Deep learning for early warning signals of tipping points

Many natural systems exhibit tipping points where slowly changing environmental conditions spark a sudden shift to a new and sometimes very different state. As the tipping point is approached, the dynamics of complex and varied systems simplify down to a limited number of possible "normal forms...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings of the National Academy of Sciences - PNAS Ročník 118; číslo 39
Hlavní autoři: Bury, Thomas M, Sujith, R I, Pavithran, Induja, Scheffer, Marten, Lenton, Timothy M, Anand, Madhur, Bauch, Chris T
Médium: Journal Article
Jazyk:angličtina
Vydáno: 28.09.2021
ISSN:1091-6490, 1091-6490
On-line přístup:Zjistit podrobnosti o přístupu
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Many natural systems exhibit tipping points where slowly changing environmental conditions spark a sudden shift to a new and sometimes very different state. As the tipping point is approached, the dynamics of complex and varied systems simplify down to a limited number of possible "normal forms" that determine qualitative aspects of the new state that lies beyond the tipping point, such as whether it will oscillate or be stable. In several of those forms, indicators like increasing lag-1 autocorrelation and variance provide generic early warning signals (EWS) of the tipping point by detecting how dynamics slow down near the transition. But they do not predict the nature of the new state. Here we develop a deep learning algorithm that provides EWS in systems it was not explicitly trained on, by exploiting information about normal forms and scaling behavior of dynamics near tipping points that are common to many dynamical systems. The algorithm provides EWS in 268 empirical and model time series from ecology, thermoacoustics, climatology, and epidemiology with much greater sensitivity and specificity than generic EWS. It can also predict the normal form that characterizes the oncoming tipping point, thus providing qualitative information on certain aspects of the new state. Such approaches can help humans better prepare for, or avoid, undesirable state transitions. The algorithm also illustrates how a universe of possible models can be mined to recognize naturally occurring tipping points.Many natural systems exhibit tipping points where slowly changing environmental conditions spark a sudden shift to a new and sometimes very different state. As the tipping point is approached, the dynamics of complex and varied systems simplify down to a limited number of possible "normal forms" that determine qualitative aspects of the new state that lies beyond the tipping point, such as whether it will oscillate or be stable. In several of those forms, indicators like increasing lag-1 autocorrelation and variance provide generic early warning signals (EWS) of the tipping point by detecting how dynamics slow down near the transition. But they do not predict the nature of the new state. Here we develop a deep learning algorithm that provides EWS in systems it was not explicitly trained on, by exploiting information about normal forms and scaling behavior of dynamics near tipping points that are common to many dynamical systems. The algorithm provides EWS in 268 empirical and model time series from ecology, thermoacoustics, climatology, and epidemiology with much greater sensitivity and specificity than generic EWS. It can also predict the normal form that characterizes the oncoming tipping point, thus providing qualitative information on certain aspects of the new state. Such approaches can help humans better prepare for, or avoid, undesirable state transitions. The algorithm also illustrates how a universe of possible models can be mined to recognize naturally occurring tipping points.
AbstractList Many natural systems exhibit tipping points where slowly changing environmental conditions spark a sudden shift to a new and sometimes very different state. As the tipping point is approached, the dynamics of complex and varied systems simplify down to a limited number of possible "normal forms" that determine qualitative aspects of the new state that lies beyond the tipping point, such as whether it will oscillate or be stable. In several of those forms, indicators like increasing lag-1 autocorrelation and variance provide generic early warning signals (EWS) of the tipping point by detecting how dynamics slow down near the transition. But they do not predict the nature of the new state. Here we develop a deep learning algorithm that provides EWS in systems it was not explicitly trained on, by exploiting information about normal forms and scaling behavior of dynamics near tipping points that are common to many dynamical systems. The algorithm provides EWS in 268 empirical and model time series from ecology, thermoacoustics, climatology, and epidemiology with much greater sensitivity and specificity than generic EWS. It can also predict the normal form that characterizes the oncoming tipping point, thus providing qualitative information on certain aspects of the new state. Such approaches can help humans better prepare for, or avoid, undesirable state transitions. The algorithm also illustrates how a universe of possible models can be mined to recognize naturally occurring tipping points.Many natural systems exhibit tipping points where slowly changing environmental conditions spark a sudden shift to a new and sometimes very different state. As the tipping point is approached, the dynamics of complex and varied systems simplify down to a limited number of possible "normal forms" that determine qualitative aspects of the new state that lies beyond the tipping point, such as whether it will oscillate or be stable. In several of those forms, indicators like increasing lag-1 autocorrelation and variance provide generic early warning signals (EWS) of the tipping point by detecting how dynamics slow down near the transition. But they do not predict the nature of the new state. Here we develop a deep learning algorithm that provides EWS in systems it was not explicitly trained on, by exploiting information about normal forms and scaling behavior of dynamics near tipping points that are common to many dynamical systems. The algorithm provides EWS in 268 empirical and model time series from ecology, thermoacoustics, climatology, and epidemiology with much greater sensitivity and specificity than generic EWS. It can also predict the normal form that characterizes the oncoming tipping point, thus providing qualitative information on certain aspects of the new state. Such approaches can help humans better prepare for, or avoid, undesirable state transitions. The algorithm also illustrates how a universe of possible models can be mined to recognize naturally occurring tipping points.
