Capturing the Diversity of Mesoscale Trade Wind Cumuli Using Complementary Approaches From Self‐Supervised Deep Learning

Abstract At mesoscale, trade wind clouds organize with various spatial arrangements, shaping their effect on Earth's energy budget. Representing their fine‐scale dynamics even at 1 km scale climate simulations remains challenging. However, geostationary satellites (GS) offer high‐resolution clo...

Full description

Saved in:
Bibliographic Details
Main Authors: Dwaipayan Chatterjee, Sabrina Schnitt, Paula Bigalke, Claudia Acquistapace, Susanne Crewell
Format: Article
Language:English
Published: Wiley 2024-06-01
Series:Geophysical Research Letters
Subjects:
Online Access:https://doi.org/10.1029/2024GL108889
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850134761944645632
author Dwaipayan Chatterjee
Sabrina Schnitt
Paula Bigalke
Claudia Acquistapace
Susanne Crewell
author_facet Dwaipayan Chatterjee
Sabrina Schnitt
Paula Bigalke
Claudia Acquistapace
Susanne Crewell
author_sort Dwaipayan Chatterjee
collection DOAJ
description Abstract At mesoscale, trade wind clouds organize with various spatial arrangements, shaping their effect on Earth's energy budget. Representing their fine‐scale dynamics even at 1 km scale climate simulations remains challenging. However, geostationary satellites (GS) offer high‐resolution cloud observation for gaining insights into trade wind cumuli from long‐term records. To capture the observed organizational variability, this work proposes an integrated framework using a continuous followed by discrete self‐supervised deep learning approach, which exploits cloud optical depth from GS measurements. We aim to simplify the entire mesoscale cloud spectrum by reducing the image complexity in the feature space and meaningfully partitioning it into seven classes whose connection to environmental conditions is illustrated with reanalysis data. Our framework facilitates comparing human‐labeled mesoscale classes with machine‐identified ones, addressing uncertainties in both methods. It advances previous methods by exploring transitions between regimes, a challenge for physical simulations, and illustrates a case study of sugar‐to‐flower transitions.
format Article
id doaj-art-63afd1cfc0334c5fb9aee97fb37b9651
institution OA Journals
issn 0094-8276
1944-8007
language English
publishDate 2024-06-01
publisher Wiley
record_format Article
series Geophysical Research Letters
spelling doaj-art-63afd1cfc0334c5fb9aee97fb37b96512025-08-20T02:31:38ZengWileyGeophysical Research Letters0094-82761944-80072024-06-015112n/an/a10.1029/2024GL108889Capturing the Diversity of Mesoscale Trade Wind Cumuli Using Complementary Approaches From Self‐Supervised Deep LearningDwaipayan Chatterjee0Sabrina Schnitt1Paula Bigalke2Claudia Acquistapace3Susanne Crewell4Institute for Geophysics and Meteorology University of Cologne Cologne GermanyInstitute for Geophysics and Meteorology University of Cologne Cologne GermanyInstitute for Geophysics and Meteorology University of Cologne Cologne GermanyInstitute for Geophysics and Meteorology University of Cologne Cologne GermanyInstitute for Geophysics and Meteorology University of Cologne Cologne GermanyAbstract At mesoscale, trade wind clouds organize with various spatial arrangements, shaping their effect on Earth's energy budget. Representing their fine‐scale dynamics even at 1 km scale climate simulations remains challenging. However, geostationary satellites (GS) offer high‐resolution cloud observation for gaining insights into trade wind cumuli from long‐term records. To capture the observed organizational variability, this work proposes an integrated framework using a continuous followed by discrete self‐supervised deep learning approach, which exploits cloud optical depth from GS measurements. We aim to simplify the entire mesoscale cloud spectrum by reducing the image complexity in the feature space and meaningfully partitioning it into seven classes whose connection to environmental conditions is illustrated with reanalysis data. Our framework facilitates comparing human‐labeled mesoscale classes with machine‐identified ones, addressing uncertainties in both methods. It advances previous methods by exploring transitions between regimes, a challenge for physical simulations, and illustrates a case study of sugar‐to‐flower transitions.https://doi.org/10.1029/2024GL108889mesoscale cloud organizationtropical cloudsartificial intelligenceself‐supervisioncloud variabilitycloud system transition
spellingShingle Dwaipayan Chatterjee
Sabrina Schnitt
Paula Bigalke
Claudia Acquistapace
Susanne Crewell
Capturing the Diversity of Mesoscale Trade Wind Cumuli Using Complementary Approaches From Self‐Supervised Deep Learning
Geophysical Research Letters
mesoscale cloud organization
tropical clouds
artificial intelligence
self‐supervision
cloud variability
cloud system transition
title Capturing the Diversity of Mesoscale Trade Wind Cumuli Using Complementary Approaches From Self‐Supervised Deep Learning
title_full Capturing the Diversity of Mesoscale Trade Wind Cumuli Using Complementary Approaches From Self‐Supervised Deep Learning
title_fullStr Capturing the Diversity of Mesoscale Trade Wind Cumuli Using Complementary Approaches From Self‐Supervised Deep Learning
title_full_unstemmed Capturing the Diversity of Mesoscale Trade Wind Cumuli Using Complementary Approaches From Self‐Supervised Deep Learning
title_short Capturing the Diversity of Mesoscale Trade Wind Cumuli Using Complementary Approaches From Self‐Supervised Deep Learning
title_sort capturing the diversity of mesoscale trade wind cumuli using complementary approaches from self supervised deep learning
topic mesoscale cloud organization
tropical clouds
artificial intelligence
self‐supervision
cloud variability
cloud system transition
url https://doi.org/10.1029/2024GL108889
work_keys_str_mv AT dwaipayanchatterjee capturingthediversityofmesoscaletradewindcumuliusingcomplementaryapproachesfromselfsuperviseddeeplearning
AT sabrinaschnitt capturingthediversityofmesoscaletradewindcumuliusingcomplementaryapproachesfromselfsuperviseddeeplearning
AT paulabigalke capturingthediversityofmesoscaletradewindcumuliusingcomplementaryapproachesfromselfsuperviseddeeplearning
AT claudiaacquistapace capturingthediversityofmesoscaletradewindcumuliusingcomplementaryapproachesfromselfsuperviseddeeplearning
AT susannecrewell capturingthediversityofmesoscaletradewindcumuliusingcomplementaryapproachesfromselfsuperviseddeeplearning