Qi-Fan Wu, Markus Jochum, James E. Avery, Guido Vettoretti, Roman Nuterman
{"title":"大西洋经向翻转环流（AMOC）强度的机器引导推导","authors":"Qi-Fan Wu, Markus Jochum, James E. Avery, Guido Vettoretti, Roman Nuterman","doi":"10.1029/2024GL113454","DOIUrl":null,"url":null,"abstract":"<p>A machine learning based methodology is developed to determine the strength of the Atlantic Meridional Overturning Circulation (AMOC) in the Community Earth System Model (CESM). Neural networks capture relationships between various climate variables and AMOC. We then identify which of the various are the most important to control the AMOC, and then perform symbolic regression to transform complex interactions into a simple closed-form approximation. A sensitivity analysis for this equation reveals that surface freshwater flux and potential density at 200 m depth are the main controls of the AMOC.</p>","PeriodicalId":12523,"journal":{"name":"Geophysical Research Letters","volume":"52 3","pages":""},"PeriodicalIF":4.6000,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1029/2024GL113454","citationCount":"0","resultStr":"{\"title\":\"Machine Guided Derivation of the Atlantic Meridional Overturning Circulation (AMOC) Strength\",\"authors\":\"Qi-Fan Wu, Markus Jochum, James E. Avery, Guido Vettoretti, Roman Nuterman\",\"doi\":\"10.1029/2024GL113454\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>A machine learning based methodology is developed to determine the strength of the Atlantic Meridional Overturning Circulation (AMOC) in the Community Earth System Model (CESM). Neural networks capture relationships between various climate variables and AMOC. We then identify which of the various are the most important to control the AMOC, and then perform symbolic regression to transform complex interactions into a simple closed-form approximation. A sensitivity analysis for this equation reveals that surface freshwater flux and potential density at 200 m depth are the main controls of the AMOC.</p>\",\"PeriodicalId\":12523,\"journal\":{\"name\":\"Geophysical Research Letters\",\"volume\":\"52 3\",\"pages\":\"\"},\"PeriodicalIF\":4.6000,\"publicationDate\":\"2025-01-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1029/2024GL113454\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Geophysical Research Letters\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2024GL113454\",\"RegionNum\":1,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"GEOSCIENCES, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Geophysical Research Letters","FirstCategoryId":"89","ListUrlMain":"https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2024GL113454","RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"GEOSCIENCES, MULTIDISCIPLINARY","Score":null,"Total":0}
Machine Guided Derivation of the Atlantic Meridional Overturning Circulation (AMOC) Strength
A machine learning based methodology is developed to determine the strength of the Atlantic Meridional Overturning Circulation (AMOC) in the Community Earth System Model (CESM). Neural networks capture relationships between various climate variables and AMOC. We then identify which of the various are the most important to control the AMOC, and then perform symbolic regression to transform complex interactions into a simple closed-form approximation. A sensitivity analysis for this equation reveals that surface freshwater flux and potential density at 200 m depth are the main controls of the AMOC.
期刊介绍：
Geophysical Research Letters (GRL) publishes high-impact, innovative, and timely research on major scientific advances in all the major geoscience disciplines. Papers are communications-length articles and should have broad and immediate implications in their discipline or across the geosciences. GRLmaintains the fastest turn-around of all high-impact publications in the geosciences and works closely with authors to ensure broad visibility of top papers.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