Author Anand, Madhur
Pavithran, Induja
Bauch, Chris T
Scheffer, Marten
Bury, Thomas M
Sujith, R I
Lenton, Timothy M
Author_xml – sequence: 1
  givenname: Thomas M
  surname: Bury
  fullname: Bury, Thomas M
– sequence: 2
  givenname: R I
  surname: Sujith
  fullname: Sujith, R I
– sequence: 3
  givenname: Induja
  surname: Pavithran
  fullname: Pavithran, Induja
– sequence: 4
  givenname: Marten
  surname: Scheffer
  fullname: Scheffer, Marten
– sequence: 5
  givenname: Timothy M
  surname: Lenton
  fullname: Lenton, Timothy M
– sequence: 6
  givenname: Madhur
  surname: Anand
  fullname: Anand, Madhur
– sequence: 7
  givenname: Chris T
  surname: Bauch
  fullname: Bauch, Chris T
BookMark eNpNjD1PwzAURS1UJNrCzOqRJeU9x7H9RlQ-pUosMFemfqmCgm3iVIh_TxAdmO7Rubp3IWYxRRbiEmGFYOvrHH1ZKQSDGhDdiZgjEFZGE8z-8ZlYlPIOANQ4mAu6Zc6yZz_ELu5lmwY5cf8tv46mdPvo-yJTK8cu51-VUxfHci5O26ngi2Muxev93cv6sdo8PzytbzbVrrboKhfY1-RCq1pC57WlN62cIcvOowqsLZKzriETdNBQ1xR8owEYjSflWC3F1d9vHtLngcu4_ejKjvveR06HslWNbcBMe6V-ABcIS-M
CitedBy_id crossref_primary_10_1016_j_enggeo_2025_108261
crossref_primary_10_1103_Physics_17_110
crossref_primary_10_1103_PhysRevResearch_5_043209
crossref_primary_10_1063_5_0214733
crossref_primary_10_1098_rsif_2024_0864
crossref_primary_10_1038_s42256_024_00957_w
crossref_primary_10_1029_2023AV001148
crossref_primary_10_1073_pnas_2207720119
crossref_primary_10_1007_s10712_024_09833_z
crossref_primary_10_1038_s42005_025_02172_4
crossref_primary_10_1038_s42256_024_00937_0
crossref_primary_10_1140_epjp_s13360_023_03939_w
crossref_primary_10_1038_s42005_023_01379_7
crossref_primary_10_1016_j_physa_2023_129401
crossref_primary_10_1016_j_physa_2024_129868
crossref_primary_10_1016_j_cosust_2025_101526
crossref_primary_10_1016_j_cnsns_2023_107665
crossref_primary_10_1038_s41598_024_61365_z
crossref_primary_10_1016_j_chaos_2025_116853
crossref_primary_10_1016_j_cie_2025_111110
crossref_primary_10_1016_j_physrep_2025_09_003
crossref_primary_10_1371_journal_pcbi_1012782
crossref_primary_10_1016_j_plrev_2022_09_005
crossref_primary_10_1038_s41467_023_43744_8
crossref_primary_10_1063_5_0242626
crossref_primary_10_1111_2041_210X_14013
crossref_primary_10_1109_TASE_2024_3384504
crossref_primary_10_1063_5_0245575
crossref_primary_10_1109_ACCESS_2022_3186444
crossref_primary_10_7554_eLife_93694_3
crossref_primary_10_1155_2022_3202099
crossref_primary_10_1016_j_mbs_2024_109264
crossref_primary_10_1017_sus_2024_15
crossref_primary_10_1088_1402_4896_acde20
crossref_primary_10_1017_nws_2023_10
crossref_primary_10_3934_mbe_2025101
crossref_primary_10_1016_j_oneear_2024_04_004
crossref_primary_10_1016_j_isci_2025_111924
crossref_primary_10_1038_s41893_023_01157_x
crossref_primary_10_1016_j_physleta_2025_130626
crossref_primary_10_1038_s41612_024_00768_1
crossref_primary_10_1093_comnet_cnad018
crossref_primary_10_1016_j_physa_2024_129563
crossref_primary_10_1007_s11214_024_01081_2
crossref_primary_10_1016_j_scitotenv_2023_168487
crossref_primary_10_1038_s41558_025_02328_8
crossref_primary_10_1007_s12080_024_00593_5
crossref_primary_10_1038_s41467_023_44609_w
