity Diagnosed From Surface Data With Machine Learning
title_short Vertical Velocity Diagnosed From Surface Data With Machine Learning
title_sort vertical velocity diagnosed from surface data with machine learning
url https://doi.org/10.1029/2023GL104835
work_keys_str_mv AT jinghe verticalvelocitydiagnosedfromsurfacedatawithmachinelearning
AT amalamahadevan verticalvelocitydiagnosedfromsurfacedatawithmachinelearning