crossref_primary_10_1073_pnas_2210407119
crossref_primary_10_1098_rspa_2025_0376
crossref_primary_10_1016_j_ecoinf_2024_102889
crossref_primary_10_1155_2022_7653766
crossref_primary_10_1111_ecog_06674
crossref_primary_10_1016_j_scitotenv_2023_164169
crossref_primary_10_1073_pnas_2416637122
crossref_primary_10_1016_j_mbs_2023_109075
crossref_primary_10_5194_essd_14_5267_2022
crossref_primary_10_1098_rspa_2025_0405
crossref_primary_10_1002_ecy_4240
crossref_primary_10_1038_s41467_023_42020_z
crossref_primary_10_1007_s11071_025_10977_9
crossref_primary_10_1126_science_abn7950
crossref_primary_10_1007_s00603_025_04728_w
crossref_primary_10_5194_esd_15_947_2024
crossref_primary_10_5194_esd_15_1179_2024
crossref_primary_10_1016_j_tree_2025_07_003
crossref_primary_10_1016_j_ebiom_2023_104939
crossref_primary_10_1016_j_biotechadv_2023_108204
crossref_primary_10_1016_j_physa_2022_127929
crossref_primary_10_1103_jc9p_m3rn
crossref_primary_10_3390_e27020113
crossref_primary_10_1038_s41598_025_06525_5
crossref_primary_10_1080_21693277_2022_2155263
crossref_primary_10_1098_rsos_242240
crossref_primary_10_1109_JAS_2023_123537
crossref_primary_10_3389_feart_2022_786829
crossref_primary_10_1016_j_plrev_2024_11_004
crossref_primary_10_3390_informatics11030047
crossref_primary_10_1098_rsif_2025_0046
crossref_primary_10_5194_esd_16_1503_2025
crossref_primary_10_1007_s11071_025_10877_y
crossref_primary_10_1093_bioinformatics_btae525
crossref_primary_10_1140_epjs_s11734_023_00781_0
crossref_primary_10_1080_14747731_2022_2117500
crossref_primary_10_1016_j_jcp_2023_111953
crossref_primary_10_1103_PhysRevResearch_6_013013
crossref_primary_10_1098_rsos_231767
crossref_primary_10_1016_j_physa_2025_130401
crossref_primary_10_1016_j_scs_2021_103581
crossref_primary_10_1103_y9gq_yjxy
crossref_primary_10_1111_1751_7915_14222
crossref_primary_10_3390_e26121050
crossref_primary_10_7554_eLife_93694
crossref_primary_10_1093_bib_bbac164
crossref_primary_10_1103_PhysRevX_14_031009
crossref_primary_10_3390_e24020210
crossref_primary_10_3233_JIFS_210666
crossref_primary_10_3390_ijms25031570
crossref_primary_10_1016_j_xinn_2025_101010
crossref_primary_10_1016_j_physd_2024_134490
crossref_primary_10_1103_PhysRevResearch_6_043194
crossref_primary_10_1016_j_physd_2023_133949
crossref_primary_10_1063_5_0200898
crossref_primary_10_1103_PhysRevX_14_021037
crossref_primary_10_1111_cobi_14247
crossref_primary_10_1017_sus_2023_14
crossref_primary_10_1038_s42005_023_01210_3
crossref_primary_10_5194_esd_14_1171_2023
crossref_primary_10_1007_s12080_025_00615_w
crossref_primary_10_1038_s41598_024_68177_1
crossref_primary_10_62486_latia202583
crossref_primary_10_1111_ele_70012
crossref_primary_10_1080_13647830_2022_2080122
crossref_primary_10_1073_pnas_2115605118
crossref_primary_10_1088_1748_9326_ad4c79
crossref_primary_10_1007_s11625_023_01299_z
crossref_primary_10_1098_rsos_211475
crossref_primary_10_1038_s41559_023_01985_2
crossref_primary_10_3390_math13172782
crossref_primary_10_1016_j_aquaculture_2025_742385
ContentType Journal Article
Copyright Copyright © 2021 the Author(s). Published by PNAS.
Copyright_xml – notice: Copyright © 2021 the Author(s). Published by PNAS.
DBID 7X8
DOI 10.1073/pnas.2106140118
DatabaseName MEDLINE - Academic
DatabaseTitle MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
Database_xml – sequence: 1
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Sciences (General)
EISSN 1091-6490
GroupedDBID ---
-DZ
-~X
.55
0R~
123
29P
2AX
2FS
2WC
4.4
53G
5RE
5VS
7X8
85S
AACGO
AAFWJ
AANCE
ABBHK
ABOCM
ABPLY
ABPPZ
ABTLG
ABXSQ
ABZEH
ACGOD
ACIWK
ACNCT
ACPRK
AENEX
AEUPB
AEXZC
AFFNX
AFRAH
ALMA_UNASSIGNED_HOLDINGS
BKOMP
CS3
D0L
DCCCD
DIK
DU5
E3Z
EBS
F5P
FRP
GX1
H13
HH5
HYE
IPSME
JAAYA
JBMMH
JENOY
JHFFW
JKQEH
JLS
JLXEF
JPM
JSG
JST
KQ8
L7B
LU7
N9A
N~3
O9-
OK1
PNE
PQQKQ
R.V
RHI
RNA
RNS
RPM
RXW
SA0
SJN
TAE
TN5
UKR
W8F
WH7
WOQ
WOW
X7M
XSW
Y6R
YBH
YKV
YSK
ZCA
~02
~KM
ID FETCH-LOGICAL-c3718-8dea398df2f918a479b428697e8a12de4719878596d4d40339da5400e16a928e2
IEDL.DBID 7X8
ISSN 1091-6490
IngestDate Thu Sep 04 17:16:53 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 39
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c3718-8dea398df2f918a479b428697e8a12de4719878596d4d40339da5400e16a928e2
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
OpenAccessLink https://www.pnas.org/doi/10.1073/pnas.2106140118
PQID 2575065962
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2575065962
PublicationCentury 2000
PublicationDate 2021-09-28
PublicationDateYYYYMMDD 2021-09-28
PublicationDate_xml – month: 09
  year: 2021
  text: 2021-09-28
  day: 28
PublicationDecade 2020
PublicationTitle Proceedings of the National Academy of Sciences - PNAS
PublicationYear 2021
SSID ssj0009580
Score 2.6961288
Snippet Many natural systems exhibit tipping points where slowly changing environmental conditions spark a sudden shift to a new and sometimes very different state. As...
SourceID proquest
SourceType Aggregation Database
Title Deep learning for early warning signals of tipping points
URI https://www.proquest.com/docview/2575065962
Volume 118
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV09T8MwELWAMrAA5UN8y0gMMJgmtuP4JoSAiqliAKlb5cTnqksSSIG_j526AokFiTWKLMd5uXv2Xd4j5EL4wKtQJcxmRjCJIBnwzDLPRTApuFGZcJ3ZRD4a6fEYnuKBWxvbKpcxsQvUti7DGfnAQysLNUDFb5pXFlyjQnU1Wmiskp7wVCagOh_rH6K7eqFGAClTEpKltE8uBk1l2mve7YfCv5e_InGXXoZb_53YNtmMxJLeLpDQJytY7ZB-_HRbehn1pa92CdwjNjTaRUypZ60Ug8wx_YxXQk-HRyWtHZ13-g1T2tSzat7ukZfhw_PdI4sOCqwUPukwbdEI0NZxB6k2MofCbzcU5KhNyi36zAQ6137yVlqZCAHWeAqXYKoMcI18n6xVdYUHhCoOfkxXKC61BG6NKwHTrHDWoB8lOyTny-WZeISGsoOpsH5vJ98LdPSHe47JBg9tI6Hwo09Iz_nnxVOyXn7MZ-3bWfeCvwA4iq6K
linkProvider ProQuest
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Deep+learning+for+early+warning+signals+of+tipping+points&rft.jtitle=Proceedings+of+the+National+Academy+of+Sciences+-+PNAS&rft.au=Bury%2C+Thomas+M&rft.au=Sujith%2C+R+I&rft.au=Pavithran%2C+Induja&rft.au=Scheffer%2C+Marten&rft.date=2021-09-28&rft.issn=1091-6490&rft.eissn=1091-6490&rft.volume=118&rft.issue=39&rft_id=info:doi/10.1073%2Fpnas.2106140118&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1091-6490&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1091-6490&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1091-6490&client=summon